Home Automatic prediction model of overall survival in prostate cancer patients with bone metastasis using deep neural networks
Article Open Access

Automatic prediction model of overall survival in prostate cancer patients with bone metastasis using deep neural networks

  • Zhongxiao Wang ORCID logo , Tianyu Xiong , Mingxin Jiang , Yun Cui , Xiaosong Qian , Yao Su , Xiaolei Zhang , Shiqi Xu , Dong Wen , Xianling Dong EMAIL logo , Minfu Yang EMAIL logo and Yinong Niu EMAIL logo
Published/Copyright: June 28, 2023
Download Article (PDF)
Oncologie
From the journal Oncologie Volume 25 Issue 5

Abstract

Objectives

Bone is the most common site of metastasis in prostate cancer (PCa) patients and is correlated with poor prognosis and increasing economic burden. Few studies have analyzed the prognostic prediction for metastatic PCa patients with the assistance of neural networks.

Methods

Four convolutional neural network (CNN) models are developed and evaluated to predict the overall survival (OS) of PCa patients with bone metastasis. All the CNN models are first trained with 64 samples and evaluated with 10 samples; two models use only bone scan images and two models use both bone scan images and clinical parameters (CPs). The predictions of the best models are compared with those by two urology surgeons on 20 test samples.

Results

Our best models can predict OS of PCa patients with bone metastasis with AUC=0.8022 by using only bone scan images and AUC=0.8132 by using both bone scan images and CPs on 20 test samples. The best Youden indexes of the two models are 0.6263 and 0.7142, respectively, which are 0.3077 and 0.3131 higher than that of the urologists’ average Youden index, which indicate that CNN models exhibit significant advantages.

Conclusions

CNN models are suitable to predict OS in PCa patients with bone metastasis using bone scan images and CPs. Our models show better performance in terms of accuracy and stability than urology surgeons.

Keywords: bone metastasis; bone scan; convolutional neural network; overall survival; prostate cancer

Introduction

Prostate cancer (PCa) is the second largest cause of malignant tumors in men worldwide, accounting for over 370,000 death annually [1]. PCa has a strong proclivity to metastasize to bone, which may be partly explained by the “dependence of the seed on a fertile soil” theory [2]. According to a previous study, based on autopsies, bone is the most common metastatic site of PCa and is involved in approximately 90 % of patients with metastatic PCa [3]. The progression of bone metastasis is a comprehensive multistep process that includes the colonization of circulating cancer cells and the reconstruction of bone structure [4, 5]. Bone metastasis has been confirmed to be an adverse prognostic factor of PCa that imposes clinical and economic burdens on patients, especially those with skeletal-related events such as pathologic fracture, spinal cord compression, or palliative treatment [6], [7], [8], [9].

For PCa patients with bone metastasis, bone scanning is the most prevalent and cost-effective method for diagnosis and follow-up [10]. It is performed using an intravenous injection of technetium-99m-labeled diphosphonate, a compound that can rapidly accumulate in the bones. Imaging is typically performed 2–6 h after injection, which allows clearance of the radiotracer from the soft tissues and improves bone visualization [11]. Anterior and posterior whole-body images of the skeleton are obtained and potential sites of bone lesions are identified as hotspots. Bone metastases of PCa often show increased blood flow levels and a high rate of new bone formation, leading to radiotracer accumulation. One major disadvantage of bone scans is non-tumor-specific radiotracer uptake, resulting in limited specificity; this is inferior to the specificity of other molecular imaging methods such as positron emission tomography/computed tomography (PET/CT) [12, 13]. However, owing to its sensitivity, availability, and affordability, bone scanning remains the mainstay method for investigating bone metastasis in PCa patients in most institutions [14].

In recent years, deep neural networks, particularly convolutional neural network (CNN) models, have achieved excellent success in computer vision applications, including image classification, image semantic segmentation, and image object detection. Numerous CNN models have been developed to improve performance on natural image classification [15], [16], [17], [18], [19], [20], [21]. Based on the success of natural image recognition, many CNN models have been developed and proven effective for medical image processing [22], [23], [24], [25], [26], [27], [28], [29].

In this study, we built CNN models to predict the overall survival (OS) of PCa based on data from bone scan images and clinical parameters (CPs). First, several CNN models have been developed based either only on bone scan images or using both bone scan images and CPs. Second, the four best-trained CNN models were selected using a validation set. Finally, the performance of the selected models was compared with that of two urology surgeons using a test set.

Materials and methods

Patient selection

We retrospectively reviewed the data of patients with PCa and bone metastasis at Beijing Chaoyang Hospital from September 2008 to August 2021. All patients were diagnosed with PCa using ultrasound-guided transrectal prostate biopsy. The highest Gleason score among all biopsy cores was documented as the biopsy Gleason score. Bone metastatic lesions were evaluated using a bone scan prior to treatment. The images were acquired using a conventional SPECT/CT camera (Infinia Hawkeye 4, GE, USA). Patients who received any type of PCa treatment before the bone scan were excluded.

All patients were initially treated with a combined androgen blockade, which was administered with an androgen receptor blocker (bicalutamide) and a GnRH agonist (leuproline or goserelin), or surgical castration followed by abiraterone glucocorticoid and/or docetaxel chemotherapy for subsequent castration-resistant prostate cancer. Cytoreductive prostatectomy was performed by urological surgeons with at least 10 years of experience in laparoscopic surgery. Bone-modifying agents, pain relief, and palliative radiotherapy for terminally ill patients were used as appropriate and were not regulated.

This study was conducted in accordance with the Declaration of Helsinki (as revised in 2013) and approved by the Institutional Review Board of Beijing Chaoyang Hospital, Capital Medical University (No. 2022-Ke-55), which waived the requirement for informed consent for this retrospective analysis.

Data preparation

Bone scan images and CPs at diagnosis were retrieved by reviewing electronic medical records. The endpoint of this study was all-cause mortality, and the OS time was calculated from the diagnosis of metastatic PCa to the date of death. Ultimately, 94 samples were collected from the dataset. 64 samples from the dataset were randomly selected as the training set and 10 of the remaining samples were used as the validation set to select the best models. To verify the accuracy of our model in an extensive setting and compare it with that of various urology surgeons as human readers, the remaining 20 samples were used as the test set.

A typical series of bone scan images contained four sub-images for each patient, including two grayscale images and two color (RGB) images. The grayscale images included one front scan image (GFSI) and one back scan image (GBSI); the color images also included a front scan image (CFSI) and a back scan image (CBSI). A typical example of a bone scan is shown in Figure 1. The extra CPs corresponding to the bone scan images of each patient were collected at the first diagnosis, as shown in Table 1.

Figure 1: A typical example of bone scan image with four sub-images. (a) The grayscale front scan image (GFSI). (b) The grayscale back scan image (GBSI). (c) The color front scan image (CFSI). (d) The color back scan image (CBSI).
Figure 1:

A typical example of bone scan image with four sub-images. (a) The grayscale front scan image (GFSI). (b) The grayscale back scan image (GBSI). (c) The color front scan image (CFSI). (d) The color back scan image (CBSI).

Table 1:

Baseline characteristics of all patients.

Factors Value
Number of patients, n 94
Age at diagnosis (year), median (IRQ) 72 (69–76)
Clinical tumor stage, n, %
T2 44 (46.8)
T3a 9 (9.6)
T3b 20 (21.3)
T4 21 (22.3)
Visceral metastasis, n, % 4 (4.3)
Biopsy gleason score, n, %
3 + 3 6 (6.4)
3 + 4 6 (6.4)
4 + 3 10 (10.6)
8 15 (16.0)
9 or 10 30 (31.9)
Unknown 27 (28.7)
PSA level at diagnosis, ng/mL, median (IRQ) 67.35 (17.40–390.84)
PSA level when bone scan was performed, ng/mL, median (IRQ) 40.70 (17.40–390.84)
Cytoreductive surgery, n, % 33 (35.1)
Hemoglobin, g/L, median (IRQ) 129 (116–140)
White blood cell count (109), median (IRQ) 5.98 (4.79–7.60)
Neutrophil ratio, % median (IRQ) 65.4 (58.2–72.0)
Neutrophil count (109), median (IRQ) 3.97 (2.72–5.41)
Lymphocyte ratio, %, median (IRQ) 24.7 (19.2–31.2)
Lymphocyte count (109), median (IRQ) 1.55 (1.16–1.87)
Monocyte ratio, %, median (IRQ) 6.7 (5.5–8.2)
Monocyte count (109), median (IRQ) 0.39 (0.32–0.50)
Platelet count (109), median (IRQ) 202 (146–245)
Albumin, g/L, median (IRQ) 40.7 (35.8–43.7)
Serum calcium, mmol/L, median (IRQ) 2.26 (2.15–2.37)
Total cholesterol level, mmol/L, median (IRQ) 4.54 (3.80–5.11)
Alkaline phosphatase, u/L, median (IRQ) 90 (75–157)

  1. IQR, interquartile range; PSA, prostate-specific antigen.

The OS of each PCa patient was obtained during outpatient follow-up. Samples with an OS of less than 5 years were labeled as positive, and the others labeled as negative. The distribution of OS within the datasets is shown in Table.2. The training set comprised 42 positive and 22 negative samples. The validation set contained 7 positive and 3 negative samples. The test set contained 13 positive and 7 negative samples.

Table 2:

The distributions of the data sets.

Data sets <5 years (positive) >5 years (negative) Total
Training set 42 22 64
Validation set 7 3 10
Test set 13 7 20

Development of CNN models for PCa OS

Two CNN models were developed to predict the OS of patients with PCa based solely on bone scan images. Two other CNN models were developed using both bone scan images and CPs. The models were trained to minimize the cross-entropy loss function between the labels and the model predictions. A momentum optimizer was used to train the models. The batch size was 64. The original learning rate was 0.01, which was decayed by 0.9 per epoch.

Image preprocessing for CNN models

The bone scan images contained many unusable areas. To obtain the useful area, the central 256 × 850 pixels of each sub-image was cropped and concatenated. Two concatenation methods were developed: Figure 2(a) shows one method that concatenates all four sub-images, and Figure 2(b) shows another method that concatenates GFSI with CFSI and concatenates GBSI with CBSI. In the next step, all concatenating images were resized to 256 × 640 pixels and fed into the basis CNN models.

Figure 2: The models for predicting the OS using only bone scan images. (a) was model A, all the four sub-images were concatenated, resized to 256 × 640, followed a basis CNN model, FC layer + Softmax to obtain the output. (b) Was model B, the GFSI and CFSI were concatenated, resized and fed into a basis CNN model. The GBSI and CBSI were concatenated, resized and fed into another basis CNN model. All the features extracting from the two basis CNN models were concatenated and fed into FC layer + Softmax to get the output. (c) Was the basis CNN model, which employed four residual modules, contained 9 convolutional layers and 1 global average pooling layer. The values of C determined the width of the networks. In this study, the values of C were set to 8, 16 and 32 for model A and 4, 8 and 16 for model B. Cori was set to 8 for model A and set to 4 for model B.
Figure 2:

The models for predicting the OS using only bone scan images. (a) was model A, all the four sub-images were concatenated, resized to 256 × 640, followed a basis CNN model, FC layer + Softmax to obtain the output. (b) Was model B, the GFSI and CFSI were concatenated, resized and fed into a basis CNN model. The GBSI and CBSI were concatenated, resized and fed into another basis CNN model. All the features extracting from the two basis CNN models were concatenated and fed into FC layer + Softmax to get the output. (c) Was the basis CNN model, which employed four residual modules, contained 9 convolutional layers and 1 global average pooling layer. The values of C determined the width of the networks. In this study, the values of C were set to 8, 16 and 32 for model A and 4, 8 and 16 for model B. Cori was set to 8 for model A and set to 4 for model B.

The basis CNN model

The residual module used in ResNet is based on the basis CNN model. Figure 2(c) shows the structure of the basis CNN model, which contains nine convolutional layers and one global average pooling layer. Models with different network widths (different channel numbers in each layer, determined by the value of C in Figure 2(c)) were established. The best models were selected by comparing the performances of all the models on the validation set.

Development models using both bone scan images and CPs

To improve the performance of the models further, two other models were developed using both bone scan images and CPs. Figure 3(a) shows one model (model C) concatenating the CPs and the features extracted from one CNN model and feeding all the features into an FC layer + Softmax to obtain the prediction results. Figure 3(b) shows another model (model D) extracting features from two CNN models: one extracting the features of the concatenating GFSI and CFSI sub-images, and the other extracting the features of the concatenating GBSI and CBSI sub-images. The CPs and all CNN extracting features were concatenated and fed into the next step.

Figure 3: The models for predicting the OS using both bone scan images and CPs. The CPs and the CNN extracting features were concatenated and fed into FC layer + Softmax to get the output. (a) Was model C, which extracted the CNN features from the concatenating four sub-images. (b) Was model D, which extracted the CNN features from both the concatenating GFSI and CFSI sub-images and the concatenating GBSI and CBSI sub-images.
Figure 3:

The models for predicting the OS using both bone scan images and CPs. The CPs and the CNN extracting features were concatenated and fed into FC layer + Softmax to get the output. (a) Was model C, which extracted the CNN features from the concatenating four sub-images. (b) Was model D, which extracted the CNN features from both the concatenating GFSI and CFSI sub-images and the concatenating GBSI and CBSI sub-images.

Performance comparison to urology surgeons

Two urologists with at least 5 years of experience at Beijing Chaoyang Hospital, Capital Medical University, were recruited for prognosis prediction. The prediction of urology surgeons proceeded in two phases. First, urologists were provided with all originally acquired bone scan images for each patient, including the grayscale front, grayscale back, color front, and color back scan images. In the second phase, urologists were provided with both bone scan images and the CPs for each patient. Patients were presented to urologists in a random order. The urologists were aware that all patients had metastatic PCa but were otherwise blinded to the follow-up results. The urologists were instructed to predict the 5-year OS with a yes or no answer for each patient based on their expertise and clinical experience. To evaluate the stability of urology surgeons, they were instructed to repeat the prediction procedure on another day using 30 samples to test intra-observer reliability.

We compared the prediction performance of the CNN models and urology surgeons, which was first evaluated by reading only bone scan images and then by reading both bone scan images and CPs. The diagnostic results were compared using the metrics described below.

Analysis of diagnostic performance using metrics methods

Sensitivity and specificity were used to evaluate the performances of urology surgeons and our models. Sensitivity represents the true-positive rate, whereas specificity represents the true-negative rate. In this study, we considered samples with an OS of <5 years as positive samples and other samples as negative samples.

Our models only predicted the positive probability of each sample, therefore the performance was best illustrated by the AUC and the receiver operating characteristic (ROC) curve. An ROC curve is a graphical plot that illustrates the diagnostic ability of a binary classifier system as its discrimination threshold is varied [30, 31]. The ROC curve in this scenario was created by plotting the sensitivity against (1 – specificity) at various threshold settings. The AUC is the area under the ROC curve. The Youden index was used to facilitate a comparison between the performances of the CNNs and of the urologists.

Results

Performance of the models using only bone scan images

The validation set was used to evaluate the models’ performances. Two models with different structures–Model A, shown in Figure 2(a), and Model B, shown in Figure 2(b)–were established. Models with three different network widths were evaluated to select the best ones. Model A exhibited the performance of AUC=0.6190, 0.7619, and 0.7143 for C=8, 16, and 32, respectively. Figure 4(a) shows the best performance of model A, with an AUC of 0.7619, when C=16. Model B exhibited the performance of AUC=0.7143, 0.8571, and 0.8095 for C=4, 8, and 16, respectively. Figure 4(a) shows the best performance of Model B, with AUC=0.8571 when C=8. The best performance of Model B was superior to that of Model A, with the AUC of the former being 9.52 % higher than that of the latter.

Figure 4: The performance of the models on validation set. (a) Were the performance of model A and B (showing in Figure 2(a, b)) using only bone scan images. (b) Were the performance of model C and D (showing in Figure 3) using both bone scan images and CPs. Model B (D) showed better performance than model A (C), and model D was better than model B.
Figure 4:

The performance of the models on validation set. (a) Were the performance of model A and B (showing in Figure 2(a, b)) using only bone scan images. (b) Were the performance of model C and D (showing in Figure 3) using both bone scan images and CPs. Model B (D) showed better performance than model A (C), and model D was better than model B.

Performance of the models using both bone scan images and CPs

To further improve the performance of the models, two models using both bone scan images and CPs, namely Model C, shown in Figure 3(a), and Model D, shown in Figure 3(b), were established and evaluated using the validation set. Figure 4(b) shows the best performance of Model C, with an AUC of 0.7619 when C=16. Figure 4(b) also shows the best performance of Model D, with an AUC of 0.9048 when C=8. When considering both the bone scan images and CPs, Model D performed better than model C, with the AUC of the former being 14.29 % higher, indicating that the model structure used in Models B and D was more suitable for processing bone scan images.

Performance comparison between CNN models and urology surgeons

To comprehensively compare our models with the predictions of the urologists, all four models (A, B, C, and D) and the predictions of the urologists were evaluated. For the same samples, our models obtained the same prediction results at different times; however, the urologists obtained different results. To evaluate the stability of the urologists, the intra-observer agreement between the two urologists was tested. The results are shown below.

Using only bone scan images

Models A and B were compared with the two urologists for predicting PCa OS using bone scan images. To compare our two best models with the predictions of the urologists, the two urology surgeons from Beijing Chaoyang Hospital and the two best models independently scored 20 bone scan images (test set). The best performance was obtained by Model A (AUC=0.7692) and Model B (AUC=0.8022), with both outperforming the two urology surgeons, as shown in Figure 5(a). When the specificity was set to be equal to the urologists’ average level, the sensitivities of Models A and B were 15.38 and 30.77 % higher, respectively, than the urologists’ average level. The best Youden indices of Models A and B were 0.5604 and 0.6263, respectively, which were 0.2418 and 0.3077 higher than the urologists’ average level. Our models achieved better performance in PCa OS when using only bone scan images.

Figure 5: The performance of the models and urologists on test set. (a) Were the performance of the models and urologists on the test set using only bone scan images. (b) Were the performance of the models and urologists on the test set using both bone scan images and CPs.
Figure 5:

The performance of the models and urologists on test set. (a) Were the performance of the models and urologists on the test set using only bone scan images. (b) Were the performance of the models and urologists on the test set using both bone scan images and CPs.

Using both bone scan images and CPs

Our models were further compared with the predictions of the urologists for PCa OS using both bone scan images and CPs. Figure 5(b) shows the performance of our models and the predictions of the urologists. Model C demonstrated an AUC of 0.7912 and model D exhibited an AUC of 0.8132; thus, Model D showed better performance. Both models showed better performance than the urologists. When the sensitivities were set to be equal to the urologists’ average level, the specificities of both Models C and D were 7.2 % higher than the urologists’ average level. When the specificities were set to the urologists’ average levels, the sensitivities of both Models C and D were 7.7 % higher than the urologists’ average levels. The best Youden indices of Models C and D were 0.6373 and 0.7142, respectively, which were 0.2362 and 0.3131 higher than the urologists’ average level. Overall, our models achieved a better performance for PCa OS when considering both bone scan images and CPs.

The stability of urology surgeons

Each of the two selected urologists predicted 30 samples at one month interval to evaluate the consistency of the human readers. Table 3 shows their performance. When only bone scan images were used, the two urologists obtained consistency rates of 86.7 and 76.7 %, respectively, with an average of 81.7 %. When using both bone scan images and CPs, the two urologists obtained consistency rates of 83.3 and 86.7 %, respectively, with an average of 85.0 %. All models had a 100 % consistency rate regardless of the interval; therefore, our model showed better stability than the predictions by the urologists.

Table 3:

The inter-observer results of two urologists.

Using only bone scan images Using both bone scan images and CPs
Urologist 1 86.7 % (26/30) 83.3 % (25/30)
Urologist 2 76.7 % (23/30) 86.7 % (26/30)
Average 81.7 % 85.0 %

Discussion

In recent years, CNN methods have demonstrated many successful applications in medical image processing, proving that they are suitable for this domain. Several previous studies have shown that CNN methods are useful for assisting in the diagnosis and radiotherapy treatment planning for PCa patients [32], [33], [34]. However, these studies have been limited to predicting the prognosis of metastatic PCa using neural networks. In addition, models based on a combination of bone scan images and CPs have not yet been reported. In this study, we built prediction models for patients with PCa and bone metastasis using CNN methods based on data from a Chinese population. The bone scan images were typical medical images. Therefore, a CNN was employed in this study to process the bone scan images to predict the OS of PCa patients with bone metastasis.

Prognostic prediction for PCa patients with bone metastasis is essential for determining the appropriate treatment. The increased extent of metastatic lesions has been confirmed to be associated with an increasingly poor prognosis [6, 35]. Several researchers have attempted to quantify the degree of bone metastasis using bone scan images and have obtained different results. The extent of disease (EOD) score is a semi-quantitative parameter useful for the prognostic prediction of PCa [36]. However, this method is subjective, and the results may vary significantly depending on the observer. An index called the “bone scan index” (BSI) was developed to provide an objective and quantitative measurement of the percentage of the skeleton consumed by bone metastases [37]. Although the BSI provides a relatively objective estimation of the metastatic burden of PCa, especially with the assistance of a computer-aided diagnostic system, it is an indirect indicator of disease aggressiveness [38, 39]. Further analysis is required to establish the thresholds for risk stratification of prognosis [40]. In addition, the calculation of BSI does not consider the different effects among metastatic sites, as metastases in the appendicular skeleton, such as the ribs and limbs, have been reported to be significantly correlated with a poorer response to androgen deprivation therapy and a shorter survival time [35]. Additionally, the utility of BSI is limited by its reliance on automated measurement platforms. However, in this study, the bone scan images were directly processed using CNN methods, which simultaneously analyzed both the number and position of metastatic sites. Furthermore, our models were able to generate a direct prediction of OS for PCa patients with bone metastasis, were simple to use, and omitted secondary analyses for prognosis.

Another advantage of our models is their superior performance compared to that of the selected urologists. In our study, we noted that the tumor stage, biopsy Gleason score, and the degree of metastatic burden shown in the bone scan images were the major concerns of clinicians when making their predictions. Generally, patients with higher tumor stages, higher Gleason scores, and more metastatic lesions are considered to have a shorter OS. Similarly, prediction models reported in previous studies were based on these clinical parameters [41, 42]. However, urologists are not sufficiently competent to process large volumes of data. As a result, their predictions hardly benefit from the addition of more CP types. In this study, our models could directly analyze the entire database using CNN methods and provided significantly more accurate predictions than the selected urologists. The results showed that our CNN models performed better than the urologists in predicting OS in patients with PCa with bone metastasis using bone scan images. Therefore, we believe that our model may effectively improve the management of PCa patients with bone metastasis.

Four CNN models were trained and evaluated in this study. Two models (Models A and B) used only bone scan images, and two models (Models C and D) used both bone scan images and CPs. The results showed that the latter achieved better performance than the former. The CPs contain different types of information regarding the features extracted from the images. When considering both the bone scan images and the CPs, more information was fed into the last classifier, which resulted in a better performance. Therefore, Model C showed better performance than Model A, and Model D showed better performance than Model B. Two models (Models B and D) independently extracted the features of the front and back sub-images, while two models (Models A and C) fused and extracted the features of the four sub-images. The front and back sub-images of the bone scan provide different clinical information regarding bone invasion. It is better to extract the features of each sub-image and merge them in the last classifier than to merge them in each convolutional layer. Therefore, Model B performed better than Model A and Model D performed better than Model C.

Our CNN models showed better performance in terms of accuracy and stability than the predictions of the urologists. However, this study has some limitations. First, the sample size used in our study was relatively small, and more samples would improve the performance of the models. Second, because our study was based solely on single-center medical samples, it was difficult to verify the generalizability of our CNN models. Therefore, additional multicenter medical samples may help improve and verify the generalizability of the models. Third, the performances of only two urologists were evaluated and compared in our study. The evaluations of prediction by a greater number of urological surgeons with different levels of clinical experience is warranted.

Conclusions

In conclusion, our study is the first to prove that CNN models can be used to predict OS in patients with PCa presenting bone metastasis based on data from bone scan images and CPs. Our models showed better performance in terms of accuracy and stability than the predictions of urological surgeons. Our study provides a useful reference for adopting deep neural networks for prognostic prediction in patients with metastatic PCa.

Corresponding authors: Xianling Dong, Hebei Key Laboratory of Nerve Injury and Repair, Chengde Medical University, Chengde, China; Hebei International Research Center of Medical Engineering, Chengde Medical University, Chengde, China, E-mail: ; Minfu Yang, Department of Nuclear Medicine, Beijing Chaoyang Hospital, Capital Medical University, Beijing, China, E-mail: ; and Yinong Niu, Department of Urology, Beijing Shijitan Hospital, Capital Medical University, Beijing, China, E-mail:
Zhongxiao Wang and Tianyu Xiong contributed equally to this work.

Funding source: Hebei Natural Science Foundation

Award Identifier / Grant number: C2022406010

Funding source: Hebei Province Introduced Returned Overseas Chinese Scholars Funding Project

Award Identifier / Grant number: C20220107

Funding source: Chengde Biomedicine Industry Research Institute Funding project

Award Identifier / Grant number: 202205B086

Funding source: National Natural Science Foundation of China

Award Identifier / Grant number: 82170783

Funding source: Funded by Science and Technology Project of Hebei Education Department

Award Identifier / Grant number: BJK2023060

  1. Research funding: This work was supported by National Natural Science Foundation of China (grant numbers: 82170783), Funded by Science and Technology Project of Hebei Education Department (BJK2023060), Hebei Province Introduced Returned Overseas Chinese Scholars Funding Project (C20220107) and Hebei Natural Science Foundation (C2022406010).

  2. Author contributions: Concept and design: Z.W., and T.X.; Acquisition, analysis of data: Y.S., and Z.W.; Drafting of the manuscript: Z.W., T.X., X.D., and Y.N.; Formal analysis: Y.C. and X.Q.; Administrative, technical, or material support: X.Z., and S.X.; Obtained funding: X.D., and Y.N.; Supervision: D.W., X.D., M.Y., and Y.N.

  3. Competing interests: All the authors declare that the research was conducted in the absence of any commercial or financial relationships that could be construed as a potential competing of interest.

  4. Informed consent: The requirement of informed consent for this retrospective analysis was waived with the approval of the Institutional Review Board of Beijing Chaoyang Hospital, Capital Medical University.

  5. Ethical approval: Our study was conducted in accordance with the Declaration of Helsinki (as revised in 2013) and was approved by the Institutional Review Board of Beijing Chaoyang Hospital, Capital Medical University (NO.: 2022-Ke-55).

References

1. Wild, CP, Weiderpass, E, Stewart, BW. World cancer report 2020: cancer research for cancer prevention. Lyon, France: International Agency for Research on Cancer; 2020. Available from: http://publications.iarc.fr/586.Search in Google Scholar

2. Rucci, N, Angelucci, A. Prostate cancer and bone: the elective affinities. BioMed Res Int 2014;2014:167035–14. https://doi.org/10.1155/2014/167035.Search in Google Scholar PubMed PubMed Central

3. Bubendorf, L, Schöpfer, A, Wagner, U, Sauter, G, Moch, H, Willi, N, et al.. Metastatic patterns of prostate cancer: an autopsy study of 1,589 patients. Hum Pathol 2000;31:578–83. https://doi.org/10.1053/hp.2000.6698.Search in Google Scholar PubMed

4. Croucher, PI, McDonald, MM, Martin, TJ. Bone metastasis: the importance of the neighbourhood. Nat Rev Cancer 2016;16:373–86. https://doi.org/10.1038/nrc.2016.44.Search in Google Scholar PubMed

5. Patel, SH, Panian, J, Bree, K, Derweesh, I, Millard, F, Randall, J, et al.. Systemic treatment of bone disease in metastatic urinary malignancies. Eur Urol Focus 2020;6:17–25. https://doi.org/10.1016/j.euf.2019.06.007.Search in Google Scholar PubMed

6. Groot, MT, Boeken Kruger, CG, Pelger, RC, Uyl-de Groot, CA. Costs of prostate cancer, metastatic to the bone, in The Netherlands. Eur Urol 2003;43:226–32. https://doi.org/10.1016/s0302-2838(03)00007-1.Search in Google Scholar PubMed

7. Zhuo, L, Cheng, Y, Pan, Y, Zong, J, Sun, W, Xu, L, et al.. Prostate cancer with bone metastasis in Beijing: an observational study of prevalence, hospital visits and treatment costs using data from an administrative claims database. BMJ Open 2019;9:e028214. https://doi.org/10.1136/bmjopen-2018-028214.Search in Google Scholar PubMed PubMed Central

8. Yong, C, Onukwugha, E, Mullins, CD. Clinical and economic burden of bone metastasis and skeletal-related events in prostate cancer. Curr Opin Oncol 2014;26:274–83. https://doi.org/10.1097/cco.0000000000000071.Search in Google Scholar

9. Jayasekera, J, Onukwugha, E, Bikov, K, Mullins, CD, Seal, B, Hussain, A. The economic burden of skeletal-related events among elderly men with metastatic prostate cancer. Pharmacoeconomics 2014;32:173–91. https://doi.org/10.1007/s40273-013-0121-y.Search in Google Scholar PubMed

10. Mease, RC. Radionuclide based imaging of prostate cancer. Curr Top Med Chem 2010;10:1600–16. https://doi.org/10.2174/156802610793176774.Search in Google Scholar PubMed

11. Love, C, Din, AS, Tomas, MB, Kalapparambath, TP, Palestro, CJ. Radionuclide bone imaging: an illustrative review. Radiographics 2003;23:341–58. https://doi.org/10.1148/rg.232025103.Search in Google Scholar PubMed

12. Shen, G, Deng, H, Hu, S, Jia, Z. Comparison of choline-PET/CT, MRI, SPECT, and bone scintigraphy in the diagnosis of bone metastases in patients with prostate cancer: a meta-analysis. Skeletal Radiol 2014;43:1503–13. https://doi.org/10.1007/s00256-014-1903-9.Search in Google Scholar PubMed

13. Chen, B, Wei, P, Macapinlac, HA, Lu, Y. Comparison of 18F-Fluciclovine PET/CT and 99mTc-MDP bone scan in detection of bone metastasis in prostate cancer. Nucl Med Commun 2019;40:940–6. https://doi.org/10.1097/mnm.0000000000001051.Search in Google Scholar PubMed

14. Nadel, HR. Bone scan update. Semin Nucl Med 2007;37:332–9. https://doi.org/10.1053/j.semnuclmed.2007.06.001.Search in Google Scholar PubMed

15. LeCun, L, Bottou, L, Bengio, Y, Haffner, P. Gradient-based learning applied to document recognition. Proc IEEE 1998;86:2278–324. https://doi.org/10.1109/5.726791.Search in Google Scholar

16. Krizhevsky, A, Sutskever, I, Hinton, G. Imagenet classification with deep convolutional neural networks. Adv Neural Inf Process Syst 2012;25:1106–14.Search in Google Scholar

17. Simonyan, K, Zisserman, A. Very deep convolutional networks for large-scale image recognition. arXiv 2014;1409.1556. https://arxiv.org/abs/ 1409.1556.Search in Google Scholar

18. He, K, Zhang, X, Ren, S, Sun, J. Deep residual learning for image recognition. In: 2016 IEEE conference on computer vision and pattern recognition (CVPR); 2016:770–8 pp.10.1109/CVPR.2016.90Search in Google Scholar

19. Szegedy, C, Liu, W, Jia, Y, Sermanet, P, Reed, S, Anguelov, D, et al.. Going deeper with convolutions. In: 2015 IEEE conference on computer vision and pattern recognition (CVPR); 2015:1–9 pp.10.1109/CVPR.2015.7298594Search in Google Scholar

20. Chollet, F. Xception: deep learning with depthwise separable convolutions. In: 2017 IEEE conference on computer vision and pattern recognition (CVPR); 2017:1800–7 pp.10.1109/CVPR.2017.195Search in Google Scholar

21. Zhao, H, Shi, J, Qi, X, Wang, Q, Jia, J. Pyramid scene parsing network. In: 2017 IEEE conference on computer vision and pattern recognition (CVPR); 2017:6230–9 pp.10.1109/CVPR.2017.660Search in Google Scholar

22. Gulshan, V, Peng, L, Coram, M, Stumpe, MC, Wu, D, Narayanaswamy, A, et al.. Development and validation of a deep learning algorithm for detection of diabetic retinopathy in retinal fundus photographs. JAMA 2016;316:2402–10. https://doi.org/10.1001/jama.2016.17216.Search in Google Scholar PubMed

23. Maji, D, Santara, A, Mitra, P, Sheet, D. Ensemble of deep convolutional neural networks for learning to detect retinal vessels in fundus images; 2016. Available from: https://arxiv.org/abs/1603.04833.Search in Google Scholar

24. Poplin, R, Varadarajan, AV, Blumer, K, Liu, Y, McConnell, MV, Corrado, GS, et al.. Prediction of cardiovascular risk factors from retinal fundus photographs via deep learning. Nat Biomed Eng 2018;2:158–64. https://doi.org/10.1038/s41551-018-0195-0.Search in Google Scholar PubMed

25. Shichijo, S, Nomura, S, Aoyama, K, Nishikawa, Y, Miura, M, Shinagawa, T, et al.. Application of convolutional neural networks in the diagnosis of helicobacter pylori infection based on endoscopic images. EBioMedicine 2017;25:106–11. https://doi.org/10.1016/j.ebiom.2017.10.014.Search in Google Scholar PubMed PubMed Central

26. Smith, KP, Kang, AD, Kirby, JE. Automated interpretation of blood culture gram stains by use of a deep convolutional neural network. J Clin Microbiol 2018;56:e01521–17. https://doi.org/10.1128/jcm.01521-17.Search in Google Scholar PubMed PubMed Central

27. Racsa, LD, Gander, RM, Southern, PM, McElvania TeKippe, E, Doern, C, Luu, HS. Detection of intracellular parasites by use of the CellaVision DM96 analyzer during routine screening of peripheral blood smears. J Clin Microbiol 2015;53:167–71. https://doi.org/10.1128/jcm.01783-14.Search in Google Scholar PubMed PubMed Central

28. Wang, Z, Zhang, L, Zhao, M, Wang, Y, Bai, H, Wang, Y, et al.. Deep neural networks offer morphologic classification and diagnosis of bacterial vaginosis. J Clin Microbiol 2021;59:e02236–20. https://doi.org/10.1128/jcm.02236-20.Search in Google Scholar

29. Tomita, N, Tafe, LJ, Suriawinata, AA, Tsongalis, GJ, Nasir-Moin, M, Dragnev, K, et al.. Predicting oncogene mutations of lung cancer using deep learning and histopathologic features on whole-slide images. Transl Oncol 2022;24:101494. https://doi.org/10.1016/j.tranon.2022.101494.Search in Google Scholar PubMed PubMed Central

30. MathWorks. Detector performance analysis using ROC curves [Internet]. The MathWorks, Inc; 2020. https://www.mathworks.com/help/phased/detection-and-system-analysis.html [Accessed 10 Oct 2022].Search in Google Scholar

31. Powers, DM. Evaluation: from precision, recall and F-measure to ROC, informedness, markedness correlation. Int J Mach Learn Technol 2008;2:37–63.Search in Google Scholar

32. Sobecki, P, Jóźwiak, R, Sklinda, K, Przelaskowski, A. Effect of domain knowledge encoding in CNN model architecture-a prostate cancer study using mpMRI images. PeerJ 2021;9:e11006. https://doi.org/10.7717/peerj.11006.Search in Google Scholar PubMed PubMed Central

33. Soni, M, Khan, IR, Babu, KS, Nasrullah, S, Madduri, A, Rahin, SA. Light weighted healthcare CNN model to detect prostate cancer on multiparametric MRI. Comput Intell Neurosci 2022;2022:5497120–11. https://doi.org/10.1155/2022/5497120.Search in Google Scholar PubMed PubMed Central

34. Sultana, S, Robinson, A, Song, DY, Lee, J. CNN-based hierarchical coarse-to-fine segmentation of pelvic CT images for prostate cancer radiotherapy. Proc SPIE-Int Soc Opt Eng 2020;11315:113151I. https://doi.org/10.1117/12.2549979.Search in Google Scholar PubMed PubMed Central

35. Rigaud, J, Tiguert, R, Le Normand, L, Karam, G, Glemain, P, Buzelin, JM, et al.. Prognostic value of bone scan in patients with metastatic prostate cancer treated initially with androgen deprivation therapy. J Urol 2002;168:1423–6. https://doi.org/10.1097/00005392-200210010-00029.Search in Google Scholar

36. Soloway, MS, Hardeman, SW, Hickey, D, Raymond, J, Todd, B, Soloway, S, et al.. Stratification of patients with metastatic prostate cancer based on extent of disease on initial bone scan. Cancer 1988;61:195–202. https://doi.org/10.1002/1097-0142(19880101)61:1<195:aid-cncr2820610133>3.0.co;2-y.10.1002/1097-0142(19880101)61:1<195::AID-CNCR2820610133>3.0.CO;2-YSearch in Google Scholar

37. Imbriaco, M, Larson, SM, Yeung, HW, Mawlawi, OR, Erdi, Y, Venkatraman, ES, et al.. A new parameter for measuring metastatic bone involvement by prostate cancer: the bone scan index. Clin Cancer Res 1998;4:1765–72.Search in Google Scholar

38. Ulmert, D, Kaboteh, R, Fox, JJ, Savage, C, Evans, MJ, Lilja, H, et al.. A novel automated platform for quantifying the extent of skeletal tumour involvement in prostate cancer patients using the Bone Scan Index. Eur Urol 2012;62:78–84. https://doi.org/10.1016/j.eururo.2012.01.037.Search in Google Scholar PubMed PubMed Central

39. Armstrong, AJ, Anand, A, Edenbrandt, L, Bondesson, E, Bjartell, A, Widmark, A, et al.. Phase 3 assessment of the automated bone scan index as a prognostic imaging biomarker of overall survival in men with metastatic castration-resistant prostate cancer: a secondary analysis of a randomized clinical trial. JAMA Oncol 2018;4:944–51. https://doi.org/10.1001/jamaoncol.2018.1093.Search in Google Scholar PubMed PubMed Central

40. Nakajima, K, Mizokami, A, Matsuyama, H, Ichikawa, T, Kaneko, G, Takahashi, S, et al.. Prognosis of patients with prostate cancer and bone metastasis from the Japanese prostatic cancer registry of standard hormonal and chemotherapy using bone scan index cohort study. Int J Urol 2021;28:955–63. https://doi.org/10.1111/iju.14614.Search in Google Scholar PubMed PubMed Central

41. Crnalic, S, Löfvenberg, R, Bergh, A, Widmark, A, Hildingsson, C. Predicting survival for surgery of metastatic spinal cord compression in prostate cancer: a new score. Spine 2012;37:2168–76. https://doi.org/10.1097/brs.0b013e31826011bc.Search in Google Scholar PubMed

42. Owari, T, Miyake, M, Nakai, Y, Morizawa, Y, Hori, S, Anai, S, et al.. A genitourinary cancer-specific scoring system for the prediction of survival in patients with bone metastasis: a retrospective analysis of prostate cancer, renal cell carcinoma, and urothelial carcinoma. Anticancer Res 2018;38:3097–103. https://doi.org/10.21873/anticanres.12568.Search in Google Scholar PubMed

Supplementary Material

This article contains supplementary material (https://doi.org/10.1515/oncologie-2023-0115).

Received: 2023-03-16
Accepted: 2023-06-12
Published Online: 2023-06-28

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

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

Articles in the same Issue

  1. Frontmatter
  2. Review Article
  3. Ethosomes as delivery system for treatment of melanoma: a mini-review
  4. Research Articles
  5. Pre-treatment predictors of cardiac dose exposure in left-sided breast cancer radiotherapy patients after breast conserving surgery
  6. Glycoprofiling of early non-small cell lung cancer using lectin microarray technology
  7. Overexpression of TRIM28 predicts an unfavorable prognosis and promotes the proliferation and migration of hepatocellular carcinoma
  8. MiRNA-219a-1-3p inhibits the malignant progression of gastric cancer and is regulated by DNA methylation
  9. The effect of ubiquitin-specific peptidase 21 on proliferation, migration, and invasion in DU145 cells
  10. Automatic prediction model of overall survival in prostate cancer patients with bone metastasis using deep neural networks
  11. Clinical neutrophil-related gene helps treat bladder urothelial carcinoma
  12. Forkhead Box P4 promotes the proliferation of cells in colorectal adenocarcinoma
  13. Effect of a CrossMab cotargeting CD20 and HLA-DR in non-Hodgkin lymphoma
  14. Case Reports
  15. Endoscopic resection of gastric glomus tumor: a case report and literature review
  16. Long bone metastases of renal cell carcinoma imaging features: case report and literature review
  17. The Warthin-like variant of papillary thyroid carcinomas: a clinicopathologic analysis report of two cases
  18. Corrigendum
  19. Corrigendum to: Experience of patients with metastatic breast cancer in France: results of the 2021 RÉALITÉS survey and comparison with 2015 results
https://doi.org/10.1515/oncologie-2023-0115
Keywords for this article
bone metastasis; bone scan; convolutional neural network; overall survival; prostate cancer
Creative Commons
BY 4.0

Articles in the same Issue

  1. Frontmatter
  2. Review Article
  3. Ethosomes as delivery system for treatment of melanoma: a mini-review
  4. Research Articles
  5. Pre-treatment predictors of cardiac dose exposure in left-sided breast cancer radiotherapy patients after breast conserving surgery
  6. Glycoprofiling of early non-small cell lung cancer using lectin microarray technology
  7. Overexpression of TRIM28 predicts an unfavorable prognosis and promotes the proliferation and migration of hepatocellular carcinoma
  8. MiRNA-219a-1-3p inhibits the malignant progression of gastric cancer and is regulated by DNA methylation
  9. The effect of ubiquitin-specific peptidase 21 on proliferation, migration, and invasion in DU145 cells
  10. Automatic prediction model of overall survival in prostate cancer patients with bone metastasis using deep neural networks
  11. Clinical neutrophil-related gene helps treat bladder urothelial carcinoma
  12. Forkhead Box P4 promotes the proliferation of cells in colorectal adenocarcinoma
  13. Effect of a CrossMab cotargeting CD20 and HLA-DR in non-Hodgkin lymphoma
  14. Case Reports
  15. Endoscopic resection of gastric glomus tumor: a case report and literature review
  16. Long bone metastases of renal cell carcinoma imaging features: case report and literature review
  17. The Warthin-like variant of papillary thyroid carcinomas: a clinicopathologic analysis report of two cases
  18. Corrigendum
  19. Corrigendum to: Experience of patients with metastatic breast cancer in France: results of the 2021 RÉALITÉS survey and comparison with 2015 results
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 13.9.2025 from https://www.degruyterbrill.com/document/doi/10.1515/oncologie-2023-0115/html
Scroll to top button