A Comparative Analysis of Deep Learning Models for Prediction of Microsatellite Instability in Colorectal Cancer

Abstract

Colorectal cancer remains one of the most prevalent and fatal malignancies worldwide, underscoring the necessity for early and precise diagnostic approaches to enhance patient prognoses. This study proposes a deep learning-based model for predicting microsatellite instability (MSI) in colorectal cancer using hematoxylin and eosin (H&E)-stained histopathological tissue slides. A classification framework was constructed using convolutional neural networks (CNN) and optimized through transfer learning techniques. The dataset, comprising 150,000 unique H&E-stained histologic image patches, was sourced from an open-access Kaggle repository, with 80% allocated to training and 20% to testing. A comparative evaluation of nine pre-trained models demonstrated that the VGG19 architecture yielded the highest classification performance, achieving an accuracy of 90.60%, a precision of 88.60%, a sensitivity of 93.10%, and an AUC score of 90.60%. Considering its high performance, the proposed model is expected to assist pathologists in clinical decision-making, potentially enhancing diagnostic accuracy in real-world medical applications.

Keywords

• Microsatellite instability
• Deep learning
• Colorectal cancer
• Histopathologic image

References

1. K. Bardhan and K. Liu, "Epigenetics and colorectal cancer pathogenesis," Cancers (Basel), vol. 5, no. 2, pp. 676-713, 2013. doi: 10.3390/cancers5020676.
2. R. L. Siegel, K. D. Miller, A. Goding Sauer, S. A. Fedewa, L. F. Butterly, J. C. Anderson, A. Cercek, R. A. Smith, and A. Jemal, "Colorectal cancer statistics, 2020," CA Cancer J Clin, vol. 70, no. 3, pp. 145-164, 2020. doi: 10.3322/caac.21601.
3. H. Sung, J. Ferlay, R. L. Siegel, M. Laversanne, I. Soerjomataram, A. Jemal, and F. Bray, "Global Cancer Statistics 2020: GLOBOCAN Estimates of Incidence and Mortality Worldwide for 36 Cancers in 185 Countries," CA Cancer J Clin, vol. 71, no. 3, pp. 209-249, 2021. doi: 10.3322/caac.21660.
4. American Cancer Society, Colorectal Cancer Facts & Figures 2020-2022, 2020.
5. T. A. A. Tosta, P. R. de Faria, L. A. Neves, and M. Z. do Nascimento, "Computational normalization of H&E-stained histological images: Progress, challenges and future potential," Artificial Intelligence in Medicine, vol. 95, pp. 118-132, 2019. doi: 10.1016/j.artmed.2018.10.004.
6. J. R. Wiśniewski, "Proteomic sample preparation from formalin-fixed and paraffin-embedded tissue," JoVE (Journal of Visualized Experiments), no. 79, p. e50589, 2013. doi: 10.3791/50589.
7. R. Bonneville et al., "Landscape of microsatellite instability across 39 cancer types," JCO Precision Oncology, vol. 1, pp. 1-15, 2017. doi: 10.1200/PO.17.00073.
8. J. N. Kather, N. Halama, and D. Jaeger, "Genomics and emerging biomarkers for immunotherapy of colorectal cancer," Seminars in Cancer Biology, pp. 189-197, 2018. doi: 10.1016/j.semcancer.2018.02.010.

9. J. N. Nojadeh, S. B. Sharif, and E. Sakhinia, "Microsatellite instability in colorectal cancer," EXCLI Journal, vol. 17, p. 159, 2018. doi: 10.17179/excli2017-948.
10. A. J. Kacew et al., "Artificial intelligence can cut costs while maintaining accuracy in colorectal cancer genotyping," Frontiers in Oncology, vol. 11, p. 2066, 2021. doi: 10.3389/fonc.2021.630953.
11. K. Li, H. Luo, L. Huang, H. Luo, and X. Zhu, “Microsatellite instability: A review of what the oncologist should know,” Cancer Cell International, vol. 20, no. 1, pp. 1-13, 2020, doi: 10.1186/s12935-019-1091-8.
12. J. Xu, K. Xue, and K. Zhang, “Current status and future trends of clinical diagnoses via image-based deep learning,” Theranostics, vol. 9, no. 25, p. 7556, 2019, doi: 10.7150/thno.38065.
13. S. Hosseinzadeh Kassani and P. Hosseinzadeh Kassani, “A comparative study of deep learning architectures on melanoma detection,” Tissue and Cell, vol. 58, pp. 76-83, 2019, doi: 10.1016/j.tice.2019.04.009.
14. N. Coudray, P. S. Ocampo, T. Sakellaropoulos, N. Narula, M. Snuderl, D. Fenyö, A. L. Moreira, N. Razavian, and A. Tsirigos, “Classification and mutation prediction from non–small cell lung cancer histopathology images using deep learning,” Nature Medicine, vol. 24, no. 10, pp. 1559-1567, 2018, doi: 10.1038/s41591-018-0177-5.
15. M. Chen, B. Zhang, W. Topatana, J. Cao, H. Zhu, S. Juengpanich, Q. Mao, H. Yu, and X. Cai, “Classification and mutation prediction based on histopathology H&E images in liver cancer using deep learning,” npj Precision Oncology, vol. 4, no. 1, p. 14, 2020, doi: 10.1038/s41698-020-0120-3.
16. Ş. Öztürk and B. Akdemir, “HIC-net: A deep convolutional neural network model for classification of histopathological breast images,” Computers & Electrical Engineering, vol. 76, pp. 299-310, 2019, doi: 10.1016/j.compeleceng.2019.04.012.
17. J. N. Kather, A. T. Pearson, N. Halama, D. Jäger, J. Krause, S. H. Loosen, A. Marx, P. Boor, F. Tacke, U. P. Neumann, et al., “Deep learning can predict microsatellite instability directly from histology in gastrointestinal cancer,” Nature Medicine, vol. 25, no. 7, pp. 1054-1056, 2019, doi: 10.1038/s41591-019-0462-y.
18. R. Cao, F. Yang, S. C. Ma, L. Liu, Y. Zhao, Y. Li, D. H. Wu, T. Wang, W. J. Lu, W. J. Cai, et al., “Development and interpretation of a pathomics-based model for the prediction of microsatellite instability in colorectal cancer,” Theranostics, vol. 10, no. 24, pp. 11080-11091, 2020, doi: 10.7150/thno.49864.
19. X. Zhang, X. Zhou, M. Lin, and J. Sun, “Shufflenet: An extremely efficient convolutional neural network for mobile devices,” Proceedings of the IEEE Conference on Computer Vision and Pattern Recognition, pp. 6848-6856, 2018, doi: 10.48550/arXiv.1707.01083.
20. A. Echle, H. I. Grabsch, P. Quirke, P. A. van den Brandt, N. P. West, G. G. A. Hutchins, L. R. Heij, X. Tan, S. D. Richman, J. Krause, et al., “Clinical-grade detection of microsatellite instability in colorectal tumors by deep learning,” Gastroenterology, vol. 159, no. 4, pp. 1406-1416.e11, 2020, doi: 10.1053/j.gastro.2020.06.021.
21. H. Lee, J. Seo, G. Lee, J. Park, D. Yeo, and A. Hong, “Two-stage classification method for MSI status prediction based on deep learning approach,” Applied Sciences, 2021, doi: 10.3390/app11010254.
22. J. Krause, H. I. Grabsch, M. Kloor, M. Jendrusch, A. Echle, R. D. Buelow, P. Boor, T. Luedde, T. J. Brinker, C. Trautwein, et al., “Deep learning detects genetic alterations in cancer histology generated by adversarial networks,” J. Pathol., vol. 254, no. 1, pp. 70-79, 2021, doi: 10.1002/path.5638.
23. W. Zhang, H. Yin, Z. Huang, J. Zhao, H. Zheng, D. He, M. Li, W. Tan, S. Tian, and B. Song, “Development and validation of MRI-based deep learning models for prediction of microsatellite instability in rectal cancer,” Cancer Medicine, vol. 10, no. 12, pp. 4164-4173, 2021, doi: 10.1002/cam4.3957.
24. R. Yamashita, J. Long, T. Longacre, L. Peng, G. Berry, B. Martin, J. Higgins, D. L. Rubin, and J. Shen, “Deep learning model for the prediction of microsatellite instability in colorectal cancer: A diagnostic study,” The Lancet Oncology, vol. 22, no. 1, pp. 132-141, 2021, doi: 10.1016/S1470-2045(20)30535-0.
25. A. Bustos, A. Payá, A. Torrubia, R. Jover, X. Llor, X. Bessa, A. Castells, Á. Carracedo, and C. Alenda, “xDEEP-MSI: Explainable bias-rejecting microsatellite instability deep learning system in colorectal cancer,” Biomolecules, vol. 11, no. 12, 2021, doi: 10.3390/biom11121786.
26. S. H. Lee, I. H. Song, and H. J. Jang, “Feasibility of deep learning-based fully automated classification of microsatellite instability in tissue slides of colorectal cancer,” Int. J. Cancer, vol. 149, no. 3, pp. 728-740, 2021, doi: 10.1002/ijc.33599.
27. H. S. Muti et al., “Development and validation of deep learning classifiers to detect Epstein-Barr virus and microsatellite instability status in gastric cancer: A retrospective multicentre cohort study,” The Lancet Digital Health, vol. 3, no. 10, pp. e654-e664, 2021, doi: 10.1016/S2589-7500(21)00133-3.
28. W. Qiu, J. Yang, B. Wang, M. Yang, G. Tian, P. Wang, and J. Yang, “Evaluating microsatellite instability of colorectal cancer based on multimodal deep learning integrating histopathological and molecular data,” Frontiers in Oncology, p. 3011, 2022, doi: 10.3389/fonc.2022.925079.
29. C. Saillard, O. Dehaene, T. Marchand, O. Moindrot, A. Kamoun, B. Schmauch, and S. Jegou, “Self-supervised learning improves dMMR/MSI detection from histology slides across multiple cancers,” arXiv preprint arXiv:2109.05819, 2021, doi: 10.48550/arXiv.2109.05819.
30. F. Su, J. Li, X. Zhao, B. Wang, Y. Hu, Y. Sun, and J. Ji, “Interpretable tumor differentiation grade and microsatellite instability recognition in gastric cancer using deep learning,” Laboratory Investigation, vol. 102, no. 6, pp. 641-649, 2022, doi: 10.1038/s41374-022-00742-6.
31. J. Gibert, “TCGA COAD MSI vs MSS Prediction (JPG),” Kaggle, 2019. [Online]. Available: https://www.kaggle.com/datasets/joangibert/tcga_coad_msi_mss_jpg. Accessed: Dec. 24, 2024.
32. A. Janowczyk, “DOWNLOAD TCGA DIGITAL PATHOLOGY IMAGES (FFPE),” 2018. [Online]. Available: http://www.andrewjanowczyk.com/download-tcga-digital-pathology-images-ffpe. Accessed: Dec. 24, 2024.
33. M. Macenko, M. Niethammer, J. S. Marron, D. Borland, J. T. Woosley, X. G., C. Schmitt, and N. E. Thomas, “A method for normalizing histology slides for quantitative analysis,” in 2009 IEEE International Symposium on Biomedical Imaging: From Nano to Macro, 2009, pp. 1107-1110, doi: 10.1109/ISBI.2009.5193250.
34. J. N. Kather, “Histological images for MSI vs. MSS classification in gastrointestinal cancer, FFPE samples,” Zenodo, 2019. [Online]. Available: https://doi.org/10.5281/zenodo.2530835. Accessed: Dec. 25, 2024.
35. Y. LeCun, Y. Bengio, and G. Hinton, “Deep learning,” Nature, vol. 521, no. 7553, pp. 436-444, 2015, doi: 10.1038/nature14539.
36. D. Ravì, C. Wong, F. Deligianni, M. Berthelot, J. Andreu-Perez, B. Lo, and G.-Z. Yang, “Deep learning for health informatics,” IEEE Journal of Biomedical and Health Informatics, vol. 21, no. 1, pp. 4-21, 2016, doi: 10.1109/JBHI.2016.2636665.
37. S. J. Choi, E. S. Kim, and K. Choi, “Prediction of the histology of colorectal neoplasm in white light colonoscopic images using deep learning algorithms,” Scientific Reports, vol. 11, no. 1, p. 5311, 2021, doi: 10.1038/s41598-021-84299-2.
38. A. Narin, C. Kaya, and Z. Pamuk, “Automatic detection of coronavirus disease (COVID-19) using X-ray images and deep convolutional neural networks,” Pattern Analysis and Applications, vol. 24, no. 3, pp. 1207-1220, 2021, doi: 10.1007/s10044-021-00984-y.
39. S. Pereira, A. Pinto, V. Alves, and C. A. Silva, “Brain tumor segmentation using convolutional neural networks in MRI images,” IEEE Transactions on Medical Imaging, vol. 35, no. 5, pp. 1240-1251, 2016, doi: 10.1109/TMI.2016.2538465.
40. K. O'Shea and R. Nash, “An introduction to convolutional neural networks,” arXiv preprint arXiv:1511.08458, 2015.
41. S. Albawi, T. A. Mohammed, and S. Al-Zawi, “Understanding of a convolutional neural network,” in 2017 International Conference on Engineering and Technology (ICET), 2017, pp. 1-6, doi: 10.1109/ICEngTechnol.2017.8308186.
42. İ. Özkan and E. Ülker, “Derin öğrenme ve görüntü analizinde kullanılan derin öğrenme modelleri,” Gaziosmanpaşa Bilimsel Araştırma Dergisi, vol. 6, no. 3, pp. 85-104, 2017.
43. S. Indolia, A. K. Goswami, S. P. Mishra, and P. Asopa, “Conceptual understanding of convolutional neural network- A deep learning approach,” Procedia Computer Science, vol. 132, pp. 679-688, 2018, doi: 10.1016/j.procs.2018.05.069.
44. J. Lu, V. Behbood, P. Hao, H. Zuo, S. Xue, and G. Zhang, “Transfer learning using computational intelligence: A survey,” Knowledge-Based Systems, vol. 80, pp. 14-23, 2015, doi: 10.1016/j.knosys.2015.01.010.
45. O. Russakovsky, J. Deng, H. Su, J. Krause, S. Satheesh, S. Ma, Z. Huang, A. Karpathy, A. Khosla, and M. Bernstein, “Imagenet large scale visual recognition challenge,” International Journal of Computer Vision, vol. 115, no. 3, pp. 211-252, 2015, doi: 10.1007/s11263-015-0816-y.
46. Keras. https://tr.wikipedia.org/wiki/Keras. Accessed 10.07.2024
47. K. Simonyan and A. Zisserman, "Very deep convolutional networks for large-scale image recognition," arXiv preprint arXiv:1409.1556, 2014. [Online]. Available: https://doi.org/10.48550/arXiv.1409.1556.
48. S. L. Rabano, M. K. Cabatuan, E. Sybingco, E. P. Dadios, and E. J. Calilung, "Common garbage classification using mobilenet," in 2018 IEEE 10th International Conference on Humanoid, Nanotechnology, Information Technology, Communication and Control, Environment and Management (HNICEM), 2018, pp. 1-4. doi: 10.1109/HNICEM.2018.8666300.
49. W. Wang, Y. Li, T. Zou, X. Wang, J. You, and Y. Luo, "A novel image classification approach via dense-MobileNet models," Mobile Information Systems, vol. 2020, 2020. [Online]. Available: https://doi.org/10.1155/2020/7602384.
50. M. Sandler, A. Howard, M. Zhu, A. Zhmoginov, and L.-C. Chen, "Mobilenetv2: Inverted residuals and linear bottlenecks," in Proceedings of the IEEE Conference on Computer Vision and Pattern Recognition, 2018, pp. 4510-4520. [Online]. Available: https://doi.org/10.48550/arXiv.1801.04381.
51. K. Bardhan and K. Liu, "Epigenetics and colorectal cancer pathogenesis," Cancers (Basel), vol. 5, no. 2, pp. 676-713, 2013. Doi: 10.3390/cancers5020676.
52. R. L. Siegel, K. D. Miller, A. Goding Sauer, S. A. Fedewa, L. F. Butterly, J. C. Anderson, A. Cercek, R. A. Smith, and A. Jemal, "Colorectal cancer statistics, 2020," CA Cancer J Clin, vol. 70, no. 3, pp. 145-164, 2020. Doi: 10.3322/caac.21601.
53. H. Sung, J. Ferlay, R. L. Siegel, M. Laversanne, I. Soerjomataram, A. Jemal, and F. Bray, "Global Cancer Statistics 2020: GLOBOCAN Estimates of Incidence and Mortality Worldwide for 36 Cancers in 185 Countries," CA Cancer J Clin, vol. 71, no. 3, pp. 209-249, 2021. Doi: 10.3322/caac.21660.
54. ResNet-18-Pytorch. https://docs.openvino.ai/2021.1/omz_models_public_resnet_18_pytorch_resnet_1 8_pytorch.html. Accessed 25.08.2024
55. T. A. A. Tosta, P. R. de Faria, L. A. Neves, and M. Z. do Nascimento, "Computational normalization of H&E-stained histological images: Progress, challenges and future potential," Artificial Intelligence in Medicine, vol. 95, pp. 118-132, 2019. Doi: 10.1016/j.artmed.2018.10.004.
56. J. R. Wiśniewski, "Proteomic sample preparation from formalin fixed and paraffin embedded tissue," JoVE (Journal of Visualized Experiments), no. 79, p. e50589, 2013. Doi: 10.3791/50589.
57. R. Bonneville, M. A. Krook, E. A. Kautto, J. Miya, M. R. Wing, H-Z. Chen, J. W. Reeser, L. Yu, and S. Roychowdhury, "Landscape of microsatellite instability across 39 cancer types," JCO Precision Oncology, vol. 1, pp. 1-15, 2017. Doi: 10.1200/PO.17.00073.
58. J. N. Kather, N. Halama, and D. Jaeger, "Genomics and emerging biomarkers for immunotherapy of colorectal cancer," Seminars in Cancer Biology, Elsevier, pp. 189-197, 2018. Doi: 10.1016/j.semcancer.2018.02.010.
59. J. N. Nojadeh, S. B. Sharif, and E. Sakhinia, "Microsatellite instability in colorectal cancer," EXCLI Journal, vol. 17, p. 159, 2018. Doi: 10.17179/excli2017-948.
60. A. J. Kacew, G. W. Strohbehn, L. Saulsberry, N. Laiteerapong, N. A. Cipriani, J. N. Kather, and A. T. Pearson, "Artificial intelligence can cut costs while maintaining accuracy in colorectal cancer genotyping," Frontiers in Oncology, p. 2066, 2021. Doi: 10.3389/fonc.2021.630953.