近年深度學習被廣泛應用在電腦視覺的領域，其中醫療影像分類更是常利用此技術，皮膚病變分類是醫療影像分類問題中的重要課題，許多皮膚病變可以透過肉眼察覺異常，早期的發現經過治療後往往也可以痊癒，因此皮膚病變分類系統的開發具有重要性，然而由於標註的圖片樣本數不多，如何應用未標記的圖片成為一個重要課題，在本篇論文採用半監督式學習來加以利用未標記的圖片藉以提升分類準確度，在實驗中，我們發現交叉熵損失函數(cross-entropy loss)未能提供部分細節資訊，我們提出懲罰損失函數(penalty loss)來輔助交叉熵損失函數(cross-entropy loss)。我們透過5折交叉驗證(5-fold cross validation)，類別平衡權重以及懲罰損失函數(penalty loss)提高準確度，最後在ISIC2018資料集上取得0.812的平均召回率。

Deep learning technique has been used to solve computer vision problem recently. One of the most popular applications is medical image classification. Skin lesion is a disease, which can be observed visually and can be cured if professional medical treatments are accepted at an early stage, therefore, developing skin lesion classification system becomes essential. One of the most difficulties for medical images classification problem is to collect images and label them. In this thesis, we used a semi-supervised method to utilize unlabeled images and get a better accuracy. In the experiments, we found out that the cross-entropy loss does not show very discriminative information, so we improved it by adding a penalty loss term. Our loss function shows more information and make the model optimize better than the cross-entropy loss. We combined 5-fold cross-validation and balance weight of different categories with our own loss function and got a mean recall of 0.812 on ISIC2018 dataset.

[1]
H. Rogers, M. Weinstock, S. Feldman and B. Coldiron, “Incidence estimate of nonmelanoma skin cancer (keratinocyte carcinomas) in the US population.” JAMA Dermatology. Published online April 30, 2015.
[2]
American Cancer Society, “Cancer Facts & Figures 2019.” Atlanta: American Cancer Society; 2019.
[3]
R. Siegel, K. Miller and A. Jemal, “Cancer statistics, 2019.” CA : A Cancer Journal for Clinicians. 2019; doi: 10.3322/caac.21551.
[4]
P. Tschandl, C. Rosendahl and H. Kittler, “The HAM10000 dataset, a large collection of multi-source dermatoscopic images of common pigmented skin lesions.” Scientific Data , 180161 doi:10.1038/sdata.2018.161 (2018).
[5]
I. Good, "Some Terminology and Notation in Information Theory," Proceedings of the IEE - Part C: Monographs, vol. 103, no. 3, pp. 200-204, Mar. 1956.
[6]
T. Lin, P. Goyal, R. B. Girshick, K. He and P. Dollar, “Focal loss for dense object detection.” IEEE International Conference on Computer Vision, 2017.
[7]
Y. Wen, K. Zhang, Z. Li and Y. Qiao, “A discriminative feature learning approach for deep face recognition.” In European Conference on Computer Vision, pages 499–515. Springer, 2016.
[8]
G. Huang, Z. Liu, K. Q. Weinberger and L. Maaten, “Densely connected convolutional networks.” In Computer Vision and Pattern Recognition, 2017.
[9]
A. Bissoto, F. Perez, V. Ribeiro, M. Fornaciali, S. Avila and E. Valle, “Deep-learning ensembles for skin-lesion segmentation, analysis, classification: Recod titans at isic challenge 2018.” arXiv: 1808.08480, 2018.
[10]
C. Szegedy, S. Ioffe and V. Vanhoucke, “Inception-v4, inception-resnet and the impact of residual connections on learning.” In International Conference on Learning Representations Workshop, 2016.
[11]
K. He, X. Zhang, S. Ren, and J. Sun, “Deep residual learning for image recognition.” In Computer Vision and Pattern Recognition, 2016.
[12] M. Milton, “Automated Skin Lesion Classification Using Ensemble of Deep Neural Networks in ISIC 2018: Skin Lesion Analysis Towards Melanoma Detection Challenge.” arXiv: 1901.10802, 2019.
[13] C. Liu, B. Zoph, J. Shlens, W. Hua, L. Li, F. Li, A. Yuille, J. Huang and K. Murphy, “Progressive neural architecture search.” In European Conference on Computer Vision, 2018.
[14] J. Hu, L. Shen and G. Sun, “Squeeze-and-excitation networks." In Computer Vision and Pattern Recognition, 2018.
[15] T. Majtner, B. Bajic, S. Yildirim, J. Y. Hardeberg, J. Lindblad and N. Sladoje, “Ensemble of convolutional neural networks for dermoscopic images classification.” arXiv: 1808.05071, 2018.
[16]
K. Simonyan and A. Zisserman, “Very deep convolutional networks for large-scale image recognition.” In International Conference on Learning Representations, 2015.
[17]
C. Szegedy, W. Liu, Y. Jia, P. Sermanet, S. Reed, D. Anguelov, D. Erhan, V. Vanhoucke and A. Rabinovich, “Going deeper with convolutions.” In Computer Vision and Pattern Recognition, 2015.
[18]
M. Goyal and J. Rajapakse, “Deep neural network ensemble by data augmentation and bagging for skin lesion classification.” arXiv: 1807.05496, 2018.
[19]
K. Li and E. Li, “Skin lesion analysis towards melanoma detection via end-to-end deep learning of convolutional neural networks.” arXiv: 1807.08332, 2018.
[20]
R. Hardie, R. Ali, M. Silva and T. Kebede, “Skin Lesion Segmentation and Classification for ISIC 2018 Using Traditional Classifiers with Hand-Crafted Features,” arXiv: 1807.07001, 2018.
[21]
C. Cortes and V. Vapnik, "Support-Vector Networks," Machine Learning, vol. 20, no. 3, p. 273–297, 1995.
[22]
S. Kitada and H. Iyatomi, “2018 Skin lesion classification with ensemble of squeeze-and-excitation networks and semi-supervised learning.” arXiv:1809.02568, 2018.
[23]
Y. Tokozume, Y. Ushiku and T. Harada, “Between-class learning for image classification.” In IEEE Conference on Computer Vision and Pattern Recognition, 2018.
[24]
A. Krizhevsky, “Learning multiple layers of features from tiny images.” Department of Computer Science, University of Toronto, 2009.
[25]
Y. Netzer, T. Wang, A. Coates, A. Bissacco, B. Wu and A. Y. Ng, “Reading digits in natural images with unsupervised feature learning” In Neural Information Processing Systems Workshop, 2011.
[26]
J. Deng, W. Dong, R. Socher, L. Li, K. Li and F. L, “Imagenet: A large-scale hierarchical image database,” In IEEE Conference on Computer Vision and Pattern Recognition, 2009.
[27]
S. Ioffe and C. Szegedy, “Batch normalization: Accelerating deep network training by reducing internal covariate shift.” In International Conference on Machine Learning, 2015.
[28]
V. Nair and G. Hinton. “Rectified linear units improve restricted boltzmann machines.” In International Conference on Machine Learning, 2010.
[29]
M. Lin, Q. Chen and S.Yan, “Network in network.” In International Conference on Learning Representations, 2014.
[30]
R. Kohavi, “A study of cross-validation and bootstrap for accuracy estimation and model selection.” In International Joint Conference on Artificial Intelligence, 1995.
[31]
G. King and L. Zeng, “Logistic regression in rare events data.” Political Analysis, 2001.
[32]
J. Wang and L. Perez, “The effectiveness of data augmentation in image classification using deep learning.” arXiv: 1712.04621, 2017.
[33]
F. Nachbar, W. Stolz, T. Merkle, et al. “The ABCD rule of dermatoscopy: high prospective value in the diagnosis of doubtful melanocytic skin lesions.”
Journal of the American Academy of Dermatology, 1994.
[34]
C. Bishop, “Pattern recognition and machine learning.” page 229, Springer, New York, 2006.
[35]
L. Bottou, "Large-scale machine learning with stochastic gradient descent", In International Conference on Computational Statistics, 2010.
[36]
D. Lee. “Pseudo-label: The simple and efficient semi-supervised learning method for deep neural networks.” In International Conference on Machine Learning workshop 2013.
[37]
OpenCV Website, [Onilne], [https://opencv.org]
[38]
Keras Website, [Online], [https://keras.io]
[39]
ISIC2018 Challenge Website, [Online], [ https://challenge2018.isic-archive.com]
[40]
Y. Lee, S. Jung and H. Won, “WonDerM: Skin lesion classification with fine-tuned neural networks.” arXiv: 1808.03426, 2018.
[41]
Y. Pan and Y. Xia, “Residual Network based Aggregation Model for Skin Lesion Classification.” arXiv: 1807.09150, 2018.
[42]
S. Li, W. Deng and J. Du, "Reliable crowdsourcing and deep locality-preserving learning for expression recognition in the wild." In Computer Vision and Pattern Recognition, 2017.