Home Stochastic gradient descent optimisation for convolutional neural network for medical image segmentation
Article Open Access

Stochastic gradient descent optimisation for convolutional neural network for medical image segmentation

  • Sanam Nagendram , Arunendra Singh , Gade Harish Babu , Rahul Joshi , Sandeep Dwarkanath Pande , S. K. Hasane Ahammad , Dharmesh Dhabliya and Aadarsh Bisht EMAIL logo
Published/Copyright: August 8, 2023
Download Article (PDF)
Open Life Sciences
From the journal Open Life Sciences Volume 18 Issue 1

Abstract

In accordance with the inability of various hair artefacts subjected to dermoscopic medical images, undergoing illumination challenges that include chest-Xray featuring conditions of imaging acquisi-tion situations built with clinical segmentation. The study proposed a novel deep-convolutional neural network (CNN)-integrated methodology for applying medical image segmentation upon chest-Xray and dermoscopic clinical images. The study develops a novel technique of segmenting medical images merged with CNNs with an architectural comparison that incorporates neural networks of U-net and fully convolutional networks (FCN) schemas with loss functions associated with Jaccard distance and Binary-cross entropy under optimised stochastic gradient descent + Nesterov practices. Digital image over clinical approach significantly built the diagnosis and determination of the best treatment for a patient’s condition. Even though medical digital images are subjected to varied components clarified with the effect of noise, quality, disturbance, and precision depending on the enhanced version of images segmented with the optimised process. Ultimately, the threshold technique has been employed for the output reached under the pre- and post-processing stages to contrast the image technically being developed. The data source applied is well-known in PH2 Database for Melanoma lesion segmentation and chest X-ray images since it has variations in hair artefacts and illumination. Experiment outcomes outperform other U-net and FCN architectures of CNNs. The predictions produced from the model on test images were post-processed using the threshold technique to remove the blurry boundaries around the predicted lesions. Experimental results proved that the present model has better efficiency than the existing one, such as U-net and FCN, based on the image segmented in terms of sensitivity = 0.9913, accuracy = 0.9883, and dice coefficient = 0.0246.

Keywords: machine learning; convolutional neural networks; medical chest-X-ray images; SGD

1 Introduction

Medical images have advanced due to the rapid advancement of digital technology in all areas of life. Most images are medically divided with the digital and formatting approach for the analysis [1]. Based on the challenges faced over the province of images that influence with the process of the optimised method of requesting information being structured to the principal analyst for the magnetic resonance imaging (MRI) scans subjected to the control focused into the process of computerised scam developed [2]. Further, the automatic process’s physical condition establishes a precise optimisation analysis. They additionally diagnose the automated accounting for the information passed to the clinical approach being developed into the registries with the importance of chest-Xray medical images. Several modalities that include X-ray, MRI, CT, microscopy, single photon emission computed tomography, positron emission tomography (PET) endoscopy, optical coherence tomography, and so on utilizing the creation of images clinically applied with the patients organised into body parts with separate existence of featuring image segmentation assist to the boundaries of the simulation with the simulation mounted to the insights developed under gaining the additional strategy to the region related to the diagnosis [3,4]. As per the challenges faced by the images that associate with the process of optimised approach of requesting information being structured to the principal analysis for the MRI scans subjected to the control focused into the process of CT scan developed feature learning, classifier level, and decision making [5]. Numerous approaches for image segmentation featuring enable to assist the boundaries of the simulation that is mounted to the insights developed is presented under gaining the additional strategy to the region related to the diagnosis brain image segmentation iterative deep neural network structure for medical image segmentation [6,7]. Moreover, the method utilizes an encoder–decoder system integrated an iterative design until they can improve the segmentation results in medical images that contain complex shapes recursive optimised into objective function fed to the case of appropriate functioning with the characteristics smoothing to the system provided encoder–decoder structure with 64 layers (excluding the final activation layer). Before initial sampling begins, two dense layers are present in the network’s centre [8]. Convolutional neural network (CNN) segments six textures in MRI brain images, chest muscle in MRI images, and vessels in CT cardiac images. Hence, this method is appropriate for segmenting different organs and imaging conditions [9]. Each encoder sequence has attained numerous convolutional layers under batch normalised integrated to ReLU nonlinearity observed through a sampling technique designed with the non-overlapping case for the max pooling and sub-sampling strategy. Before initial sampling begins, two dense layers are present in the network’s centre for speeding up the neural network learning process by normalizing the values in the hidden layers, like the principle behind the normalisation of features in data or activation values. This method has the potential to outperform two fully convolutional networks (FCN) and U-net architectures. Despite using up-convolutional layers and a few shortcut connections, FCN generates coarse segmentation maps. As a result, more shortcut connections are added [10]. In contrast to FCN, indices from max-pooling are copied rather than encoder features. This proposed method uses less memory than FCN. Also, the outputs produced by this method are smooth, and the borders between the region of interest (ROI) and the surrounding areas cannot be detected precisely by the physicians; therefore, we used a threshold technique as a post-processing technique to sharpen the results. The batch normalisation layer is presented after each convolution layer in the proposed network for 25 batch normalisation layers in the entire network architecture. To avoid overfitting, they used two techniques: transfer learning and data augmentation. These methods are classified into non-automatic, semi-automatic, and automatic. Because there is no human intervention in automated processes, the possibility of error is reduced.

Researchers and practitioners have been working on addressing these challenges and developing advanced optimisation algorithms and techniques that build upon stochastic gradient descent (SGD), such as momentum, adaptive learning rate methods (e.g. AdaGrad, RMSprop, Adam), and second-order optimisation methods (e.g. L-BFGS, conjugate gradient methods). These approaches aim to improve convergence speed, stability, and robustness to different problem settings.

SGD is a popular optimisation method used in CNNs for medical image segmentation. It works by updating the weights in the network based on the partial derivatives of the loss function with respect to each weight. This process is repeated iteratively for multiple epochs to minimise the loss and improve the accuracy of the model. In particular, SGD is a stochastic optimisation method, meaning that it uses a subset of the training data (known as a mini batch) to compute the gradients and update the weights at each iteration. This approach can be more efficient than using the entire training set, especially for large datasets. It is a variation of the gradient descent method, but instead of computing the gradient of the cost function over the entire dataset, it randomly selects a single data point (or a small subset of the data) at each iteration and computes the gradient based on that data point. This makes SGD much faster and more scalable than standard gradient descent, especially for large datasets. Additionally, SGD can help to avoid getting stuck in local minima by introducing randomness into the training process. Additionally, CNNs are a popular type of neural network for image segmentation tasks because they can learn to extract features from images that are relevant for the task at hand. This allows them to identify boundaries between different regions of the image and produce accurate segmentation maps. CNN involves using a deep learning model that learns to automatically identify and classify the different structures within an image. The CNN method is particularly useful for medical image segmentation because it can handle complex and heterogeneous structures, and it can adapt to different imaging modalities and resolutions. Additionally, CNNs can be trained on large amounts of data, which is important for accurate segmentation. To use the CNN method for medical image segmentation, one typically needs to prepare the training data, design the network architecture, and train the model on the data. This can involve many steps and requires expertise in deep learning and medical imaging. Certainly, CNNs and SGD are two popular methods for medical image segmentation. CNNs are a type of deep neural network commonly used for image classification and segmentation tasks. They are known for their ability to automatically extract and learn features from images, which makes them an effective method for segmentation. CNNs work by applying a series of convolutional filters to the input image, gradually learning complex patterns that help identify the ROI. SGD, on the other hand, is an optimisation algorithm commonly used to train machine learning models. It works by iteratively adjusting the weights of the model to minimise the difference between predicted and actual outputs. In the context of medical image segmentation, SGD can be used to train a variety of models, including CNNs. It is worth noting that while SGD offers these benefits, it also has some limitations and challenges, such as the sensitivity to learning rate choice, convergence to suboptimal solutions, and potential difficulties in handling noisy or unbalanced data. However, researchers have developed numerous extensions and variations in SGD to address these challenges, making it a powerful and widely used optimisation algorithm in the machine learning community.

A medical image segmentation technique based on an optimised CNN with adaptive dropout depth calculation is proposed in “Automatic data augmentation for 3D medical image segmentation” in Medical Image Computing and Computer Assisted Intervention. The study also investigates how deep neural networks’ architectures might be learned through differential evolution for analysing medical images [11,12,13].

Overall, both CNN and SGD have their own strengths and weaknesses when it comes to medical image segmentation. CNNs are generally better suited for tasks involving large amounts of data and complex image structures. SGD can be used with a wide range of models and is particularly effective when working with smaller datasets. Ultimately, the choice of method will depend on the specific needs of the project at hand. Medical image segmentation is an active area of research in the field of medical imaging. There are several ongoing research efforts aimed at developing new and improved methods for segmenting medical images. Some of the current research areas in medical image segmentation include: (a) Deep learning-based segmentation methods: Deep learning methods such as CNNs have shown promising results in medical image segmentation. Researchers are exploring different architectures and training regimes to improve the accuracy and robustness of these methods. (b) Multi-modal segmentation: Medical images often consist of multiple modalities, such as CT and MRI scans. Researchers are developing new methods to combine information from multiple modalities to improve segmentation accuracy and reduce errors. (c) Interactive segmentation: Interactive segmentation methods allow clinicians to interact with the segmentation algorithm to refine the results. Researchers are exploring new ways of integrating feedback from clinicians to improve the accuracy and efficiency of the segmentation process. (d) Domain adaptation: Medical images can vary significantly depending on the imaging modality, patient population, and other factors. Researchers are developing methods for adapting segmentation algorithms to new imaging domains to improve generalisation and reduce the need for large amounts of training data. Overall, medical image segmentation remains an active and exciting area of research, with many opportunities for innovation and improvement.

The performance metrics depends on the specific segmentation task, the target structure, and the evaluation criteria defined in the research or application context. CNNs and their variants, such as U-Net, SegNet, and DenseNet, have been widely used for medical image segmentation due to their ability to learn complex patterns and hierarchical representations. Researchers have explored architectures and modifications to improve segmentation accuracy, including skip connections, residual connections, attention mechanisms, and spatial context aggregation modules. Attention mechanisms: Attention mechanisms have gained popularity in medical image segmentation to selectively focus on relevant regions or features. Techniques such as channel attention, spatial attention, and self-attention mechanisms have been applied to improve the localisation and segmentation of target structures. Generative adversarial networks (GANs): GANs have been utilised for medical image segmentation to generate realistic and accurate segmentation masks. Adversarial training frameworks, such as Conditional GANs (cGANs) and pix2pix, have been used to enhance the quality of segmentation outputs. Multi-modality fusion: Integration of information from multiple imaging modalities, such as MRI, CT, PET, or ultrasound, has been explored to improve segmentation performance. Fusion techniques, including early fusion, late fusion, and multi-branch architectures, have been investigated to leverage complementary information from different modalities. Uncertainty estimation: Estimating uncertainty in medical image segmentation is important for assessing the reliability of the segmentation results [14,15,16,17,18]. Bayesian methods, dropout sampling, Monte Carlo sampling, and ensemble-based techniques have been applied to estimate uncertainty and provide confidence measures for segmentation predictions.

Structure of the research article is as follows: Section 2 describes the related works associated with the medical image segmentation. Section 3 presents the proposed methodology. Section 4 deals with the network architecture. Image augmentation process with the network configurations for the training, testing, and validation is explained in Section 5. Section 6 contains experimental data, its results, and design. Section 7 gives the comparative analysis. Section 8 demonstrates the results and discussions followed by conclusion in Section 9.

Convergence times for SGD can be lengthy, particularly when working with huge datasets or intricate models. In contrast to other optimisation techniques, SGD only updates the model parameters based on a portion of the training data, which introduces noise and may cause delayed convergence. SGD’s performance depends greatly on the learning rate that is selected. Instable training or divergence can come from an excessive learning rate, whereas sluggish convergence might be caused by a low learning rate. Finding the ideal learning rate can be difficult and sometimes calls for manual tuning or the use of adaptive learning rate techniques. When working with sparse datasets, where most of the features have zero or extremely few values, SGD may run into problems. In flat or saddle portions in the loss landscape, when the gradient is nearly nil, SGD may have difficulty escaping. These areas can drastically slow down the algorithm’s convergence. To address this issue, researchers have suggested modifying SGD by including momentum or employing second-order optimisation techniques. Particularly when working with complicated models and scant training data, SGD is prone to overfitting. When a model performs well on training data but struggles to generalise to untried data, overfitting takes place. To deal with this issue, regularisation strategies like L1 or L2 regularisation, dropout, or early halting are frequently used.

2 Related works

As stated, [9], the physician requires many medical sources for clinical handling to develop précised rates with statistical information and patient analysis. Many computer-based algorithms have been developed in recent years to solve the problem of medical image segmentation. Among these initiatives is an iterative deep neural network structure for medical image segmentation. This method combines an encoder–decoder design with an iterative system until they can improve the segmentation results in medical images containing complex shapes. To avoid overfitting, they used two techniques: transfer learning and data augmentation. The other work proposed a method for segmenting cardiac medical images [19]. First, a YOLO neural network detects ROI, which is fed into a CNN for segmentation. Finally, a fully connected neural network classifies the segmented images, allowing the doctor to detect precisely the type of cardiac disease. Various methods demonstrated that represent for featuring image segmentation to assist the boundaries of the simulation with the simulation mounted to the insights developed under gaining the additional strategy to the region related to the diagnosis of brain image segmentation [3]. These methods are classified into non-automatic, semi-automatic, and automatic. Because there is no human intervention in automated processes, the possibility of error is reduced. Encoder–decoder structure has 64 layers (excluding the final activation layer). Each encoder sequence has attained numerous convolutional layers under batch normalised integrated to ReLU nonlinearity observed through a sampling technique designed with the non-overlapping case for the max pooling and sub-sampling strategy. Before initial sampling begins, two dense layers are present in the network’s centre.

Another approach could train a CNN to segment six textures in MRI brain images, chest muscle in muscle MRI images, and vessels in CT cardiac images. Hence, this method is appropriate for segmenting different organs and imaging conditions. Abdelhafiz et al. proposed a technique for addressing mammographic lesions using U-net neural networks [6]. In this work, batch normalisation and data augmentation improved accuracy. Fu et al. [5] developed a method for segmenting eye vessels using fully connected neural networks. This network generates an eye vessel feature map and feeds it to the CRF neural network, which generates binary images of the eye vessels. Guo et al. [7] presented the research work which examine the medical images at three levels: Challenges with the field into the province of images that are challenging with the process of optimised approach of requesting information being structured to the principal analyst for the MRI scans subjected to the control focused into the process of CT scan developed feature learning, classifier level, and decision making. They created a neural network to detect malignant tumours in various imaging conditions (CT, PET, and MRI). Emre Celebi et al. [8] developed a method for detecting skin lesions using four threshold methods. Zhou et al. [9] normalized the values in the hidden layers, like the principle behind normalizing features in data or activation values for speeding up the neural network learning process. The batch normalisation layer is presented after each convolution layer in the proposed network. Twenty-five batch normalisation layers in the entire network architecture used mean shift estimation to improve automatic skin lesion segmentation. The technique altered with a vital image placed in the appropriate precise to maintain exact orientation with the image including a mask of truth nature throughput. Many computational sequences are required for this method. Xie and Bovik [10], combined a neural network method with a genetic algorithm to segment skin lesions. CNNs have recently emerged as one of the most essential and practical algorithms for image segmentation, particularly for medical image segmentation [19]. Its algorithm has been used for brain tumour segmentation in MRI brain images [20], cardiac image segmentation [21], skin lesion segmentation using non-dermoscopic images [22], and many other medical image segmentation tasks involving different parts of the body, different organ shapes, and various artefacts.

3 The proposed method

With estimate of the applied knowledge in application of stochastic medium built with gradient descent optimisation because substitutes to the original division of gradient analysis through estimation strategy. The optimisation approach is utilised with SGD practice. It is an iterative procedure with the recursive optimised into objective function fed to the case of appropriate functioning with the characteristics smoothing to the system provided.

SGD is an optimisation algorithm used to minimise the loss function in machine learning. It works by iteratively updating the model parameters in small batches of data, instead of using the entire dataset at once. The algorithm works as follows:

  1. Initialise the model parameters with random values.

  2. Choose a random subset of the training data (called a mini batch) to feed into the model.

  3. Compute the gradient of the loss function with respect to the model parameters using the mini batch.

  4. Update the model parameters with a small step in the direction of the negative gradient.

  5. Repeat steps 2–4 until the model converges or a stopping criterion is met.

The key advantage of SGD is that it can converge faster than batch gradient descent, especially for large datasets. However, the convergence may not be as smooth, and the optimal solution may not be reached due to the stochastic nature of the algorithm.

(1) E ( w , b ) = 1 n ∑ i = 1 n L ( y i f ( x i ) ) + α R ( w ) .

Figure 1 depicts the procedure of the stochastic gradient approach operation. With estimate of the applied knowledge in application of stochastic medium built with gradient descent optimisation because substitutes to the original division of gradient analysis through estimation strategy. For one-class optimisation problems,

(2) min w , ρ , ξ 1 2 | | ω | | 2 − ρ ξ + 1 v n ∑ i = 1 n ξ i .

For w ∀ ∈ 0 ,

(3) y i = ρ + w b ξ − 1 v i ∑ n = 0 i max ( 0 , ρ − ( w , x i ) ) ,

(4) min w , ρ , ξ v 2 | | ω | | 2 + bv ξ − 1 n ∑ i = 1 n min ( ( w , x i ) + b ) ,

(5) R ( w ) = 1 2 ∑ j = 1 m w j 2 = | | w | | 2 2 ,

(6) R ( w ) = ∑ j = 1 m | w | j ,

(7) R ( w ) = ρ 2 ∑ j = 1 n w j 2 + ( 1 − ρ ξ ) ∑ j = 1 n | w | j .

Figure 1 Schematic of SGD approach [3].
Figure 1

Schematic of SGD approach [3].

It reduces the computational burden, permitting booster iterative exchange over the approach made among the decreased convergence rate, particularly with the problems concerned with high-dimensional optimisation difficulties, and provides a good overview of convergence rates. Given a set of training examples ( x 1 , y 1 ), … ( x n , y n ), where x i ∈ R m and x i ∈ R ( y i ∈ − 1,1 for classification approach) that aims for the scoring basis into the function generated by the linear systems scored for a minimal range of f ( x ) = w T x + b integrated under specific parameters of the model based on intercept built at b ∈ R . To create estimate values with a binary classification approach that simplifies within sign functionality allotted to f ( x ) . For model identification in the model parameters, training regularised into the erroneous regularised built with the formula equated as per the analysis is minimised.

For one-dimensional (1D) variables, SGD works by iteratively adjusting the value of the variable based on the gradient of the loss function with respect to the variable. The working is as follows:

  1. Initialise the variable with a random value.

  2. Compute the gradient of the loss function with respect to the variable at the current value of the variable.

  3. Update the variable by subtracting a small multiple of the gradient from the current value. The multiple is called the learning rate, and it determines how quickly the algorithm converges to the optimal value.

  4. Repeat steps 2 and 3 until the algorithm converges to the optimal value.

In SGD, step 2 is performed using a randomly selected subset of the data, rather than the entire dataset. This makes the algorithm more efficient and allows it to scale to large datasets.

(8) ω → ω + η α δ R ( w ) δ w − δ L ( w T x i + b i y i ) δ w ,

(9) η ( i ) = et α t ,

(10) η ( i ) = 1 α ( t + t 0 ) .

Figure 2 depicts the operation of gradient descent work through the 1D variable approach. This method includes two pre-processing steps on medical images that feed into the network. These steps include image resizing and image augmentation. Following that, pre-processed images are sent to the network for segmentation. For model identification in the model parameters, training regularised into the erroneous regularised built with the formula equated as per the analysis is minimised. The results are blurred segmented images. We solved this issue by employing a post-processing step that uses a threshold technique to sharpen the segmented images. Our algorithm’s sequence has been demonstrated in Figure 3.

Figure 2 Gradient descent works in the case of one-dimensional variables [7].
Figure 2

Gradient descent works in the case of one-dimensional variables [7].

Figure 3 depicts the sequential process of implemented technique with the analysis built with the process. For model identification in the model parameters, minimisation of training regularised into the erroneous regularised created with the formula equated as per the analysis. Following that, pre-processed images are sent to the network for segmentation.

Figure 3 Sequence of the implemented algorithm.
Figure 3

Sequence of the implemented algorithm.

4 Network architecture

The proposed deep neural network has an encoder–decoder structure with 64 layers (excluding the final activation layer). Each encoder sequence has attained numerous convolutional layers under batch normalised integrated to ReLU nonlinearity, observed through a sampling technique designed with the non-overlapping case for the max pooling and sub-sampling strategy. Before initial sampling begins, two dense layers are present in the network’s centre. The max pooling indices distinguish the proposed network in the performance analysis upon generating the resolution into mapping the case of featured research. It results in the retaining way to feature details for removing the non-useful features. This neural network produces smooth images without the use of any post-processing techniques. This method has the potential to outperform two FCN and U-net architectures. Despite using up-convolutional layers and a few shortcut connections, FCN generates coarse segmentation maps. As a result, more shortcut connections are added. This proposed method uses less memory than FCN. In contrast to FCN, indices from max pooling are copied rather than encoder features. Also, the outputs produced by this method are smooth, and the borders between the ROI and the surrounding areas cannot be detected precisely by the physicians; as a result, we used a threshold technique as a post-processing technique to sharpen the results, as explained in the Sections 4.1 and 4.2.

Figure 4 depicts the proposed neural network architecture. The architecture comprises a consecutive approach with nonlinear processing layers under encoding and decoding based on a classifier of pixel-wise strategy. The individual encoder can be composed based on layers convoluted with the method of batch normalisation along with ReLu with the nonlinearity approach being overlapped with the sampling process that underwent non-overlapping oriented over max pooling and sub-sampling scheme. In accordance with sparse integration, the decoding parameter can be developed by subjecting the encoding process to the unsampled case of decoding and using indices sequenced under maximum pooling with performance for highlighting the mapping process as a key case in developing the count reduction in favour of the details frequency in the images. The frequency split into the images for which the most significant analysis during the decoding process linked with the details took place was through approaching a qualitative basis at the end process.

Figure 4 Architecture of the proposed neural network.
Figure 4

Architecture of the proposed neural network.

4.1 Loss function

A loss function is a mathematical function that helps to evaluate how well a machine learning model is performing. It compares the predicted output of the model with the actual output and calculates the difference between the two. The goal is to minimise this difference in order to improve the accuracy of the machine learning model. There are many different types of loss functions, each with their own strengths and weaknesses, depending on the type of problem you are trying to solve. Both binary cross-entropy and Jaccard distance are loss functions in this case. The cross-entropy is a function that calculates how far the prediction is from the actual value for each class and then averages the class of the error by class to calculate the final loss. In this problem, each pixel has only two categories: black or white (0 or 1), depending on the mask. As a result, rather than the categorical cross-entropy originally proposed, binary integrated to cross-entropy as per loss function is utilised. The expressed formulation of binary-oriented cross-entropy was signified based on

(11) l ( y , y ˆ ) = − 1 N ∑ i = 0 N ( y * log ( y ˆ i ) + ( 1 − y ) * ( 1 − ( y ˆ i ) ) ) .  

4.2 Network training

We used 75% of the 200 images in the PH2 dataset for the training process [23]. Furthermore, the actual image count in PH2 dataset together with chest-Xray images is more significant than 150 because the number of images increases to 450 after image augmentation as pre-processing and then enters the network. We separated these images into training and validation datasets to improve network performance. 20% of these 450 images are associated with the validation dataset, while the remaining are related to the training dataset. Figure 5 depicts the network configurations of training, testing, and validation of CNN. Based on the architecture developed within the network, parameters sum up under the networking process that undergoes training steps of 33,486,874 out of 33,384,879, under the summation of non-trainable parameters of 15,982. The implementations are written in Keras, and the environment is Google.

Figure 5 Training, testing, and validation of CNN.
Figure 5

Training, testing, and validation of CNN.

5 Image augmentation

Image augmentation on training images was used to improve the model’s robustness and reduce the likelihood of overfitting. It will also enhance the image count in the dataset available within the source. Image rotation and horizontal flipping are two simple techniques used. The images are rotated around the (−40, +40) degrees in image rotation, and the images are reversed around the horizontal axis in a horizontal flip. To maintain exact orientation with the image featuring a mask of true nature throughout, the strategy transformed with a critical image positioned into the correspondent precise. As stated in Section 4, performance of the images under the count of 200–500 will improvise once the processing of training methods gets implemented. On average, 30% of the datasets accessible for a certain condition have a collection of training photos for validating groups connected with those datasets. Figure 6 shows the technique in which the image is segmented with the open data source.

Figure 6 Image augmentation technique. (a) original medical images with their corresponding masks. (b) Rotated images with their corresponding masks. (c) Horizontally flipped images with their corresponding masks.
Figure 6

Image augmentation technique. (a) original medical images with their corresponding masks. (b) Rotated images with their corresponding masks. (c) Horizontally flipped images with their corresponding masks.

5.1 Batch normalisation

Batch normalisation is a technique for speeding up the neural network learning process by normalizing the values in the hidden layers, like the principle behind normalizing features in data or activation values. The batch normalisation layer is presented after each convolution layer in the proposed network for 25 batch normalisation layers in the entire network architecture.

6 Experimental results and design

The medical datasets used include the PH2 dermoscopic dataset, which contains 200 dermoscopic images and their label masks, and the chest-Xray images, which contain 200 RGB images and their label masks. The dataset has been developed based on the experimental investigation processed to facilitate image segmentation and classification. Dermoscopic images have a resolution of 572 × 765, while chest-Xray images have a resolution of 512 × 512. Besides, the PH2 dataset was obtained from the Dermatology Service of Hospital Pedro Hispano in Matosinhos, Portugal, and the chest-Xray dataset was made available in Kaggle. With two pre-processing before feeding the medical images to the network, one of which is resizing the images to speed up the neural network, in this work, we resize and reduce the size of all medical images to 192 × 256. It significantly diminishes, as well as training time in addition to complexity, without affecting the results significantly. They also utilised RGB 8-bit images for training and evaluating our model and labelling masks to test it. The evaluation set is 20% the size of the training set, and the test set is 25% of the scope for the label mask set (50 images).

6.1 Characteristic procedures for quality evaluation for image integration methods

Image Fusion techniques’ performance is measured using a variety of metrics. The combining image procedure preserves general information by inputting images while avoiding introducing unwanted facts. The proposed neural network’s outputs are binarised into lesion masks. The proposed algorithm’s performance was evaluated by comparing computer-generated masks as output to ground truths from the label masks dataset. Performance evaluation is performed for the model developed based on the following metrics:

Assume TP, FP, TN, and FN indicate true positives, false positives, true negatives, and false negatives count.

  • Dice coefficient: Like the precision rate, Dice score (F1) means that it quantifies positive analysis that applies consequence within the false positive within the model development. It is more like precision than accuracy. We have shown the dice coefficient by DI and have calculated it by the following formula:

    DI = 2 * TP ( TP + FP ) + ( TP + FN ) .

  • Recall: Gives the measure that targets positive states under actual natures that have yielded through the output model. Within the cases of economic analysis with a false negative claim superior to recall, the metric chooses the best model among the possible ones. Recall is also known as sensitivity (SE). We can calculate Recall using the following formula:

    SE = TP TP + FN .

  • Accuracy: Accuracy approximates how close our predicted output is to the absolute ground truth. It is denoted by AC and is calculated using the following formula:

AC = TP + TN TP + FN + TN + FP .

7 Comparison with two famous architectures

We demonstrated our findings using chest-Xray medical pictures and compared them to other methods. Furthermore, we compared our results with two well-known architectures, U-net and FCN networks, and strategies implemented by Yuan et al. and Gutman et al. [24,25]. In addition, we used the chest-Xray dataset to train the algorithm on different medical images. Table 1 displays our results from the PH2 dataset.

Table 1

Comparison results with other methods, based on different optimisation algorithms, using the PH2 dataset

Method Sensitivity Accuracy Dice coefficient
FCN 85.6 97.3 62.0
U-net 93.2 91.1 65.6
The proposed method 97.2 98.1 77.3

Table 1 lists the comparative results with the other methods, based on different optimisation algorithms, using the PH2 dataset, which has robust results in medical image segmentation and has been used in many works.

We compared our method with the U-net and FCN methods, which have robust results in medical image segmentation and have been used in many works. The developed method produces better results with higher evaluation metrics than the other methods we discussed. Table 2 lists the comparative results with other methods, based on different optimisation algorithms, using the chest-Xray dataset, which has robust results in medical image segmentation and has been used in many architectures built.

Table 2

Comparison results with other methods, based on different optimisation algorithms, using the chest-X-ray dataset

Method Sensitivity Accuracy Dice coefficient
FCN 96.7 96.5 96.8
U-net 95.6 94.2 95.9
The proposed method 99.3 98.87 98.63

Figure 7 depicts the estimation of model loss. In addition, we implemented the segmentation of original images in the results. In our algorithm, we used a post-processing step that uses a threshold technique to increase the resolution of segmented images and sharpen the borders between ROI and other regions. Using this technique, we can compare the segmented outputs to their corresponding binary masks and observe the performance of our algorithm.

Figure 7 Estimation of model loss.
Figure 7

Estimation of model loss.

Figure 8 illustrates the convergence effect of SGD strategy. The ROI boundaries are clear, and specialists can detect them completely. For dermoscopic images, there are numerous complex ROIs with varying illumination that our method was able to overcome and segment the regions in these images.

Figure 8 Convergence effect of SGD strategy.
Figure 8

Convergence effect of SGD strategy.

8 Results and discussion

We implemented our algorithm in the Google collab space, and our simulation results are shown in Figures 5 and 6. We implemented our results in matlab2014 through a segmentation application with the images of medical practice. Our model performs well with blurry borders and segmented skin lesions. On the contrary, the boundaries of the ROI are evident in the results, and doctors can completely recognise the ROI and cure the patients. Furthermore, we applied two FCN and U-net methods to our dataset, but as shown in Figure 4, the ROI borders are ambiguous and unclear. Our method is a robust and precise medical image segmentation algorithm that can be applied to other medical images such as brain cancer datasets, bladder, Covid19-chest-Xray medical images, etc. This method shows each medical image’s segmentation and results. First, in Figure 5, we offer the results for dermoscopic medical images. Comparatively, the proposed technique is more robust than the remaining approaches based on the outcomes. The ROI boundaries are clear, and specialists can detect them completely. For dermoscopic images, there are numerous complex Regions of Interest with varying illumination that our method was able to overcome and segment the regions in these images. There are also illumination variations for chest-Xray images and our algorithm could overcome these problems too. Figure 9 shows the results of U-net and FCN based on the image segmented with the developed process.

Figure 9 Results of U-net and FCN. (a) Original medical images. (b) U-net segmentation results. (c) FCN segmentation results.
Figure 9

Results of U-net and FCN. (a) Original medical images. (b) U-net segmentation results. (c) FCN segmentation results.

Figure 10 depicts the final simulation outcomes with the evaluation verified through the process identified under segmentation for dermoscopic images. Figure 11 illustrates the final simulation outcomes with the assessment verified through the process identified under segmentation for chest-Xray images. Figure 12 shows the post-processed results with the truth mask built with the ground analysis of binary classification. Further, segmented and separated the texture of the lung from other parts of the chest-Xray medical images, and the Chest bone structures are visible in these images. This work can detect all problems, including lung tumours, lung or bone structure lesions, lung infections, and diseases caused by them, such as Covid19. According to the results, the proposed algorithm produces better and more accurate results than U-net and FCN. The borders between lungs and other textures in the segmented images are identical to those in the original images. In addition, we implemented the segmentation of authentic images in the results. In our algorithm, we used a post-processing step that uses a threshold technique to increase the resolution of segmented images and sharpen the borders between ROI and other regions. Using this technique, we can compare the segmented outputs to their corresponding binary masks and observe the performance of our algorithm.

Figure 10 Final simulation results. (a) Original dermoscopic images. (b) Segmentation outputs. (c) Final results.
Figure 10

Final simulation results. (a) Original dermoscopic images. (b) Segmentation outputs. (c) Final results.

Figure 11 Final simulation results. (a) Original chest-Xray images. (b) Segmentation outputs. (c) Final results.
Figure 11

Final simulation results. (a) Original chest-Xray images. (b) Segmentation outputs. (c) Final results.

Figure 12 Post-processed outputs. (a) Binary masks as ground truths. (b) Corresponding segmented outputs of each binary mask after post-processing.
Figure 12

Post-processed outputs. (a) Binary masks as ground truths. (b) Corresponding segmented outputs of each binary mask after post-processing.

9 Conclusion

This study proposed a novel deep-CNN-integrated methodology for applying medical image segmentation upon chest-Xray and dermoscopic clinical images. The research study understands the various strategies involved in the training format concerning the issues faced in deep neural networks with data sources of limited scenarios. Our loss function was created using both Jaccard distance and binary cross-entropy. Before feeding the training dataset to the network for training, the augmented set of image processing fields is underutilised. Besides the performance of specific actions on images that include rotation along with flipping moment horizontally, the technique is validated under testing aspects within the evaluated model of the network to apply statistical predictions. The projections facilitating the model for images under testing undergo a post-processing approach to meet the threshold case of diminishing the boundaries with sharpened images for better detecting the issue. All the test cases were operated at no constraint and within the data fed with Skin Lesion Analysis Towards Melanoma Detection in PH2 but rather chest-Xray medical images. The technique outperformed conventional or advanced approaches, including FCN and U-net. Results validated are compared, and it is found that the novel method is robust and reliable for detecting various conditioned images under artefacts within data acquisition through minimal processing practice. Thus, through the outcomes, it is straight to say that the technique is quite applicable for any segmentation tasks in the medical practice. The performance measures obtained in our experiments are Sensitivity = 0.9913, Accuracy = 0.9883, and Dice coefficient = 0.982. Also, future research will further develop our method for dice coefficient improvement and apply it to other well-known datasets, such as ISIC2017 and ISBI2016, as well as other medical datasets for numerous body parts.

Future scope of the research study includes adaptive learning rates, mini-batch selection strategies, regularisation techniques, parallel and distributed computing, loss function design, transfer learning, uncertainty estimation, and hardware acceleration. Advancements in these areas can lead to improved segmentation accuracy, faster convergence, and more efficient deployment of CNN models in medical imaging applications.

Acknowledgements

Authors would like to thank their respective institutes for sparing time and giving opportunity to collaborate and work on this project with their constant support.

  1. Funding information: Authors state no funding involved.

  2. Conflict of interest: Authors state no conflict of interest.

  3. Data availability statement: The datasets generated during and/or analysed during the current study are available from the corresponding author on reasonable request.

References

[1] Kim JU, Kim HG, Ro YM. Iterative deep convolutional encoder-decoder network for medical image segmentation. Presented at the 2017 39th Annual International Conference of the IEEE Engineering in Medicine and Biology Society (EMBC). Seogwipo, South Korea; 2017.10.1109/EMBC.2017.8036917Search in Google Scholar PubMed

[2] Chang Y, Song B, Jung C, Huang L. Automatic segmentation and cardiopathy classification in cardiac MRI images based on deep neural networks. Presented at the 2018 IEEE International Conference on Acoustics, Speech and Signal Processing (ICASSP). Calgary, AB, Canada; 2018.10.1109/ICASSP.2018.8461261Search in Google Scholar

[3] Işın A, Direkoğlu C, Şah M. Review of MRI-based brain tumor image segmentation using deep learning methods. Procedia Comput Sci. 2016;102:317–24.10.1016/j.procs.2016.09.407Search in Google Scholar

[4] Moeskops P, Wolterink JM, Van Der Velden BH, Gilhuijs KG, Leiner T, Viergever MA, et al. Deep learning for multi-task medical image segmentation in multiple modalities. In: Proc. International Conference on Medical Image Computing and Computer-Assisted Intervention; 2016. p. 468–86.10.1007/978-3-319-46723-8_55Search in Google Scholar

[5] Fu H, Xu Y, Wong DW, Liu J. Retinal vessel segmentation via deep learning network and fully-connected conditional random fields. Presented at the 2016 IEEE 13th international symposium on biomedical imaging (ISBI). Prague, Czech Republic; 2016.10.1109/ISBI.2016.7493362Search in Google Scholar

[6] Abdelhafiz D, Bi J, Ammar R, Yang C, Nabavi S. Convolutional neural network for automated mass segmentation in mammography. Presented at the 2018 IEEE 8th International Conference on Computational Advances in Bio and Medical Sciences (ICCABS). Las Vegas, NV, USA; 2018.10.1109/ICCABS.2018.8542071Search in Google Scholar

[7] Guo Z, Li X, Huang H, Guo N, Li Q. Deep learning-based image segmentation on multimodal medical imaging. IEEE Trans Radiat Plasma Med Sci. 2019;3(2):162–9.10.1109/TRPMS.2018.2890359Search in Google Scholar PubMed PubMed Central

[8] Emre Celebi M, Wen Q, Hwang S, Iyatomi H, Schaefer G. Lesion border detection in dermoscopy images using ensembles of thresholding methods. Skin Res Technol. 2013;19(1):e252–8.10.1111/j.1600-0846.2012.00636.xSearch in Google Scholar PubMed

[9] Zhou H, Li X, Schaefer G, Celebi ME, Miller P. Meanshift based gradient vector flow for image segmentation. ComputVis Image Understand. 2013;117(9):1004–16.10.1016/j.cviu.2012.11.015Search in Google Scholar

[10] Xie F, Bovik AC. Automatic segmentation of dermoscopy images using self-generating neural networks seeded by genetic algorithm. Pattern Recognit. 2013;46(3):1012–9.10.1016/j.patcog.2012.08.012Search in Google Scholar

[11] Xu J, Li M, Zhu Z. Automatic data augmentation for 3D medical image segmentation. In: Medical Image Computing and Computer Assisted Intervention–MICCAI 2020: 23rd International Conference. Lima, Peru: Springer International Publishing; October 4–8, 2020; p. 378–87. Proceedings, Part I 23.10.1007/978-3-030-59710-8_37Search in Google Scholar

[12] An FP, Liu JE. Medical image segmentation algorithm based on optimized convolutional neural network-adaptive dropout depth calculation. Complexity. 2020;2020:1–13.10.1155/2020/1645479Search in Google Scholar

[13] Belciug, S Learning deep neural networks’ architectures using differential evolution. Case study: Medical imaging processing. Computers Biol Med, 2022;146:105623.10.1016/j.compbiomed.2022.105623Search in Google Scholar PubMed PubMed Central

[14] Zhang T. Solving large scale linear prediction problems using stochastic gradient descent algorithms. Presented at the 21st International Conference on Machine Learning. Banff, Canada; 2004.10.1145/1015330.1015332Search in Google Scholar

[15] Avendi M, Kheradvar A, Jafarkhani H. A combined deep learning and deformable-model approach to fully automatic segmentation of the left ventricle in cardiac MRI. Med Image Anal. 2016;30:108–19.10.1016/j.media.2016.01.005Search in Google Scholar PubMed

[16] Carvalho Souza J, Diniz JOB, Ferreira JL, Franc¸a da Silva GL, Corr’ea Silva A, Cardoso de Paiva A. An automatic method for lung segmentation and reconstruction in chest X-Ray using deep neural networks. Comput Methods Prog Biomed. 2019;177:285–96.10.1016/j.cmpb.2019.06.005Search in Google Scholar PubMed

[17] Jafari M, Auer D, Francis S, Garibaldi J, Chen X. DRU-Net: an efficient deep convolutional neural network for medical image segmentation. 2020 IEEE 17th Int Symposium Biomedical Imaging (ISBI); 2020, April. p. 1144–8. IEEE.10.1109/ISBI45749.2020.9098391Search in Google Scholar

[18] Baldeon-Calisto M, Lai-Yuen SK. AdaResU-Net: Multiobjective adaptive convolutional neural network for medical image segmentation. Neurocomputing. 2020;392:325–40.10.1016/j.neucom.2019.01.110Search in Google Scholar

[19] Mendonça T, Ferreira PM, Marques JS, Marcal AR, Rozeira J. PH2 - A dermoscopic image database for research and benchmarking. Presented at the 2013 35th Annual International Conference of the IEEE Engineering in Medicine and Biology Society (EMBC). Osaka, Japan; 2013.10.1109/EMBC.2013.6610779Search in Google Scholar PubMed

[20] Pereira S, Pinto A, Alves V, Silva CA. Brain tumor segmentation using convolutional neural networks in MRI images. IEEE Trans Med Imag. 2016;35(5):1240–51.10.1109/TMI.2016.2538465Search in Google Scholar PubMed

[21] LeCun Y, Bottou L, Bengio Y, Haffner P. Gradient based learning applied to document recognition. Proceedings of the IEEE. 1998;6(11):2278–324.10.1109/5.726791Search in Google Scholar

[22] Ioffe S, Szegedy C. Batch normalization: Accelerating deep network training by reducing internal covariate shift. In: Proceedings of the 32nd International Conference on Machine LearningPMLR. Vol. 37. 2015. p. 448–56.Search in Google Scholar

[23] Jafari MH, Nasr-Esfahani E, Karimi N, Soroushmehr S, Samavi S, Najarian K. Extraction of skin lesions from nondermoscopic images using deep learning. arXiv preprint arXiv: 1609.02374; 2016.10.1109/ICPR.2016.7899656Search in Google Scholar

[24] Yuan Y, Chao M, Lo YC. Automatic skin lesion segmentation using deep fully convolutional networks with jaccard distance. IEEE Trans Med Imaging. 2017;36(9):1876–86.10.1109/TMI.2017.2695227Search in Google Scholar PubMed

[25] Gutman D, Codella NCF, Celebi E, Helba B, Marchetti M, Mishra N, et al. Skin lesion analysis toward melanoma detection: A challenge at the 2017 international symposium on biomedical imaging (ISBI), hosted by the international skin imaging collaboration (ISIC). Presented at the 2018 IEEE 15th International Symposium on Biomedical Imaging (ISBI). Washington, DC, USA; 2018.10.1109/ISBI.2018.8363547Search in Google Scholar
Received: 2023-05-22
Revised: 2023-06-16
Accepted: 2023-07-02
Published Online: 2023-08-08

© 2023 the author(s), published by De Gruyter

This work is licensed under the Creative Commons Attribution 4.0 International License.

Articles in the same Issue

  1. Biomedical Sciences
  2. Systemic investigation of inetetamab in combination with small molecules to treat HER2-overexpressing breast and gastric cancers
  3. Immunosuppressive treatment for idiopathic membranous nephropathy: An updated network meta-analysis
  4. Identifying two pathogenic variants in a patient with pigmented paravenous retinochoroidal atrophy
  5. Effects of phytoestrogens combined with cold stress on sperm parameters and testicular proteomics in rats
  6. A case of pulmonary embolism with bad warfarin anticoagulant effects caused by E. coli infection
  7. Neutrophilia with subclinical Cushing’s disease: A case report and literature review
  8. Isoimperatorin alleviates lipopolysaccharide-induced periodontitis by downregulating ERK1/2 and NF-κB pathways
  9. Immunoregulation of synovial macrophages for the treatment of osteoarthritis
  10. Novel CPLANE1 c.8948dupT (p.P2984Tfs*7) variant in a child patient with Joubert syndrome
  11. Antiphospholipid antibodies and the risk of thrombosis in myeloproliferative neoplasms
  12. Immunological responses of septic rats to combination therapy with thymosin α1 and vitamin C
  13. High glucose and high lipid induced mitochondrial dysfunction in JEG-3 cells through oxidative stress
  14. Pharmacological inhibition of the ubiquitin-specific protease 8 effectively suppresses glioblastoma cell growth
  15. Levocarnitine regulates the growth of angiotensin II-induced myocardial fibrosis cells via TIMP-1
  16. Age-related changes in peripheral T-cell subpopulations in elderly individuals: An observational study
  17. Single-cell transcription analysis reveals the tumor origin and heterogeneity of human bilateral renal clear cell carcinoma
  18. Identification of iron metabolism-related genes as diagnostic signatures in sepsis by blood transcriptomic analysis
  19. Long noncoding RNA ACART knockdown decreases 3T3-L1 preadipocyte proliferation and differentiation
  20. Surgery, adjuvant immunotherapy plus chemotherapy and radiotherapy for primary malignant melanoma of the parotid gland (PGMM): A case report
  21. Dosimetry comparison with helical tomotherapy, volumetric modulated arc therapy, and intensity-modulated radiotherapy for grade II gliomas: A single‑institution case series
  22. Soy isoflavone reduces LPS-induced acute lung injury via increasing aquaporin 1 and aquaporin 5 in rats
  23. Refractory hypokalemia with sexual dysplasia and infertility caused by 17α-hydroxylase deficiency and triple X syndrome: A case report
  24. Meta-analysis of cancer risk among end stage renal disease undergoing maintenance dialysis
  25. 6-Phosphogluconate dehydrogenase inhibition arrests growth and induces apoptosis in gastric cancer via AMPK activation and oxidative stress
  26. Experimental study on the optimization of ANM33 release in foam cells
  27. Primary retroperitoneal angiosarcoma: A case report
  28. Metabolomic analysis-identified 2-hydroxybutyric acid might be a key metabolite of severe preeclampsia
  29. Malignant pleural effusion diagnosis and therapy
  30. Effect of spaceflight on the phenotype and proteome of Escherichia coli
  31. Comparison of immunotherapy combined with stereotactic radiotherapy and targeted therapy for patients with brain metastases: A systemic review and meta-analysis
  32. Activation of hypermethylated P2RY1 mitigates gastric cancer by promoting apoptosis and inhibiting proliferation
  33. Association between the VEGFR-2 -604T/C polymorphism (rs2071559) and type 2 diabetic retinopathy
  34. The role of IL-31 and IL-34 in the diagnosis and treatment of chronic periodontitis
  35. Triple-negative mouse breast cancer initiating cells show high expression of beta1 integrin and increased malignant features
  36. mNGS facilitates the accurate diagnosis and antibiotic treatment of suspicious critical CNS infection in real practice: A retrospective study
  37. The apatinib and pemetrexed combination has antitumor and antiangiogenic effects against NSCLC
  38. Radiotherapy for primary thyroid adenoid cystic carcinoma
  39. Design and functional preliminary investigation of recombinant antigen EgG1Y162–EgG1Y162 against Echinococcus granulosus
  40. Effects of losartan in patients with NAFLD: A meta-analysis of randomized controlled trial
  41. Bibliometric analysis of METTL3: Current perspectives, highlights, and trending topics
  42. Performance comparison of three scaling algorithms in NMR-based metabolomics analysis
  43. PI3K/AKT/mTOR pathway and its related molecules participate in PROK1 silence-induced anti-tumor effects on pancreatic cancer
  44. The altered expression of cytoskeletal and synaptic remodeling proteins during epilepsy
  45. Effects of pegylated recombinant human granulocyte colony-stimulating factor on lymphocytes and white blood cells of patients with malignant tumor
  46. Prostatitis as initial manifestation of Chlamydia psittaci pneumonia diagnosed by metagenome next-generation sequencing: A case report
  47. NUDT21 relieves sevoflurane-induced neurological damage in rats by down-regulating LIMK2
  48. Association of interleukin-10 rs1800896, rs1800872, and interleukin-6 rs1800795 polymorphisms with squamous cell carcinoma risk: A meta-analysis
  49. Exosomal HBV-DNA for diagnosis and treatment monitoring of chronic hepatitis B
  50. Shear stress leads to the dysfunction of endothelial cells through the Cav-1-mediated KLF2/eNOS/ERK signaling pathway under physiological conditions
  51. Interaction between the PI3K/AKT pathway and mitochondrial autophagy in macrophages and the leukocyte count in rats with LPS-induced pulmonary infection
  52. Meta-analysis of the rs231775 locus polymorphism in the CTLA-4 gene and the susceptibility to Graves’ disease in children
  53. Cloning, subcellular localization and expression of phosphate transporter gene HvPT6 of hulless barley
  54. Coptisine mitigates diabetic nephropathy via repressing the NRLP3 inflammasome
  55. Significant elevated CXCL14 and decreased IL-39 levels in patients with tuberculosis
  56. Whole-exome sequencing applications in prenatal diagnosis of fetal bowel dilatation
  57. Gemella morbillorum infective endocarditis: A case report and literature review
  58. An unusual ectopic thymoma clonal evolution analysis: A case report
  59. Severe cumulative skin toxicity during toripalimab combined with vemurafenib following toripalimab alone
  60. Detection of V. vulnificus septic shock with ARDS using mNGS
  61. Novel rare genetic variants of familial and sporadic pulmonary atresia identified by whole-exome sequencing
  62. The influence and mechanistic action of sperm DNA fragmentation index on the outcomes of assisted reproduction technology
  63. Novel compound heterozygous mutations in TELO2 in an infant with You-Hoover-Fong syndrome: A case report and literature review
  64. ctDNA as a prognostic biomarker in resectable CLM: Systematic review and meta-analysis
  65. Diagnosis of primary amoebic meningoencephalitis by metagenomic next-generation sequencing: A case report
  66. Phylogenetic analysis of promoter regions of human Dolichol kinase (DOLK) and orthologous genes using bioinformatics tools
  67. Collagen changes in rabbit conjunctiva after conjunctival crosslinking
  68. Effects of NM23 transfection of human gastric carcinoma cells in mice
  69. Oral nifedipine and phytosterol, intravenous nicardipine, and oral nifedipine only: Three-arm, retrospective, cohort study for management of severe preeclampsia
  70. Case report of hepatic retiform hemangioendothelioma: A rare tumor treated with ultrasound-guided microwave ablation
  71. Curcumin induces apoptosis in human hepatocellular carcinoma cells by decreasing the expression of STAT3/VEGF/HIF-1α signaling
  72. Rare presentation of double-clonal Waldenström macroglobulinemia with pulmonary embolism: A case report
  73. Giant duplication of the transverse colon in an adult: A case report and literature review
  74. Ectopic thyroid tissue in the breast: A case report
  75. SDR16C5 promotes proliferation and migration and inhibits apoptosis in pancreatic cancer
  76. Vaginal metastasis from breast cancer: A case report
  77. Screening of the best time window for MSC transplantation to treat acute myocardial infarction with SDF-1α antibody-loaded targeted ultrasonic microbubbles: An in vivo study in miniswine
  78. Inhibition of TAZ impairs the migration ability of melanoma cells
  79. Molecular complexity analysis of the diagnosis of Gitelman syndrome in China
  80. Effects of maternal calcium and protein intake on the development and bone metabolism of offspring mice
  81. Identification of winter wheat pests and diseases based on improved convolutional neural network
  82. Ultra-multiplex PCR technique to guide treatment of Aspergillus-infected aortic valve prostheses
  83. Virtual high-throughput screening: Potential inhibitors targeting aminopeptidase N (CD13) and PIKfyve for SARS-CoV-2
  84. Immune checkpoint inhibitors in cancer patients with COVID-19
  85. Utility of methylene blue mixed with autologous blood in preoperative localization of pulmonary nodules and masses
  86. Integrated analysis of the microbiome and transcriptome in stomach adenocarcinoma
  87. Berberine suppressed sarcopenia insulin resistance through SIRT1-mediated mitophagy
  88. DUSP2 inhibits the progression of lupus nephritis in mice by regulating the STAT3 pathway
  89. Lung abscess by Fusobacterium nucleatum and Streptococcus spp. co-infection by mNGS: A case series
  90. Genetic alterations of KRAS and TP53 in intrahepatic cholangiocarcinoma associated with poor prognosis
  91. Granulomatous polyangiitis involving the fourth ventricle: Report of a rare case and a literature review
  92. Studying infant mortality: A demographic analysis based on data mining models
  93. Metaplastic breast carcinoma with osseous differentiation: A report of a rare case and literature review
  94. Protein Z modulates the metastasis of lung adenocarcinoma cells
  95. Inhibition of pyroptosis and apoptosis by capsaicin protects against LPS-induced acute kidney injury through TRPV1/UCP2 axis in vitro
  96. TAK-242, a toll-like receptor 4 antagonist, against brain injury by alleviates autophagy and inflammation in rats
  97. Primary mediastinum Ewing’s sarcoma with pleural effusion: A case report and literature review
  98. Association of ADRB2 gene polymorphisms and intestinal microbiota in Chinese Han adolescents
  99. Tanshinone IIA alleviates chondrocyte apoptosis and extracellular matrix degeneration by inhibiting ferroptosis
  100. Study on the cytokines related to SARS-Cov-2 in testicular cells and the interaction network between cells based on scRNA-seq data
  101. Effect of periostin on bone metabolic and autophagy factors during tooth eruption in mice
  102. HP1 induces ferroptosis of renal tubular epithelial cells through NRF2 pathway in diabetic nephropathy
  103. Intravaginal estrogen management in postmenopausal patients with vaginal squamous intraepithelial lesions along with CO2 laser ablation: A retrospective study
  104. Hepatocellular carcinoma cell differentiation trajectory predicts immunotherapy, potential therapeutic drugs, and prognosis of patients
  105. Effects of physical exercise on biomarkers of oxidative stress in healthy subjects: A meta-analysis of randomized controlled trials
  106. Identification of lysosome-related genes in connection with prognosis and immune cell infiltration for drug candidates in head and neck cancer
  107. Development of an instrument-free and low-cost ELISA dot-blot test to detect antibodies against SARS-CoV-2
  108. Research progress on gas signal molecular therapy for Parkinson’s disease
  109. Adiponectin inhibits TGF-β1-induced skin fibroblast proliferation and phenotype transformation via the p38 MAPK signaling pathway
  110. The G protein-coupled receptor-related gene signatures for predicting prognosis and immunotherapy response in bladder urothelial carcinoma
  111. α-Fetoprotein contributes to the malignant biological properties of AFP-producing gastric cancer
  112. CXCL12/CXCR4/CXCR7 axis in placenta tissues of patients with placenta previa
  113. Association between thyroid stimulating hormone levels and papillary thyroid cancer risk: A meta-analysis
  114. Significance of sTREM-1 and sST2 combined diagnosis for sepsis detection and prognosis prediction
  115. Diagnostic value of serum neuroactive substances in the acute exacerbation of chronic obstructive pulmonary disease complicated with depression
  116. Research progress of AMP-activated protein kinase and cardiac aging
  117. TRIM29 knockdown prevented the colon cancer progression through decreasing the ubiquitination levels of KRT5
  118. Cross-talk between gut microbiota and liver steatosis: Complications and therapeutic target
  119. Metastasis from small cell lung cancer to ovary: A case report
  120. The early diagnosis and pathogenic mechanisms of sepsis-related acute kidney injury
  121. The effect of NK cell therapy on sepsis secondary to lung cancer: A case report
  122. Erianin alleviates collagen-induced arthritis in mice by inhibiting Th17 cell differentiation
  123. Loss of ACOX1 in clear cell renal cell carcinoma and its correlation with clinical features
  124. Signalling pathways in the osteogenic differentiation of periodontal ligament stem cells
  125. Crosstalk between lactic acid and immune regulation and its value in the diagnosis and treatment of liver failure
  126. Clinicopathological features and differential diagnosis of gastric pleomorphic giant cell carcinoma
  127. Traumatic brain injury and rTMS-ERPs: Case report and literature review
  128. Extracellular fibrin promotes non-small cell lung cancer progression through integrin β1/PTEN/AKT signaling
  129. Knockdown of DLK4 inhibits non-small cell lung cancer tumor growth by downregulating CKS2
  130. The co-expression pattern of VEGFR-2 with indicators related to proliferation, apoptosis, and differentiation of anagen hair follicles
  131. Inflammation-related signaling pathways in tendinopathy
  132. CD4+ T cell count in HIV/TB co-infection and co-occurrence with HL: Case report and literature review
  133. Clinical analysis of severe Chlamydia psittaci pneumonia: Case series study
  134. Bioinformatics analysis to identify potential biomarkers for the pulmonary artery hypertension associated with the basement membrane
  135. Influence of MTHFR polymorphism, alone or in combination with smoking and alcohol consumption, on cancer susceptibility
  136. Catharanthus roseus (L.) G. Don counteracts the ampicillin resistance in multiple antibiotic-resistant Staphylococcus aureus by downregulation of PBP2a synthesis
  137. Combination of a bronchogenic cyst in the thoracic spinal canal with chronic myelocytic leukemia
  138. Bacterial lipoprotein plays an important role in the macrophage autophagy and apoptosis induced by Salmonella typhimurium and Staphylococcus aureus
  139. TCL1A+ B cells predict prognosis in triple-negative breast cancer through integrative analysis of single-cell and bulk transcriptomic data
  140. Ezrin promotes esophageal squamous cell carcinoma progression via the Hippo signaling pathway
  141. Ferroptosis: A potential target of macrophages in plaque vulnerability
  142. Predicting pediatric Crohn's disease based on six mRNA-constructed risk signature using comprehensive bioinformatic approaches
  143. Applications of genetic code expansion and photosensitive UAAs in studying membrane proteins
  144. HK2 contributes to the proliferation, migration, and invasion of diffuse large B-cell lymphoma cells by enhancing the ERK1/2 signaling pathway
  145. IL-17 in osteoarthritis: A narrative review
  146. Circadian cycle and neuroinflammation
  147. Probiotic management and inflammatory factors as a novel treatment in cirrhosis: A systematic review and meta-analysis
  148. Hemorrhagic meningioma with pulmonary metastasis: Case report and literature review
  149. SPOP regulates the expression profiles and alternative splicing events in human hepatocytes
  150. Knockdown of SETD5 inhibited glycolysis and tumor growth in gastric cancer cells by down-regulating Akt signaling pathway
  151. PTX3 promotes IVIG resistance-induced endothelial injury in Kawasaki disease by regulating the NF-κB pathway
  152. Pancreatic ectopic thyroid tissue: A case report and analysis of literature
  153. The prognostic impact of body mass index on female breast cancer patients in underdeveloped regions of northern China differs by menopause status and tumor molecular subtype
  154. Report on a case of liver-originating malignant melanoma of unknown primary
  155. Case report: Herbal treatment of neutropenic enterocolitis after chemotherapy for breast cancer
  156. The fibroblast growth factor–Klotho axis at molecular level
  157. Characterization of amiodarone action on currents in hERG-T618 gain-of-function mutations
  158. A case report of diagnosis and dynamic monitoring of Listeria monocytogenes meningitis with NGS
  159. Effect of autologous platelet-rich plasma on new bone formation and viability of a Marburg bone graft
  160. Small breast epithelial mucin as a useful prognostic marker for breast cancer patients
  161. Continuous non-adherent culture promotes transdifferentiation of human adipose-derived stem cells into retinal lineage
  162. Nrf3 alleviates oxidative stress and promotes the survival of colon cancer cells by activating AKT/BCL-2 signal pathway
  163. Favorable response to surufatinib in a patient with necrolytic migratory erythema: A case report
  164. Case report of atypical undernutrition of hypoproteinemia type
  165. Down-regulation of COL1A1 inhibits tumor-associated fibroblast activation and mediates matrix remodeling in the tumor microenvironment of breast cancer
  166. Sarcoma protein kinase inhibition alleviates liver fibrosis by promoting hepatic stellate cells ferroptosis
  167. Research progress of serum eosinophil in chronic obstructive pulmonary disease and asthma
  168. Clinicopathological characteristics of co-existing or mixed colorectal cancer and neuroendocrine tumor: Report of five cases
  169. Role of menopausal hormone therapy in the prevention of postmenopausal osteoporosis
  170. Precisional detection of lymph node metastasis using tFCM in colorectal cancer
  171. Advances in diagnosis and treatment of perimenopausal syndrome
  172. A study of forensic genetics: ITO index distribution and kinship judgment between two individuals
  173. Acute lupus pneumonitis resembling miliary tuberculosis: A case-based review
  174. Plasma levels of CD36 and glutathione as biomarkers for ruptured intracranial aneurysm
  175. Fractalkine modulates pulmonary angiogenesis and tube formation by modulating CX3CR1 and growth factors in PVECs
  176. Novel risk prediction models for deep vein thrombosis after thoracotomy and thoracoscopic lung cancer resections, involving coagulation and immune function
  177. Exploring the diagnostic markers of essential tremor: A study based on machine learning algorithms
  178. Evaluation of effects of small-incision approach treatment on proximal tibia fracture by deep learning algorithm-based magnetic resonance imaging
  179. An online diagnosis method for cancer lesions based on intelligent imaging analysis
  180. Medical imaging in rheumatoid arthritis: A review on deep learning approach
  181. Predictive analytics in smart healthcare for child mortality prediction using a machine learning approach
  182. Utility of neutrophil–lymphocyte ratio and platelet–lymphocyte ratio in predicting acute-on-chronic liver failure survival
  183. A biomedical decision support system for meta-analysis of bilateral upper-limb training in stroke patients with hemiplegia
  184. TNF-α and IL-8 levels are positively correlated with hypobaric hypoxic pulmonary hypertension and pulmonary vascular remodeling in rats
  185. Stochastic gradient descent optimisation for convolutional neural network for medical image segmentation
  186. Comparison of the prognostic value of four different critical illness scores in patients with sepsis-induced coagulopathy
  187. Application and teaching of computer molecular simulation embedded technology and artificial intelligence in drug research and development
  188. Hepatobiliary surgery based on intelligent image segmentation technology
  189. Value of brain injury-related indicators based on neural network in the diagnosis of neonatal hypoxic-ischemic encephalopathy
  190. Analysis of early diagnosis methods for asymmetric dementia in brain MR images based on genetic medical technology
  191. Early diagnosis for the onset of peri-implantitis based on artificial neural network
  192. Clinical significance of the detection of serum IgG4 and IgG4/IgG ratio in patients with thyroid-associated ophthalmopathy
  193. Forecast of pain degree of lumbar disc herniation based on back propagation neural network
  194. SPA-UNet: A liver tumor segmentation network based on fused multi-scale features
  195. Systematic evaluation of clinical efficacy of CYP1B1 gene polymorphism in EGFR mutant non-small cell lung cancer observed by medical image
  196. Rehabilitation effect of intelligent rehabilitation training system on hemiplegic limb spasms after stroke
  197. A novel approach for minimising anti-aliasing effects in EEG data acquisition
  198. ErbB4 promotes M2 activation of macrophages in idiopathic pulmonary fibrosis
  199. Clinical role of CYP1B1 gene polymorphism in prediction of postoperative chemotherapy efficacy in NSCLC based on individualized health model
  200. Lung nodule segmentation via semi-residual multi-resolution neural networks
  201. Evaluation of brain nerve function in ICU patients with Delirium by deep learning algorithm-based resting state MRI
  202. A data mining technique for detecting malignant mesothelioma cancer using multiple regression analysis
  203. Markov model combined with MR diffusion tensor imaging for predicting the onset of Alzheimer’s disease
  204. Effectiveness of the treatment of depression associated with cancer and neuroimaging changes in depression-related brain regions in patients treated with the mediator-deuterium acupuncture method
  205. Molecular mechanism of colorectal cancer and screening of molecular markers based on bioinformatics analysis
  206. Monitoring and evaluation of anesthesia depth status data based on neuroscience
  207. Exploring the conformational dynamics and thermodynamics of EGFR S768I and G719X + S768I mutations in non-small cell lung cancer: An in silico approaches
  208. Optimised feature selection-driven convolutional neural network using gray level co-occurrence matrix for detection of cervical cancer
  209. Incidence of different pressure patterns of spinal cerebellar ataxia and analysis of imaging and genetic diagnosis
  210. Pathogenic bacteria and treatment resistance in older cardiovascular disease patients with lung infection and risk prediction model
  211. Adoption value of support vector machine algorithm-based computed tomography imaging in the diagnosis of secondary pulmonary fungal infections in patients with malignant hematological disorders
  212. From slides to insights: Harnessing deep learning for prognostic survival prediction in human colorectal cancer histology
  213. Ecology and Environmental Science
  214. Monitoring of hourly carbon dioxide concentration under different land use types in arid ecosystem
  215. Comparing the differences of prokaryotic microbial community between pit walls and bottom from Chinese liquor revealed by 16S rRNA gene sequencing
  216. Effects of cadmium stress on fruits germination and growth of two herbage species
  217. Bamboo charcoal affects soil properties and bacterial community in tea plantations
  218. Optimization of biogas potential using kinetic models, response surface methodology, and instrumental evidence for biodegradation of tannery fleshings during anaerobic digestion
  219. Understory vegetation diversity patterns of Platycladus orientalis and Pinus elliottii communities in Central and Southern China
  220. Studies on macrofungi diversity and discovery of new species of Abortiporus from Baotianman World Biosphere Reserve
  221. Food Science
  222. Effect of berrycactus fruit (Myrtillocactus geometrizans) on glutamate, glutamine, and GABA levels in the frontal cortex of rats fed with a high-fat diet
  223. Guesstimate of thymoquinone diversity in Nigella sativa L. genotypes and elite varieties collected from Indian states using HPTLC technique
  224. Analysis of bacterial community structure of Fuzhuan tea with different processing techniques
  225. Untargeted metabolomics reveals sour jujube kernel benefiting the nutritional value and flavor of Morchella esculenta
  226. Mycobiota in Slovak wine grapes: A case study from the small Carpathians wine region
  227. Elemental analysis of Fadogia ancylantha leaves used as a nutraceutical in Mashonaland West Province, Zimbabwe
  228. Microbiological transglutaminase: Biotechnological application in the food industry
  229. Influence of solvent-free extraction of fish oil from catfish (Clarias magur) heads using a Taguchi orthogonal array design: A qualitative and quantitative approach
  230. Chromatographic analysis of the chemical composition and anticancer activities of Curcuma longa extract cultivated in Palestine
  231. The potential for the use of leghemoglobin and plant ferritin as sources of iron
  232. Investigating the association between dietary patterns and glycemic control among children and adolescents with T1DM
  233. Bioengineering and Biotechnology
  234. Biocompatibility and osteointegration capability of β-TCP manufactured by stereolithography 3D printing: In vitro study
  235. Clinical characteristics and the prognosis of diabetic foot in Tibet: A single center, retrospective study
  236. Agriculture
  237. Biofertilizer and NPSB fertilizer application effects on nodulation and productivity of common bean (Phaseolus vulgaris L.) at Sodo Zuria, Southern Ethiopia
  238. On correlation between canopy vegetation and growth indexes of maize varieties with different nitrogen efficiencies
  239. Exopolysaccharides from Pseudomonas tolaasii inhibit the growth of Pleurotus ostreatus mycelia
  240. A transcriptomic evaluation of the mechanism of programmed cell death of the replaceable bud in Chinese chestnut
  241. Melatonin enhances salt tolerance in sorghum by modulating photosynthetic performance, osmoregulation, antioxidant defense, and ion homeostasis
  242. Effects of plant density on alfalfa (Medicago sativa L.) seed yield in western Heilongjiang areas
  243. Identification of rice leaf diseases and deficiency disorders using a novel DeepBatch technique
  244. Artificial intelligence and internet of things oriented sustainable precision farming: Towards modern agriculture
  245. Animal Sciences
  246. Effect of ketogenic diet on exercise tolerance and transcriptome of gastrocnemius in mice
  247. Combined analysis of mRNA–miRNA from testis tissue in Tibetan sheep with different FecB genotypes
  248. Isolation, identification, and drug resistance of a partially isolated bacterium from the gill of Siniperca chuatsi
  249. Tracking behavioral changes of confined sows from the first mating to the third parity
  250. The sequencing of the key genes and end products in the TLR4 signaling pathway from the kidney of Rana dybowskii exposed to Aeromonas hydrophila
  251. Development of a new candidate vaccine against piglet diarrhea caused by Escherichia coli
  252. Plant Sciences
  253. Crown and diameter structure of pure Pinus massoniana Lamb. forest in Hunan province, China
  254. Genetic evaluation and germplasm identification analysis on ITS2, trnL-F, and psbA-trnH of alfalfa varieties germplasm resources
  255. Tissue culture and rapid propagation technology for Gentiana rhodantha
  256. Effects of cadmium on the synthesis of active ingredients in Salvia miltiorrhiza
  257. Cloning and expression analysis of VrNAC13 gene in mung bean
  258. Chlorate-induced molecular floral transition revealed by transcriptomes
  259. Effects of warming and drought on growth and development of soybean in Hailun region
  260. Effects of different light conditions on transient expression and biomass in Nicotiana benthamiana leaves
  261. Comparative analysis of the rhizosphere microbiome and medicinally active ingredients of Atractylodes lancea from different geographical origins
  262. Distinguish Dianthus species or varieties based on chloroplast genomes
  263. Comparative transcriptomes reveal molecular mechanisms of apple blossoms of different tolerance genotypes to chilling injury
  264. Study on fresh processing key technology and quality influence of Cut Ophiopogonis Radix based on multi-index evaluation
  265. An advanced approach for fig leaf disease detection and classification: Leveraging image processing and enhanced support vector machine methodology
  266. Erratum
  267. Erratum to “Protein Z modulates the metastasis of lung adenocarcinoma cells”
  268. Erratum to “BRCA1 subcellular localization regulated by PI3K signaling pathway in triple-negative breast cancer MDA-MB-231 cells and hormone-sensitive T47D cells”
  269. Retraction
  270. Retraction to “Protocatechuic acid attenuates cerebral aneurysm formation and progression by inhibiting TNF-alpha/Nrf-2/NF-kB-mediated inflammatory mechanisms in experimental rats”
https://doi.org/10.1515/biol-2022-0665
Keywords for this article
machine learning; convolutional neural networks; medical chest-X-ray images; SGD
Creative Commons
BY 4.0

Articles in the same Issue

  1. Biomedical Sciences
  2. Systemic investigation of inetetamab in combination with small molecules to treat HER2-overexpressing breast and gastric cancers
  3. Immunosuppressive treatment for idiopathic membranous nephropathy: An updated network meta-analysis
  4. Identifying two pathogenic variants in a patient with pigmented paravenous retinochoroidal atrophy
  5. Effects of phytoestrogens combined with cold stress on sperm parameters and testicular proteomics in rats
  6. A case of pulmonary embolism with bad warfarin anticoagulant effects caused by E. coli infection
  7. Neutrophilia with subclinical Cushing’s disease: A case report and literature review
  8. Isoimperatorin alleviates lipopolysaccharide-induced periodontitis by downregulating ERK1/2 and NF-κB pathways
  9. Immunoregulation of synovial macrophages for the treatment of osteoarthritis
  10. Novel CPLANE1 c.8948dupT (p.P2984Tfs*7) variant in a child patient with Joubert syndrome
  11. Antiphospholipid antibodies and the risk of thrombosis in myeloproliferative neoplasms
  12. Immunological responses of septic rats to combination therapy with thymosin α1 and vitamin C
  13. High glucose and high lipid induced mitochondrial dysfunction in JEG-3 cells through oxidative stress
  14. Pharmacological inhibition of the ubiquitin-specific protease 8 effectively suppresses glioblastoma cell growth
  15. Levocarnitine regulates the growth of angiotensin II-induced myocardial fibrosis cells via TIMP-1
  16. Age-related changes in peripheral T-cell subpopulations in elderly individuals: An observational study
  17. Single-cell transcription analysis reveals the tumor origin and heterogeneity of human bilateral renal clear cell carcinoma
  18. Identification of iron metabolism-related genes as diagnostic signatures in sepsis by blood transcriptomic analysis
  19. Long noncoding RNA ACART knockdown decreases 3T3-L1 preadipocyte proliferation and differentiation
  20. Surgery, adjuvant immunotherapy plus chemotherapy and radiotherapy for primary malignant melanoma of the parotid gland (PGMM): A case report
  21. Dosimetry comparison with helical tomotherapy, volumetric modulated arc therapy, and intensity-modulated radiotherapy for grade II gliomas: A single‑institution case series
  22. Soy isoflavone reduces LPS-induced acute lung injury via increasing aquaporin 1 and aquaporin 5 in rats
  23. Refractory hypokalemia with sexual dysplasia and infertility caused by 17α-hydroxylase deficiency and triple X syndrome: A case report
  24. Meta-analysis of cancer risk among end stage renal disease undergoing maintenance dialysis
  25. 6-Phosphogluconate dehydrogenase inhibition arrests growth and induces apoptosis in gastric cancer via AMPK activation and oxidative stress
  26. Experimental study on the optimization of ANM33 release in foam cells
  27. Primary retroperitoneal angiosarcoma: A case report
  28. Metabolomic analysis-identified 2-hydroxybutyric acid might be a key metabolite of severe preeclampsia
  29. Malignant pleural effusion diagnosis and therapy
  30. Effect of spaceflight on the phenotype and proteome of Escherichia coli
  31. Comparison of immunotherapy combined with stereotactic radiotherapy and targeted therapy for patients with brain metastases: A systemic review and meta-analysis
  32. Activation of hypermethylated P2RY1 mitigates gastric cancer by promoting apoptosis and inhibiting proliferation
  33. Association between the VEGFR-2 -604T/C polymorphism (rs2071559) and type 2 diabetic retinopathy
  34. The role of IL-31 and IL-34 in the diagnosis and treatment of chronic periodontitis
  35. Triple-negative mouse breast cancer initiating cells show high expression of beta1 integrin and increased malignant features
  36. mNGS facilitates the accurate diagnosis and antibiotic treatment of suspicious critical CNS infection in real practice: A retrospective study
  37. The apatinib and pemetrexed combination has antitumor and antiangiogenic effects against NSCLC
  38. Radiotherapy for primary thyroid adenoid cystic carcinoma
  39. Design and functional preliminary investigation of recombinant antigen EgG1Y162–EgG1Y162 against Echinococcus granulosus
  40. Effects of losartan in patients with NAFLD: A meta-analysis of randomized controlled trial
  41. Bibliometric analysis of METTL3: Current perspectives, highlights, and trending topics
  42. Performance comparison of three scaling algorithms in NMR-based metabolomics analysis
  43. PI3K/AKT/mTOR pathway and its related molecules participate in PROK1 silence-induced anti-tumor effects on pancreatic cancer
  44. The altered expression of cytoskeletal and synaptic remodeling proteins during epilepsy
  45. Effects of pegylated recombinant human granulocyte colony-stimulating factor on lymphocytes and white blood cells of patients with malignant tumor
  46. Prostatitis as initial manifestation of Chlamydia psittaci pneumonia diagnosed by metagenome next-generation sequencing: A case report
  47. NUDT21 relieves sevoflurane-induced neurological damage in rats by down-regulating LIMK2
  48. Association of interleukin-10 rs1800896, rs1800872, and interleukin-6 rs1800795 polymorphisms with squamous cell carcinoma risk: A meta-analysis
  49. Exosomal HBV-DNA for diagnosis and treatment monitoring of chronic hepatitis B
  50. Shear stress leads to the dysfunction of endothelial cells through the Cav-1-mediated KLF2/eNOS/ERK signaling pathway under physiological conditions
  51. Interaction between the PI3K/AKT pathway and mitochondrial autophagy in macrophages and the leukocyte count in rats with LPS-induced pulmonary infection
  52. Meta-analysis of the rs231775 locus polymorphism in the CTLA-4 gene and the susceptibility to Graves’ disease in children
  53. Cloning, subcellular localization and expression of phosphate transporter gene HvPT6 of hulless barley
  54. Coptisine mitigates diabetic nephropathy via repressing the NRLP3 inflammasome
  55. Significant elevated CXCL14 and decreased IL-39 levels in patients with tuberculosis
  56. Whole-exome sequencing applications in prenatal diagnosis of fetal bowel dilatation
  57. Gemella morbillorum infective endocarditis: A case report and literature review
  58. An unusual ectopic thymoma clonal evolution analysis: A case report
  59. Severe cumulative skin toxicity during toripalimab combined with vemurafenib following toripalimab alone
  60. Detection of V. vulnificus septic shock with ARDS using mNGS
  61. Novel rare genetic variants of familial and sporadic pulmonary atresia identified by whole-exome sequencing
  62. The influence and mechanistic action of sperm DNA fragmentation index on the outcomes of assisted reproduction technology
  63. Novel compound heterozygous mutations in TELO2 in an infant with You-Hoover-Fong syndrome: A case report and literature review
  64. ctDNA as a prognostic biomarker in resectable CLM: Systematic review and meta-analysis
  65. Diagnosis of primary amoebic meningoencephalitis by metagenomic next-generation sequencing: A case report
  66. Phylogenetic analysis of promoter regions of human Dolichol kinase (DOLK) and orthologous genes using bioinformatics tools
  67. Collagen changes in rabbit conjunctiva after conjunctival crosslinking
  68. Effects of NM23 transfection of human gastric carcinoma cells in mice
  69. Oral nifedipine and phytosterol, intravenous nicardipine, and oral nifedipine only: Three-arm, retrospective, cohort study for management of severe preeclampsia
  70. Case report of hepatic retiform hemangioendothelioma: A rare tumor treated with ultrasound-guided microwave ablation
  71. Curcumin induces apoptosis in human hepatocellular carcinoma cells by decreasing the expression of STAT3/VEGF/HIF-1α signaling
  72. Rare presentation of double-clonal Waldenström macroglobulinemia with pulmonary embolism: A case report
  73. Giant duplication of the transverse colon in an adult: A case report and literature review
  74. Ectopic thyroid tissue in the breast: A case report
  75. SDR16C5 promotes proliferation and migration and inhibits apoptosis in pancreatic cancer
  76. Vaginal metastasis from breast cancer: A case report
  77. Screening of the best time window for MSC transplantation to treat acute myocardial infarction with SDF-1α antibody-loaded targeted ultrasonic microbubbles: An in vivo study in miniswine
  78. Inhibition of TAZ impairs the migration ability of melanoma cells
  79. Molecular complexity analysis of the diagnosis of Gitelman syndrome in China
  80. Effects of maternal calcium and protein intake on the development and bone metabolism of offspring mice
  81. Identification of winter wheat pests and diseases based on improved convolutional neural network
  82. Ultra-multiplex PCR technique to guide treatment of Aspergillus-infected aortic valve prostheses
  83. Virtual high-throughput screening: Potential inhibitors targeting aminopeptidase N (CD13) and PIKfyve for SARS-CoV-2
  84. Immune checkpoint inhibitors in cancer patients with COVID-19
  85. Utility of methylene blue mixed with autologous blood in preoperative localization of pulmonary nodules and masses
  86. Integrated analysis of the microbiome and transcriptome in stomach adenocarcinoma
  87. Berberine suppressed sarcopenia insulin resistance through SIRT1-mediated mitophagy
  88. DUSP2 inhibits the progression of lupus nephritis in mice by regulating the STAT3 pathway
  89. Lung abscess by Fusobacterium nucleatum and Streptococcus spp. co-infection by mNGS: A case series
  90. Genetic alterations of KRAS and TP53 in intrahepatic cholangiocarcinoma associated with poor prognosis
  91. Granulomatous polyangiitis involving the fourth ventricle: Report of a rare case and a literature review
  92. Studying infant mortality: A demographic analysis based on data mining models
  93. Metaplastic breast carcinoma with osseous differentiation: A report of a rare case and literature review
  94. Protein Z modulates the metastasis of lung adenocarcinoma cells
  95. Inhibition of pyroptosis and apoptosis by capsaicin protects against LPS-induced acute kidney injury through TRPV1/UCP2 axis in vitro
  96. TAK-242, a toll-like receptor 4 antagonist, against brain injury by alleviates autophagy and inflammation in rats
  97. Primary mediastinum Ewing’s sarcoma with pleural effusion: A case report and literature review
  98. Association of ADRB2 gene polymorphisms and intestinal microbiota in Chinese Han adolescents
  99. Tanshinone IIA alleviates chondrocyte apoptosis and extracellular matrix degeneration by inhibiting ferroptosis
  100. Study on the cytokines related to SARS-Cov-2 in testicular cells and the interaction network between cells based on scRNA-seq data
  101. Effect of periostin on bone metabolic and autophagy factors during tooth eruption in mice
  102. HP1 induces ferroptosis of renal tubular epithelial cells through NRF2 pathway in diabetic nephropathy
  103. Intravaginal estrogen management in postmenopausal patients with vaginal squamous intraepithelial lesions along with CO2 laser ablation: A retrospective study
  104. Hepatocellular carcinoma cell differentiation trajectory predicts immunotherapy, potential therapeutic drugs, and prognosis of patients
  105. Effects of physical exercise on biomarkers of oxidative stress in healthy subjects: A meta-analysis of randomized controlled trials
  106. Identification of lysosome-related genes in connection with prognosis and immune cell infiltration for drug candidates in head and neck cancer
  107. Development of an instrument-free and low-cost ELISA dot-blot test to detect antibodies against SARS-CoV-2
  108. Research progress on gas signal molecular therapy for Parkinson’s disease
  109. Adiponectin inhibits TGF-β1-induced skin fibroblast proliferation and phenotype transformation via the p38 MAPK signaling pathway
  110. The G protein-coupled receptor-related gene signatures for predicting prognosis and immunotherapy response in bladder urothelial carcinoma
  111. α-Fetoprotein contributes to the malignant biological properties of AFP-producing gastric cancer
  112. CXCL12/CXCR4/CXCR7 axis in placenta tissues of patients with placenta previa
  113. Association between thyroid stimulating hormone levels and papillary thyroid cancer risk: A meta-analysis
  114. Significance of sTREM-1 and sST2 combined diagnosis for sepsis detection and prognosis prediction
  115. Diagnostic value of serum neuroactive substances in the acute exacerbation of chronic obstructive pulmonary disease complicated with depression
  116. Research progress of AMP-activated protein kinase and cardiac aging
  117. TRIM29 knockdown prevented the colon cancer progression through decreasing the ubiquitination levels of KRT5
  118. Cross-talk between gut microbiota and liver steatosis: Complications and therapeutic target
  119. Metastasis from small cell lung cancer to ovary: A case report
  120. The early diagnosis and pathogenic mechanisms of sepsis-related acute kidney injury
  121. The effect of NK cell therapy on sepsis secondary to lung cancer: A case report
  122. Erianin alleviates collagen-induced arthritis in mice by inhibiting Th17 cell differentiation
  123. Loss of ACOX1 in clear cell renal cell carcinoma and its correlation with clinical features
  124. Signalling pathways in the osteogenic differentiation of periodontal ligament stem cells
  125. Crosstalk between lactic acid and immune regulation and its value in the diagnosis and treatment of liver failure
  126. Clinicopathological features and differential diagnosis of gastric pleomorphic giant cell carcinoma
  127. Traumatic brain injury and rTMS-ERPs: Case report and literature review
  128. Extracellular fibrin promotes non-small cell lung cancer progression through integrin β1/PTEN/AKT signaling
  129. Knockdown of DLK4 inhibits non-small cell lung cancer tumor growth by downregulating CKS2
  130. The co-expression pattern of VEGFR-2 with indicators related to proliferation, apoptosis, and differentiation of anagen hair follicles
  131. Inflammation-related signaling pathways in tendinopathy
  132. CD4+ T cell count in HIV/TB co-infection and co-occurrence with HL: Case report and literature review
  133. Clinical analysis of severe Chlamydia psittaci pneumonia: Case series study
  134. Bioinformatics analysis to identify potential biomarkers for the pulmonary artery hypertension associated with the basement membrane
  135. Influence of MTHFR polymorphism, alone or in combination with smoking and alcohol consumption, on cancer susceptibility
  136. Catharanthus roseus (L.) G. Don counteracts the ampicillin resistance in multiple antibiotic-resistant Staphylococcus aureus by downregulation of PBP2a synthesis
  137. Combination of a bronchogenic cyst in the thoracic spinal canal with chronic myelocytic leukemia
  138. Bacterial lipoprotein plays an important role in the macrophage autophagy and apoptosis induced by Salmonella typhimurium and Staphylococcus aureus
  139. TCL1A+ B cells predict prognosis in triple-negative breast cancer through integrative analysis of single-cell and bulk transcriptomic data
  140. Ezrin promotes esophageal squamous cell carcinoma progression via the Hippo signaling pathway
  141. Ferroptosis: A potential target of macrophages in plaque vulnerability
  142. Predicting pediatric Crohn's disease based on six mRNA-constructed risk signature using comprehensive bioinformatic approaches
  143. Applications of genetic code expansion and photosensitive UAAs in studying membrane proteins
  144. HK2 contributes to the proliferation, migration, and invasion of diffuse large B-cell lymphoma cells by enhancing the ERK1/2 signaling pathway
  145. IL-17 in osteoarthritis: A narrative review
  146. Circadian cycle and neuroinflammation
  147. Probiotic management and inflammatory factors as a novel treatment in cirrhosis: A systematic review and meta-analysis
  148. Hemorrhagic meningioma with pulmonary metastasis: Case report and literature review
  149. SPOP regulates the expression profiles and alternative splicing events in human hepatocytes
  150. Knockdown of SETD5 inhibited glycolysis and tumor growth in gastric cancer cells by down-regulating Akt signaling pathway
  151. PTX3 promotes IVIG resistance-induced endothelial injury in Kawasaki disease by regulating the NF-κB pathway
  152. Pancreatic ectopic thyroid tissue: A case report and analysis of literature
  153. The prognostic impact of body mass index on female breast cancer patients in underdeveloped regions of northern China differs by menopause status and tumor molecular subtype
  154. Report on a case of liver-originating malignant melanoma of unknown primary
  155. Case report: Herbal treatment of neutropenic enterocolitis after chemotherapy for breast cancer
  156. The fibroblast growth factor–Klotho axis at molecular level
  157. Characterization of amiodarone action on currents in hERG-T618 gain-of-function mutations
  158. A case report of diagnosis and dynamic monitoring of Listeria monocytogenes meningitis with NGS
  159. Effect of autologous platelet-rich plasma on new bone formation and viability of a Marburg bone graft
  160. Small breast epithelial mucin as a useful prognostic marker for breast cancer patients
  161. Continuous non-adherent culture promotes transdifferentiation of human adipose-derived stem cells into retinal lineage
  162. Nrf3 alleviates oxidative stress and promotes the survival of colon cancer cells by activating AKT/BCL-2 signal pathway
  163. Favorable response to surufatinib in a patient with necrolytic migratory erythema: A case report
  164. Case report of atypical undernutrition of hypoproteinemia type
  165. Down-regulation of COL1A1 inhibits tumor-associated fibroblast activation and mediates matrix remodeling in the tumor microenvironment of breast cancer
  166. Sarcoma protein kinase inhibition alleviates liver fibrosis by promoting hepatic stellate cells ferroptosis
  167. Research progress of serum eosinophil in chronic obstructive pulmonary disease and asthma
  168. Clinicopathological characteristics of co-existing or mixed colorectal cancer and neuroendocrine tumor: Report of five cases
  169. Role of menopausal hormone therapy in the prevention of postmenopausal osteoporosis
  170. Precisional detection of lymph node metastasis using tFCM in colorectal cancer
  171. Advances in diagnosis and treatment of perimenopausal syndrome
  172. A study of forensic genetics: ITO index distribution and kinship judgment between two individuals
  173. Acute lupus pneumonitis resembling miliary tuberculosis: A case-based review
  174. Plasma levels of CD36 and glutathione as biomarkers for ruptured intracranial aneurysm
  175. Fractalkine modulates pulmonary angiogenesis and tube formation by modulating CX3CR1 and growth factors in PVECs
  176. Novel risk prediction models for deep vein thrombosis after thoracotomy and thoracoscopic lung cancer resections, involving coagulation and immune function
  177. Exploring the diagnostic markers of essential tremor: A study based on machine learning algorithms
  178. Evaluation of effects of small-incision approach treatment on proximal tibia fracture by deep learning algorithm-based magnetic resonance imaging
  179. An online diagnosis method for cancer lesions based on intelligent imaging analysis
  180. Medical imaging in rheumatoid arthritis: A review on deep learning approach
  181. Predictive analytics in smart healthcare for child mortality prediction using a machine learning approach
  182. Utility of neutrophil–lymphocyte ratio and platelet–lymphocyte ratio in predicting acute-on-chronic liver failure survival
  183. A biomedical decision support system for meta-analysis of bilateral upper-limb training in stroke patients with hemiplegia
  184. TNF-α and IL-8 levels are positively correlated with hypobaric hypoxic pulmonary hypertension and pulmonary vascular remodeling in rats
  185. Stochastic gradient descent optimisation for convolutional neural network for medical image segmentation
  186. Comparison of the prognostic value of four different critical illness scores in patients with sepsis-induced coagulopathy
  187. Application and teaching of computer molecular simulation embedded technology and artificial intelligence in drug research and development
  188. Hepatobiliary surgery based on intelligent image segmentation technology
  189. Value of brain injury-related indicators based on neural network in the diagnosis of neonatal hypoxic-ischemic encephalopathy
  190. Analysis of early diagnosis methods for asymmetric dementia in brain MR images based on genetic medical technology
  191. Early diagnosis for the onset of peri-implantitis based on artificial neural network
  192. Clinical significance of the detection of serum IgG4 and IgG4/IgG ratio in patients with thyroid-associated ophthalmopathy
  193. Forecast of pain degree of lumbar disc herniation based on back propagation neural network
  194. SPA-UNet: A liver tumor segmentation network based on fused multi-scale features
  195. Systematic evaluation of clinical efficacy of CYP1B1 gene polymorphism in EGFR mutant non-small cell lung cancer observed by medical image
  196. Rehabilitation effect of intelligent rehabilitation training system on hemiplegic limb spasms after stroke
  197. A novel approach for minimising anti-aliasing effects in EEG data acquisition
  198. ErbB4 promotes M2 activation of macrophages in idiopathic pulmonary fibrosis
  199. Clinical role of CYP1B1 gene polymorphism in prediction of postoperative chemotherapy efficacy in NSCLC based on individualized health model
  200. Lung nodule segmentation via semi-residual multi-resolution neural networks
  201. Evaluation of brain nerve function in ICU patients with Delirium by deep learning algorithm-based resting state MRI
  202. A data mining technique for detecting malignant mesothelioma cancer using multiple regression analysis
  203. Markov model combined with MR diffusion tensor imaging for predicting the onset of Alzheimer’s disease
  204. Effectiveness of the treatment of depression associated with cancer and neuroimaging changes in depression-related brain regions in patients treated with the mediator-deuterium acupuncture method
  205. Molecular mechanism of colorectal cancer and screening of molecular markers based on bioinformatics analysis
  206. Monitoring and evaluation of anesthesia depth status data based on neuroscience
  207. Exploring the conformational dynamics and thermodynamics of EGFR S768I and G719X + S768I mutations in non-small cell lung cancer: An in silico approaches
  208. Optimised feature selection-driven convolutional neural network using gray level co-occurrence matrix for detection of cervical cancer
  209. Incidence of different pressure patterns of spinal cerebellar ataxia and analysis of imaging and genetic diagnosis
  210. Pathogenic bacteria and treatment resistance in older cardiovascular disease patients with lung infection and risk prediction model
  211. Adoption value of support vector machine algorithm-based computed tomography imaging in the diagnosis of secondary pulmonary fungal infections in patients with malignant hematological disorders
  212. From slides to insights: Harnessing deep learning for prognostic survival prediction in human colorectal cancer histology
  213. Ecology and Environmental Science
  214. Monitoring of hourly carbon dioxide concentration under different land use types in arid ecosystem
  215. Comparing the differences of prokaryotic microbial community between pit walls and bottom from Chinese liquor revealed by 16S rRNA gene sequencing
  216. Effects of cadmium stress on fruits germination and growth of two herbage species
  217. Bamboo charcoal affects soil properties and bacterial community in tea plantations
  218. Optimization of biogas potential using kinetic models, response surface methodology, and instrumental evidence for biodegradation of tannery fleshings during anaerobic digestion
  219. Understory vegetation diversity patterns of Platycladus orientalis and Pinus elliottii communities in Central and Southern China
  220. Studies on macrofungi diversity and discovery of new species of Abortiporus from Baotianman World Biosphere Reserve
  221. Food Science
  222. Effect of berrycactus fruit (Myrtillocactus geometrizans) on glutamate, glutamine, and GABA levels in the frontal cortex of rats fed with a high-fat diet
  223. Guesstimate of thymoquinone diversity in Nigella sativa L. genotypes and elite varieties collected from Indian states using HPTLC technique
  224. Analysis of bacterial community structure of Fuzhuan tea with different processing techniques
  225. Untargeted metabolomics reveals sour jujube kernel benefiting the nutritional value and flavor of Morchella esculenta
  226. Mycobiota in Slovak wine grapes: A case study from the small Carpathians wine region
  227. Elemental analysis of Fadogia ancylantha leaves used as a nutraceutical in Mashonaland West Province, Zimbabwe
  228. Microbiological transglutaminase: Biotechnological application in the food industry
  229. Influence of solvent-free extraction of fish oil from catfish (Clarias magur) heads using a Taguchi orthogonal array design: A qualitative and quantitative approach
  230. Chromatographic analysis of the chemical composition and anticancer activities of Curcuma longa extract cultivated in Palestine
  231. The potential for the use of leghemoglobin and plant ferritin as sources of iron
  232. Investigating the association between dietary patterns and glycemic control among children and adolescents with T1DM
  233. Bioengineering and Biotechnology
  234. Biocompatibility and osteointegration capability of β-TCP manufactured by stereolithography 3D printing: In vitro study
  235. Clinical characteristics and the prognosis of diabetic foot in Tibet: A single center, retrospective study
  236. Agriculture
  237. Biofertilizer and NPSB fertilizer application effects on nodulation and productivity of common bean (Phaseolus vulgaris L.) at Sodo Zuria, Southern Ethiopia
  238. On correlation between canopy vegetation and growth indexes of maize varieties with different nitrogen efficiencies
  239. Exopolysaccharides from Pseudomonas tolaasii inhibit the growth of Pleurotus ostreatus mycelia
  240. A transcriptomic evaluation of the mechanism of programmed cell death of the replaceable bud in Chinese chestnut
  241. Melatonin enhances salt tolerance in sorghum by modulating photosynthetic performance, osmoregulation, antioxidant defense, and ion homeostasis
  242. Effects of plant density on alfalfa (Medicago sativa L.) seed yield in western Heilongjiang areas
  243. Identification of rice leaf diseases and deficiency disorders using a novel DeepBatch technique
  244. Artificial intelligence and internet of things oriented sustainable precision farming: Towards modern agriculture
  245. Animal Sciences
  246. Effect of ketogenic diet on exercise tolerance and transcriptome of gastrocnemius in mice
  247. Combined analysis of mRNA–miRNA from testis tissue in Tibetan sheep with different FecB genotypes
  248. Isolation, identification, and drug resistance of a partially isolated bacterium from the gill of Siniperca chuatsi
  249. Tracking behavioral changes of confined sows from the first mating to the third parity
  250. The sequencing of the key genes and end products in the TLR4 signaling pathway from the kidney of Rana dybowskii exposed to Aeromonas hydrophila
  251. Development of a new candidate vaccine against piglet diarrhea caused by Escherichia coli
  252. Plant Sciences
  253. Crown and diameter structure of pure Pinus massoniana Lamb. forest in Hunan province, China
  254. Genetic evaluation and germplasm identification analysis on ITS2, trnL-F, and psbA-trnH of alfalfa varieties germplasm resources
  255. Tissue culture and rapid propagation technology for Gentiana rhodantha
  256. Effects of cadmium on the synthesis of active ingredients in Salvia miltiorrhiza
  257. Cloning and expression analysis of VrNAC13 gene in mung bean
  258. Chlorate-induced molecular floral transition revealed by transcriptomes
  259. Effects of warming and drought on growth and development of soybean in Hailun region
  260. Effects of different light conditions on transient expression and biomass in Nicotiana benthamiana leaves
  261. Comparative analysis of the rhizosphere microbiome and medicinally active ingredients of Atractylodes lancea from different geographical origins
  262. Distinguish Dianthus species or varieties based on chloroplast genomes
  263. Comparative transcriptomes reveal molecular mechanisms of apple blossoms of different tolerance genotypes to chilling injury
  264. Study on fresh processing key technology and quality influence of Cut Ophiopogonis Radix based on multi-index evaluation
  265. An advanced approach for fig leaf disease detection and classification: Leveraging image processing and enhanced support vector machine methodology
  266. Erratum
  267. Erratum to “Protein Z modulates the metastasis of lung adenocarcinoma cells”
  268. Erratum to “BRCA1 subcellular localization regulated by PI3K signaling pathway in triple-negative breast cancer MDA-MB-231 cells and hormone-sensitive T47D cells”
  269. Retraction
  270. Retraction to “Protocatechuic acid attenuates cerebral aneurysm formation and progression by inhibiting TNF-alpha/Nrf-2/NF-kB-mediated inflammatory mechanisms in experimental rats”
Sign up now to receive a 20% welcome discount
Institutional Access
How does access work?
Have an idea on how to improve our website?
Please write us.
© 2025 De Gruyter Brill
Downloaded on 6.9.2025 from https://www.degruyterbrill.com/document/doi/10.1515/biol-2022-0665/html
Scroll to top button