黃斑部皺褶，是一種慢性眼疾，經常發生在年長者身上，患者視網膜的黃斑 部會產生皺摺，進而影響視力。不過，雖然已知此疾病對於視力有非常重大的影 響，但在同樣患有此疾病的患者當中，卻可能擁有不同的視力分布，有些病人的 視力可能僅僅只有 0.1，有些病人卻能夠擁有高達 1.0 的視力。視力的差異難以單 純地依靠肉眼檢視醫學影像來判斷，因此，以深度學習為基礎的電腦視覺將可能 是一個有效之方法。

深度學習在這幾年來可以說是蓬勃發展，尤其是在影像辨識方面更是有著相 當優異的表現，本論文將使用 Resnet18、Resnet50、MobilenetV2、ShuffleV2 這四 種神經網路來加以分析，透過卷積神經網路強大的圖形識別能力，來幫助我們找 到在患有黃斑部皺褶的病人的黃斑部之中影響視力最為關鍵的部分。本論文所使 用的資料集是採用台大醫院眼科所提供的 angio retina 影像，它是一種使用了光學 原理成像的眼底血管影像，由於本論文中所使用到的資料集較難以蒐集，所以在 數量上比較稀少，因此除了針對資料集做了資料增強來增加資料集的數量外，另 外還有使用投票法、K 折交叉驗證等方法，來提升模型的表現，在實驗的最後， 本論文採用了 Grad-CAM++這個工具，使訓練結果可以視覺化，以熱像圖的方式 描繪出卷積神經網路所關注的區域，希望此有助於眼科醫師的臨床判斷。

Epiretinal Membrane (ERM) is a chronic eye disease that often occurs in the elderly. The macular area of the retina of the patient will be wrinkled, which will affect vision. However, although this disease is known to have a very significant impact on vision, the patients with this disease may have different visual acuity. Some patients’ visual acuity (VA) may only be 0.1, while some patients’ VA can be 1.0. It is difficult to judge the difference in vision through medical images by naked eyes. Therefore, computer vision based on deep learning may be an effective method.

Deep learning has flourished in recent years, especially in image recognition. In this thesis, we will use Resnet18, Resnet50, MobilenetV2, and ShuffleV2 these four neural network models to help us to find the most critical part of the macula of patients with ERM. The dataset used in this thesis is “angio retina”, which is provided by the Department of Ophthalmology of National Taiwan University Hospital. It is a blood vessel image of the eye. Since it is difficult to collect the images, the amount of the images is relatively small. Thus, we use data augmentation to increase the amount of images. In addition, we used voting and the K-fold cross-validation to improve the performance of the model. At the end of the experiment, we used Grad-CAM++ to visualize the training results. It is expected that the experimental results can really help ophthalmologists clinically.

[1] C. Cortes and V . V apnik, "Support-vector networks." Machine learning, 1995. vol 20, pp. 273-297.

[2] J. De Fauw, J.R. Ledsam, B. Romera-Paredes, S. Nikolov, N. Tomasev, S. Blackwell, H. Askham, X. Glorot, B. O’Donoghue, and D. Visentin, "Clinically applicable deep learning for diagnosis and referral in retinal disease." Nature medicine, 2018. vol 24, pp. 1342-1350.

[3] C.S. Lee, D.M. Baughman, and A.Y. Lee, "Deep learning is effective for classifying normal versus age-related macular degeneration OCT images." Ophthalmology Retina, 2017. vol 1, pp. 322-327.

[4] Y.C. Lo, K.H. Lin, H. Bair, W.H.H. Sheu, C.S. Chang, Y.C. Shen, and C.L. Hung, "epiretinal Membrane Detection at the ophthalmologist Level using Deep Learning of optical coherence tomography." Scientific Reports, 2020. vol 10, pp. 1-8.

[5] B.S. Wang, Y.Y. Lin, Y.T. Hsieh, C.Y. Su, and Y.H. Lai, "Study of Deep Learning Approach to Predict the Visual Acuity Using Optical Coherence Tomography Images." IEEE Engineering in Medicine & Biology Society (EMBS), 2020.

[6] Y. LeCun, L. Bottou, Y. Bengio, and P. Haffner, "Gradient-based learning applied to document recognition." Proceedings of the IEEE, 1998. vol 86, pp. 2278-2324.

[7] A. Krizhevsky, I. Sutskever, and G.E. Hinton, "Imagenet classification with deep convolutional neural networks." Advances in neural information processing systems, 2012. vol 25, pp. 1097-1105.

[8] K. He, X. Zhang, S. Ren, and J. Sun. "Deep residual learning for image recognition". in Proceedings of the IEEE conference on computer vision and pattern recognition. 2016.

[9] X. Glorot and Y. Bengio. "Understanding the difficulty of training deep feedforward neural networks". in Proceedings of the thirteenth international conference on artificial intelligence and statistics. 2010. JMLR Workshop and Conference Proceedings.

[10] A.G. Howard, M. Zhu, B. Chen, D. Kalenichenko, W. Wang, T. Weyand, M. Andreetto, and H. Adam, "Mobilenets: Efficient convolutional neural networks for mobile vision applications." arXiv preprint arXiv:1704.04861, 2017.

[11] 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.

[12] X. Zhang, X. Zhou, M. Lin, and J. Sun. "Shufflenet: An extremely efficient convolutional neural network for mobile devices". in Proceedings of the IEEE conference on computer vision and pattern recognition. 2018.

[13] D.B. Judd and G. Wyszecki, "Color in Business, Science, and Industry. THIRD EDITION (Wiley Series in Pure and Applied Optics)". 1975: Wiley-Interscience.

[14] H. Kolb. " Simple Anatomy of the Retina". 2011; Available from: https://webvision.med.utah.edu/book/part-i-foundations/simple-anatomy-of-the-retina/?fbclid=IwAR1XrcgtVvPnZnZRsvE3jCOEMv-ZN3nvvzWCJD-
haq3Z6t10jzLDGeRxWJY .

[15] H. Gray, "Anatomy of the Human Body", ed. W.H. Lewis. 1918, Philadelphia and New York: Lea and Febiger.

[16] B.c. staff. "Medical gallery of Blausen Medical 2014". 2014.

[17] A.M. Hagag, S.S. Gao, Y. Jia, and D. Huang, "Optical coherence tomography angiography: technical principles and clinical applications in ophthalmology." Taiwan journal of ophthalmology, 2017. vol 7, pp. 115.

[18] E. Dimitriadou, A. Weingessel, and K. Hornik. "Voting-merging: An ensemble method for clustering". in International conference on artificial neural networks. 2001. Springer.

[19] H. Wang, Y. Yang, H. Wang, and D. Chen. "Soft-voting clustering ensemble". in International Workshop on Multiple Classifier Systems. 2013. Springer.

[20] S.C. Larson, "The shrinkage of the coefficient of multiple correlation." Journal of Educational Psychology, 1931. vol 22, pp. 45.

[21] F. Mosteller and D.L. Wallace, "Inference in an authorship problem: A comparative study of discrimination methods applied to the authorship of the disputed Federalist Papers." Journal of the American Statistical Association, 1963. vol 58, pp. 275-309.

[22] R. Kohavi. "A study of cross-validation and bootstrap for accuracy estimation and model selection". in Ijcai. 1995. Montreal, Canada.

[23] P.A. Devijver and J. Kittler, "Pattern recognition: A statistical approach". 1982: Prentice hall.

[24] Z.C. Lipton, "The Mythos of Model Interpretability: In machine learning, the concept of interpretability is both important and slippery." Queue, 2018. vol 16, pp. 31-57.

[25] B. Zhou, A. Khosla, A. Lapedriza, A. Oliva, and A. Torralba. "Learning deep features for discriminative localization". in Proceedings of the IEEE conference on computer vision and pattern recognition. 2016.

[26] M. Lin, Q. Chen, and S. Yan, "Network in network." arXiv preprint arXiv:1312.4400, 2013.

[27] R.R. Selvaraju, M. Cogswell, A. Das, R. Vedantam, D. Parikh, and D. Batra. "Grad-cam: Visual explanations from deep networks via gradient-based localization". in Proceedings of the IEEE international conference on computer vision. 2017.

[28] A. Chattopadhay, A. Sarkar, P. Howlader, and V.N. Balasubramanian. "Grad- cam++: Generalized gradient-based visual explanations for deep convolutional networks". in 2018 IEEE Winter Conference on Applications of Computer Vision (WACV). 2018. IEEE.

[29] M.D. Zeiler and R. Fergus. "Visualizing and understanding convolutional networks". in European conference on computer vision. 2014. Springer.

[30] S.J. Pan and Q. Yang, "A survey on transfer learning." IEEE Transactions on knowledge and data engineering, 2009. vol 22, pp. 1345-1359.

[31] L. Bottou, F.E. Curtis, and J. Nocedal, "Optimization methods for large-scale machine learning." Siam Review, 2018. vol 60, pp. 223-311.