SASAN: ground truth for the effective segmentation and classification of skin cancer using biopsy images

Sajid Khan; Muhammad Asif Khan; Adeeb Noor; Kainat Fareed

doi:10.1515/dx-2024-0012

Article

SASAN: ground truth for the effective segmentation and classification of skin cancer using biopsy images

Sajid Khan , Muhammad Asif Khan , Adeeb Noor and Kainat Fareed

Published/Copyright: March 18, 2024

Published by

Become an author with De Gruyter Brill

Submit Manuscript Author Information Explore this Subject

From the journal Diagnosis Volume 11 Issue 3

Abstract

Objectives

Early skin cancer diagnosis can save lives; however, traditional methods rely on expert knowledge and can be time-consuming. This calls for automated systems using machine learning and deep learning. However, existing datasets often focus on flat skin surfaces, neglecting more complex cases on organs or with nearby lesions.

Methods

This work addresses this gap by proposing a skin cancer diagnosis methodology using a dataset named ASAN that covers diverse skin cancer cases but suffers from noisy features. To overcome the noisy feature problem, a segmentation dataset named SASAN is introduced, focusing on Region of Interest (ROI) extraction-based classification. This allows models to concentrate on critical areas within the images while ignoring learning the noisy features.

Results

Various deep learning segmentation models such as UNet, LinkNet, PSPNet, and FPN were trained on the SASAN dataset to perform segmentation-based ROI extraction. Classification was then performed using the dataset with and without ROI extraction. The results demonstrate that ROI extraction significantly improves the performance of these models in classification. This implies that SASAN is effective in evaluating performance metrics for complex skin cancer cases.

Conclusions

This study highlights the importance of expanding datasets to include challenging scenarios and developing better segmentation methods to enhance automated skin cancer diagnosis. The SASAN dataset serves as a valuable tool for researchers aiming to improve such systems and ultimately contribute to better diagnostic outcomes.

Keywords: annotation; ASAN dataset; biomedical image processing; region of interest extraction; skin cancer biology; skin cancer diagnosis

Corresponding author: Sajid Khan, Department of Computer Science, School of Engineering, Central Asian University, Tashkent, Uzbekistan, E-mail: s.khan@centralasian.uz

Acknowledgments

We acknowledge the efforts of Dr. Ashok Kumar (M.B.B.S, dermatologist) of Samadha skin care clinic, Sukkur to help us understand the boundaries of dif-ferent types of lesions.

Research ethics: Not applicable.
Informed consent: Informed consent was obtained from all individuals included in this study.
Author contributions: Conceptualization, methodology, and experiments Sajid Khan; validation, Kainat Fareed; annotation of ground truths, Muhammad Asif Khan, and Kainat Fareed; writing, review and editing, Adeeb Noor; funding acquisition, Adeeb Noor. All authors have accepted responsibility for the entire content of this manuscript and approved its submission.
Competing interests: The authors state no conflict of interest.
Research funding: Not applicable.
Data availability: All the datasets created, python and MATLAB codes, along with the top five trained segmentation networks can be downloaded from https://github.com/sajidkhandipDL/SASAN -Any other information/data can be obtained on request from the corresponding author.

References

1. Das, K, Cockerell, CJ, Patil, A, Pietkiewicz, P, Giulini, M, Grabbe, S, et al.. Machine learning and its application in skin cancer. Int J Environ Res Public Health 2021;18:13409. https://doi.org/10.3390/ijerph182413409.Search in Google Scholar PubMed PubMed Central

2. Iqbal, I, Younus, M, Walayat, K, Kakar, MU, Ma, J. Automated multi-class classification of skin lesions through deep convolutional neural network with dermoscopic images. CMIG (Comput Med Imaging Graph) 2021;88:101843. https://doi.org/10.1016/j.compmedimag.2020.101843.Search in Google Scholar PubMed

3. Khamparia, A, Singh, PK, Rani, P, Samanta, D, Khanna, A, Bhushan, B. An internet of health things-driven deep learning framework for detection and classification of skin cancer using transfer learning. ETT 2021;32:e3963. https://doi.org/10.1002/ett.3963.Search in Google Scholar

4. Shakya, BR, Shrestha, P, Teppo, HR, Rieppo, L. The use of Fourier Transform Infrared (FTIR) spectroscopy in skin cancer research: a systematic review. Appl Spectrosc Rev 2021;56:347–79. https://doi.org/10.1080/05704928.2020.1791152.Search in Google Scholar

5. Saghir, U, Devendran, V. A brief review of feature extraction methods for melanoma detection. In: Proceedings of the 7th international conference on advanced computing and communication systems; 2021. 1304–7 pp.10.1109/ICACCS51430.2021.9441787Search in Google Scholar

6. Afza, F, Sharif, M, Mittal, M, Khan, MA, Hemanth, DJ. A hierarchical three-step superpixels and deep learning framework for skin lesion classification. Methods 2022;202:88–102. https://doi.org/10.1016/j.ymeth.2021.02.013.Search in Google Scholar PubMed

7. Chaturvedi, SS, Gupta, K, Prasad, PS. Skin lesion analyser: an efficient seven-way multi-class skin cancer classification using mobilenet. In: Proceedings of the international conference on advanced machine learning technologies and applications. Singapore; 2020. 165–76 pp.10.1007/978-981-15-3383-9_15Search in Google Scholar

8. Manne, R, Kantheti, S, Kantheti, S. Classification of skin cancer using deep learning, convolutional neural networks-opportunities and vulnerabilities-A systematic review. Int J Mod Trends Sci Technol 2020;6:2455–3778. https://doi.org/10.46501/IJMTST061118.Search in Google Scholar

9. Al-Masni, MA, Kim, DH, Kim, TS. Multiple skin lesions diagnostics via integrated deep convolutional networks for segmentation and classification. Comput Methods Progr Biomed 2020;190:105351. https://doi.org/10.1016/j.cmpb.2020.105351.Search in Google Scholar PubMed

10. Thiyaneswaran, B, Anguraj, K, Kumarganesh, S, Thangaraj, K. Early detection of melanoma images using gray level co-occurrence matrix features and machine learning techniques for effective clinical diagnosis. Int J Imag Syst Technol 2021;31:682–94. https://doi.org/10.1002/ima.22514.Search in Google Scholar

11. Lozano, R, Naghavi, M, Foreman, K, Lim, S, Shibuya, K, Aboyans, V, et al.. Global and regional mortality from 235 causes of death for 20 age groups in 1990 and 2010: a systematic analysis for the Global Burden of Disease Study 2010. Lancet 2012;380:2095–128. https://doi.org/10.1016/S0140-6736(12)61728-0.Search in Google Scholar PubMed PubMed Central

12. Qureshi, MN, Umar, MS. Performance evaluation of novel convolution neural network architecture for melanoma skin cancer diagnosis on different hardware processing units. In: Proceedings of ICMAI. Gurgaon, India; 2021. 12039 p.10.1088/1742-6596/1950/1/012039Search in Google Scholar

13. Hasan, MK, Dahal, L, Samarakoon, PN, Tushar, FI, Martí, R. DSNet: automatic dermoscopic skin lesion segmentation. Comput Biol Med 2020;120:103738. https://doi.org/10.1016/j.compbiomed.2020.103738.Search in Google Scholar PubMed

14. Khan, SA, Nazir, M, Khan, MA, Saba, T, Javed, K, Rehman, A, et al.. Lungs nodule detection framework from computed tomography images using support vector machine. Microsc Res Tech 2019;82:1256–66. https://doi.org/10.1002/jemt.23275.Search in Google Scholar PubMed

15. Minhas, K, Khan, MT, Arsalan, M, Naqvi, SS, Ahmed, M, Khan, HA, et al.. Accurate pixel-wise skin segmentation using shallow fully convolutional neural network. IEEE Access 2020;8:156314–27. https://doi.org/10.1109/ACCESS.2020.3019183.Search in Google Scholar

16. Khan, MT, Robles-Kelly, A, Naqvi, SS. T-Net: A resource-constrained tiny convolutional neural network for medical image segmentation. In: Proceedings of the IEEE/CVF winter conference on applications of computer vision; 2022: 644–53 pp.10.1109/WACV51458.2022.00186Search in Google Scholar

17. Yap, MH, Goyal, M, Osman, F, Ahmad, E, Martí, R, Denton, E, et al.. End-to-end breast ultrasound lesions recognition with a deep learning approach. In: Proceedings of the medical imaging 2018: biomedical applications in molecular, structural, and functional imaging. Houston, Texas, United States; 2018. 1057819 p.Search in Google Scholar

18. Havaei, M, Davy, A, Warde-Farley, D, Biard, A, Courville, A, Bengio, Y, et al.. Brain tumor segmentation with deep neural networks. Med Image Anal 2017;35:18–31. https://doi.org/10.1016/j.media.2016.05.004.Search in Google Scholar PubMed

19. Wei, JW, Tafe, LJ, Linnik, YA, Vaickus, LJ, Tomita, N, Hassanpour, S. Pathologist-level classification of histologic patterns on resected lung adenocarcinoma slides with deep neural networks. Sci Rep 2019;9:1–8. https://doi.org/10.1038/s41598-019-40041-7.Search in Google Scholar PubMed PubMed Central

20. Naveed, A, Naqvi, SS, Khan, MT, Razzak, I. PCA: progressive class-wise attention for skin lesions diagnosis. Eng Appl Artif Intell 2024;127:107417, https://doi.org/10.1016/j.engappai.2023.Search in Google Scholar

21. Mendonça, T, Ferreira, PM, Marques, JS, Marcal, AR, Rozeira, J. PH 2-A dermoscopic image database for research and benchmarking. Proceedings of the 35th annual international conference of the IEEE EMBC. Osaka, Japan; 2013. 5437–40 pp.10.1109/EMBC.2013.6610779Search in Google Scholar PubMed

22. Gutman, D, Codella, NC, Celebi, E, Helba, B, Marchetti, M, Mishra, N, et al.. Skin lesion analysis toward melanoma detection: a challenge at the international symposium on biomedical imaging (ISBI) 2016 hosted by the international skin imaging collaboration (ISIC), arXiv: 1605.01397; 2016.Search in Google Scholar

23. Codella, NC, Gutman, D, Celebi, ME, Helba, B, Marchetti, MA, Dusza, SW, 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). In: Proceedings of IEEE 15th international symposium on biomedical imaging. ISBI 2018, Washington, DC, USA; 2018. 168–72 pp.10.1109/ISBI.2018.8363547Search in Google Scholar

24. Razzak, I, Shoukat, G, Naz, S, Khan, MT. Skin lesion analysis toward accurate detection of melanoma using multistage fully connected residual network. In: IEEE international joint conference on neural networks; 2020. 1–8 pp.10.1109/IJCNN48605.2020.9206881Search in Google Scholar

25. Zhou, Q, He, T, Zou, Y. Superpixel-oriented label distribution learning for skin lesion segmentation. Diagnostics 2022;12:938. https://doi.org/10.3390/diagnostics12040938.Search in Google Scholar PubMed PubMed Central

26. Rotemberg, V, Kurtansky, N, Betz-Stablein, B, Caffery, L, Chousakos, E, Codella, N, et al.. A patient-centric dataset of images and metadata for identifying melanomas using clinical context. Sci Data 2021;8:1–8. https://doi.org/10.1038/s41597-021-00815-z.Search in Google Scholar PubMed PubMed Central

27. ASAN dataset. Available online: https://figshare.com/articles/figure/Asan_and_Hallym_Dataset_Thumbnails_/5406136 [Accessed 21 February 2024].Search in Google Scholar

28. Tschandl, P, Rosendahl, C, Kittler, H. The HAM10000 dataset, a large collection of multi-source dermatoscopic images of common pigmented skin lesions. Sci Data 2018;5:1–9. https://doi.org/10.1038/sdata.2018.161.Search in Google Scholar PubMed PubMed Central

29. Albumentations – image augmentation library. Available online: https://albumentations.ai/ [Accessed 21 February 2024].Search in Google Scholar

30. SASAN: a groundtruth for the segmentation of skin cancer lesion. Available online: https://github.com/sajidkhandipDL/SASAN [Accessed 25 February 2024].Search in Google Scholar

31. Adegun, A, Viriri, S. Deep learning techniques for skin lesion analysis and melanoma cancer detection: a survey of state-of-the-art. Artif Intell Rev 2021;54:811–41. https://doi.org/10.1007/s10462-020-09865-y.Search in Google Scholar

32. Yang, R, Yu, Y. Artificial convolutional neural network in object detection and semantic segmentation for medical imaging analysis. Front Oncol 2021;11:638182. https://doi.org/10.3389/fonc.2021.638182.Search in Google Scholar PubMed PubMed Central

33. Ronneberger, O, Fischer, P, Brox, T. U-net: convolutional networks for biomedical image segmentation. In: Proceedings of international conference on medical imaging computing and computer-assisted intervention; 2015. 234–41 pp.10.1007/978-3-319-24574-4_28Search in Google Scholar

34. Chaurasia, A, Culurciello, E. Linknet: exploiting encoder representations for efficient semantic segmentation. In: Proceedings of IEEE visual communications and image processing. VCIP, St. Petersburg, FL, USA; 2017. 1–4 pp.10.1109/VCIP.2017.8305148Search in Google Scholar

35. Lin, TY, Dollár, P, Girshick, R, He, K, Hariharan, B, Belongie, S. Feature pyramid networks for object detection. In: Proceedings of the IEEE conference on computer vision and pattern recognition; 2017. 2117–25 pp.10.1109/CVPR.2017.106Search in Google Scholar

36. Miradwal, S, Mohammad, W, Jain, A, Khilji, F. Lesion segmentation in skin cancer detection using UNet architecture. Comput Intell Data Anal 2022;142:329–40. https://doi.org/10.1007/978-981-19-3391-2_25.Search in Google Scholar

37. Widiansyah, M, Rasyid, S, Wisnu, P, Wibowo, A. Image segmentation of skin cancer using MobileNet as an encoder and linknet as a decoder. J Phys: Conf Ser. 2021;1943:012113. https://doi.org/10.1088/1742-6596/1943/1/012113.Search in Google Scholar

38. Pu, B, Lu, Y, Chen, J, Li, S, Zhu, N, Wei, W, Li, K, et al.. MobileUNet-FPN: a semantic segmentation model for fetal ultrasound four-chamber segmentation in edge computing environments. IEEE J Biomed Health Inf 2022;26:5540–50. https://doi.org/10.1109/jbhi.2022.3182722.Search in Google Scholar

39. Lima, JGP, Junior, GB, Almeida, JDS, Matos, CEF. Evaluation of encoder-decoder architectures for automatic skin lesion segmentation. In: 19th international conference on artificial intelligence in medicine; 2021. 373–7 pp.10.1007/978-3-030-77211-6_43Search in Google Scholar

40. Jaworek-Korjakowska, J, Brodzicki, A, Cassidy, B, Kendrick, C, Yap, MH. Interpretability of a deep learning based approach for the classification of skin lesions into main anatomic body sites. Cancers 2021;13:6048. https://doi.org/10.3390/cancers13236048.Search in Google Scholar PubMed PubMed Central

Received: 2024-01-14

Accepted: 2024-02-27

Published Online: 2024-03-18

You are currently not able to access this content.

Articles in the same Issue

https://doi.org/10.1515/dx-2024-0012

Keywords for this article

annotation; ASAN dataset; biomedical image processing; region of interest extraction; skin cancer biology; skin cancer diagnosis