臺灣博碩士論文加值系統

我們的研究專注於醫學圖像分析，旨在提高結直腸癌組織病理學圖像的準確分類。通過結合遷移學習和ResNet-50 CNN模型，並使用Adam優化器進行訓練，我們取得了出色的實驗結果。平均訓練準確率達到100%，平均測試準確率達到99.75%。我們的方法在結直腸癌組織病理學圖像分類方面優於其他相關研究，並超越了許多已發表的論文。這一研究成果突出了遷移學習在醫學圖像分析中的有效性，為提高結直腸癌診斷的能力提供了實用解決方案。我們相信這項研究有助於增強醫療專業人員的診斷能力，並幫助患者做出更明智的臨床決策。

Our research focuses on medical image analysis and aims to improve the accurate classification of colorectal cancer histopathology images. By combining transfer learning and the ResNet-50 CNN model, trained with the Adam optimizer, we achieved excellent experimental results. The average training accuracy reached 100%, the average test accuracy reached 99.75%. Our method outperforms other related studies in the classification of colorectal cancer histopathology images and outperforms many published papers. This research achievement highlights the effectiveness of transfer learning in medical image analysis and provides a practical solution for improving the ability of colorectal cancer diagnosis. We believe this research can help enhance the diagnostic capabilities of medical professionals and help patients make more informed clinical decisions.

摘要 I
Abstract II
Acknowledgments III
Table of Contents IV
List of Figures VI
List of Table VIII
Chapter 1 Introduction 1
1.1 Research Background 1
1.2 Research Motivation and Objectives 3
1.3 Research Contributions 7
Chapter 2 Literature Review 9
2.1 Clinical Characteristics of Colorectal Cancer 11
2.2 Classification Methods for Colorectal Cancer 12
2.3 Convolutional Neural Network(CNN) 14
2.4 Deep Learning 19
2.5 Optimizer 21
2.6 Network Architecture 25
2.7 Evaluation Metrics 27
2.8 AI for Colorectal Cancer and Related Applications 31
Chapter 3 Research methods 34
3.1 Data processing method 34
3.2 Pretrained Network 36
3.3 Experimental Design 38
3.4 Five Elements of Neural Networks 42
Chapter 4 Experimental Results and Discussion 45
4.1 Experimental process 45
4.2 Experimental results 48
4.3 Results and Comparison 72
Chapter 5 Conclusion and Future Prospects 73
References 75

[1]Liu, X., et al. (2021). A comparison of deep learning performance against health-care professionals in detecting diseases from medical imaging: a systematic review and meta-analysis. Lancet Digit Health 3, e727–e740.
[2]Gurcan, M. N., et al. (2009). Histopathological image analysis: A review. IEEE Reviews in Biomedical Engineering, 2, 147-171.
[3]Sung, H., et al. (2021). Global cancer statistics 2020: GLOBOCAN estimates of incidence and mortality worldwide for 36 cancers in 185 countries. CA: A Cancer Journal for Clinicians, 71(3), 209-249.
[4]Siegel, R. L., Miller, K. D., & Jemal, A. (2019). Cancer statistics, 2019. CA: A Cancer Journal For Clinicians, 69(1), 7-34.
[5]Kavitha, M. S., et al. (2022). Deep Neural Network Models for Colon Cancer Screening. Cancers, 14(15), 3707.
[6]Lieberman, D. A., et al. (2012). Guidelines for colonoscopy surveillance after screening and polypectomy: a consensus update by the US Multi-Society Task Force on Colorectal Cancer. Gastroenterology, 143(3), 844-857.
[7]Misawa, M., et al. (2018). Artificial intelligence-assisted polyp detection for colonoscopy: initial experience. Gastroenterology, 154(8), 2027-2029.
[8]World Health Organization. (2018). Cancer.
https://www.who.int/news-room/fact-sheets/detail/cancer
(最後查詢日期 : 2023.07.07)
[9]Wong, M. C., et al. (2021). Differences in incidence and mortality trends of colorectal cancer worldwide based on sex, age, and anatomic location. Clinical Gastroenterology and Hepatology, 19(5), 955-966.
[10]Bernal, J., et al. (2015). WM-DOVA maps for accurate polyp highlighting in colonoscopy: Validation vs. saliency maps from physicians. Computerized Medical Imaging and Graphics, 43, 99-111.
[11]Wang, P., et al. (2018). Development and validation of a deep-learning algorithm for the detection of polyps during colonoscopy. Nature Biomedical Engineering, 2(10), 741-748.
[12]Topol, E. J. (2019). High-performance medicine: the convergence of human and artificial intelligence. Nature Medicine, 25(1), 44-56.
[13]Rajkomar, A., Dean, J., & Kohane, I. (2019). Machine learning in medicine. New England Journal of Medicine, 380(14), 1347-1358.
[14]American Cancer Society. (2021). Colorectal Cancer Signs and Symptoms.https://www.cancer.org/cancer/colon-rectal-cancer/detection-diagnosis-staging/signs-and-symptoms.html
(Last query date : 2023.07.31)
[15]Jiang, M., et al. (2021). Detection and clinical significance of circulating tumor cells in colorectal cancer. Biomarker Research, 9, 1-20.
[16]Sirinukunwattana, K., et al. (2016). Locality sensitive deep learning for detection and classification of nuclei in routine colon cancer histology images. IEEE Transactions on Medical Imaging, 35(5), 1196-1206.
[17]Shen, D., Wu, G., & Suk, H. I. (2017). Deep learning in medical image analysis. Annual Review of Biomedical Engineering, 19, 221-248.
[18]LeCun, Y., Bottou, L., Bengio, Y., & Haffner, P. (1998). Gradient-based learning applied to document recognition. In Proceedings of the IEEE, 86(11), 2278-2324.
[19]Simonyan, K., & Zisserman, A. (2014). Very deep convolutional networks for large-scale image recognition. arXiv preprint arXiv:1409.1556.
[20]Scherer, D., Müller, A., & Behnke, S. (2010). Evaluation of pooling operations in convolutional architectures for object recognition. In Proceedings of the Artificial Neural Networks 20th International Conference (ICANN 2010), Thessaloniki, Greece, September 15-18, 2010, Part III 20 ,92-101. Springer Berlin Heidelberg.
[21]Zhou, B., Khosla, A., Lapedriza, A., Oliva, A., & Torralba, A. (2016). Learning deep features for discriminative localization. In Proceedings of the IEEE conference on computer vision and pattern recognition (pp. 2921-2929).
[22]Huang, G., Liu, Z., Van Der Maaten, L., & Weinberger, K. Q. (2017). Densely connected convolutional networks. In Proceedings of the IEEE conference on computer vision and pattern recognition (pp. 4700-4708).
[23]LeCun, Y., Bengio, Y., & Hinton, G. (2015). Deep learning. Nature, 521(7553), 436-444.
[24]Dean, J., et al. (2012). Large scale distributed deep networks. Advances in Neural Information Processing Systems, 25.
[25]Weiss, K., Khoshgoftaar, T. M., & Wang, D. (2016). A survey of transfer learning. Journal of Big Data, 3(1), 1-40.
[26]Kornblith, S., Shlens, J., & Le, Q. V. (2019). Do better imagenet models transfer better?. In Proceedings of the IEEE/CVF conference on computer vision and pattern recognition, 2661-2671.
[27]Rumelhart, D. E., Hinton, G. E., & Williams, R. J. (1986). Learning representations by back-propagating errors. Nature, 323(6088), 533-536.
[28]Kingma, D. P., & Ba, J. (2014). Adam: A method for stochastic optimization. arXiv preprint arXiv:1412.6980.
[29]Krizhevsky, A., Sutskever, I., & Hinton, G. E. (2017). Imagenet classification with deep convolutional neural networks. Communications of the ACM, 60(6), 84-90.
[30]He, K., Zhang, X., Ren, S., & Sun, J. (2016). Deep residual learning for image recognition. In Proceedings of the IEEE conference on computer vision and pattern recognition,770-778.
[31]Powers, D. M. (2020). Evaluation: from precision, recall and F-measure to ROC, informedness, markedness and correlation. arXiv preprint arXiv:2010.16061.
[32]Hossin, M., & Sulaiman, M. N. (2015). A review on evaluation metrics for data classification evaluations. International Journal of Data Mining and Knowledge Management Process, 5(2), 1.
[33]Davis, J., & Goadrich, M. (2006, June). The relationship between Precision-Recall and ROC curves. In Proceedings of the 23rd international conference on Machine learning, 233-240.
[34]Sokolova, M., & Lapalme, G. (2009). A systematic analysis of performance measures for classification tasks. Information Processing and Management, 45(4), 427-437.
[35]Flach, P., & Kull, M. (2015). Precision-recall-gain curves: PR analysis done right. Advances in Neural Information Processing Systems, 28.
[36]Kather, J. N., et al. (2019). Predicting survival from colorectal cancer histology slides using deep learning: A retrospective multicenter study. PLoS Medicine, 16(1), e1002730.
[37]Li, J., et al. (2022). DARC: Deep adaptive regularized clustering for histopathological image classification. Medical Image Analysis, 80, 102521.
[38]Hamida, A. B., et al. (2022). Weakly Supervised Learning using Attention gates for colon cancer histopathological image segmentation. Artificial Intelligence in Medicine, 133, 102407.
[39]Ghosh, S., Bandyopadhyay, A., Sahay, S., Ghosh, R., Kundu, I., & Santosh, K. C. (2021). Colorectal histology tumor detection using ensemble deep neural network. Engineering Applications of Artificial Intelligence, 100, 104202.
[40]Kumar, A., Vishwakarma, A., & Bajaj, V. (2023). Crccn-net: Automated framework for classification of colorectal tissue using histopathological images. Biomedical Signal Processing and Control, 79, 104172.
[41]Hamida, A. B., et al. (2021). Deep learning for colon cancer histopathological images analysis. Computers in Biology and Medicine, 136, 104730.
[42]Kather, J. N. (2019). Benchmark Dataset of 100,000 Histological Images of Human Colorectal Cancer and Healthy Tissue. Zenodo. Retrieved from https://zenodo.org/record/1214456
(Last query date : 2023.07.31)
[43]Pan, S. J., & Yang, Q. (2010). A survey on transfer learning. IEEE Transactions on Knowledge and Data Engineering, 22(10), 1345-1359.
[44]Shin, H. C., et al. (2016). Deep convolutional neural networks for computer-aided detection: CNN architectures, dataset characteristics and transfer learning. IEEE Transactions on Medical Imaging, 35(5), 1285-1298.