成功大學博碩士論文系統

簡易檢索 / 詳目顯示

回結果列表

研究生：	黃欽偉 Huang, Chin-Wei
論文名稱：	利用卷積神經網路偵測基底細胞癌應用於皮膚鏡影像 Basal Cell Carcinoma Detection in Dermoscopy Images via Convolutional Neural Network
指導教授：	李國君 Lee, Gwo Giun
學位類別：	碩士 Master
系所名稱：	電機資訊學院 - 電機工程學系 Department of Electrical Engineering
論文出版年：	2019
畢業學年度：	107
語文別：	英文
論文頁數：	163
中文關鍵詞：	皮膚鏡影像、基底細胞癌、自動白平衡、對比度限制自適應直方圖均衡、卷積神經網路、賈伯濾波器、特徵金字塔、特徵視覺化
外文關鍵詞：	Dermoscopy Image, Basal Cell Carcinoma (BCC), Automatic White Balance, Contrast Limited Adaptive Histogram Equalization (CLAHE), Convolutional Neural Network (CNN), Gabor Filter, Pyramidal Feature Hierarchy, Feature Visualizatio
相關次數：	點閱：98 下載：0
分享至:	分享至facebook 分享至twitter

查詢本校圖書館目錄查詢臺灣博碩士論文知識加值系統勘誤回報

基底細胞癌為最常見的皮膚癌，約80%的皮膚癌患者都是罹患基底細胞癌。基底細胞癌的早期偵測十分重要，早期對基底細胞癌進行治療，除可以節省醫療資源，還能降低癌細胞轉移的風險。在臨床上，醫生對皮膚疾病診斷的準確率約65.8%，透過皮膚鏡的幫助，診斷的準確率可以提升到76.2%。本文提出了一種應用於皮膚鏡影像的基底細胞癌輔助診斷系統。我們基於臨床診斷的方法設計了一個卷積神經網路對痣和基底細胞癌進行分類，該模型使用了約五十萬的參數，遠小於常見的卷積神經網路VGG16(約一億三千四百萬的參數)與 ResNet34(約兩千一百萬的參數)，因此可以使用更少的資源進行訓練與測試。在此論文中，我們討論了皮膚鏡影像前處理對卷積神經網路的影響，包含了使用自動白平衡對影像進行顏色校正與使用對比度限制自適應直方圖均衡對影像進行對比度增強。我們比較卷積神經網路結合賈柏濾波器或特徵金字塔和原始模型對痣與基底細胞癌在皮膚鏡上分類的差異。結果顯示，使用賈柏濾波器可以使得卷積神經網路在訓練時收斂得更快速，且能解決資料不足的問題。我們使用HAM10000資料庫與花蓮慈濟提供的皮膚鏡影像進行實驗，我們所設計的卷積神經網路在HAM10000資料庫上對痣和基底細胞癌的分類達到了94.65%的準確率、93.72%的靈敏度、95.58%的特異度；在花蓮慈濟提供的皮膚鏡影像對痣和基底細胞癌的分類達到了92.41%的準確率、91.33%的靈敏度、93.50%的特異度。最後，我們將卷積神經網路從影像中所學習到的特徵視覺化出來，藉此觀察卷積神經網路在痣和基底細胞癌分類的任務中，在高加索人與黃種人所使用特徵上的差異，並觀察到卷積神經網路從不同的人種的影像中，會學習使用不同的顏色特徵，並且在黃種人的影像中會使用較多的顏色特徵。

Basal Cell Carcinoma (BCC) is the most common form of the skin cancer. Earlier detection is needed to reduce the medical resources for treatment and the risk of the occurrence of metastases. The Dermoscopy can enhance the accuracy of clinical diagnosis for all skin lesion from 65.8% to 76.2% compared to that of naked eyes. This thesis proposed a computer-aided diagnosis system for BCC detection in the Dermoscopy images. Based on the clinically diagnosed method, we design a lightweight Convolutional Neural Network (CNN) (~0.5M parameters), which is much smaller than the common CNN such as VGG16 (~134.3M parameters) and ResNet34 (~21.3M parameters), to classify BCC and nevus. Thus, the lightweight CNN can use fewer resources for training and testing. We discuss the influence of the image preprocessing, such as automatic white balance and contrast limited adaptive histogram equalization, to the designed CNN for classification. We also discuss the influence of combining the Gabor filters or the pyramidal feature hierarchy with the designed CNN for classification. The result shows that using Gabor filters can not only make CNN converge quickly but also solve the problem of data insufficient. We use the HAM10000 dataset and the Hualien Tzu Chi dataset for experiments and observe the difference between the BCC in Caucasian and Asian. The lightweight CNN can achieve the accuracy of 94.65% with the sensitivity of 93.72% and the specificity of 95.58% in the HAM10000 dataset, and the accuracy of 92.41% with the sensitivity of 91.33% and the specificity of 93.50% in the Hualien Tzu Chi dataset. We visualize the features in the lightweight CNN to analyze the difference of the nevus and BCC in Caucasian and Asian and find that the CNNs focus on different color information when using different race images for training. The CNN trained with Asian images learns more color features than the one trained with Caucasian images.

摘 要	i
Abstract	iii
誌 謝	v
Table of Contents	vii
List of Tables	xii
List of Figures	xv
Chapter 1	Introduction	1
1	Introduction	1
2	Organization of this Thesis	2
3	Background Information	2
3.1	Human Skin	2
3.2	Basal Cell Carcinoma	5
3.3	Dermoscopy	8
4	Motivation	11
Chapter 2	Surveys of Related Works in the Literatures	12
1	Image Processing	13
1.1	Color Correction	14
1.1.1	Automatic White Balance	14
1.2	Contrast Enhancement	17
1.2.1	Histogram Equalization	17
1.2.2	Contrast Limited Adaptive Histogram Equalization	19
2	Image Segmentation	21
2.1	Thresholding Approach	21
2.1.1	Otsu’s Method	22
2.2	Edge Based Approach	24
2.2.1	First-order Edge Detection	24
2.2.2	Prewitt Operator	26
2.2.3	Sobel Operator	26
2.2.4	Laplacian Operator	27
3	Feature Extraction	28
3.1	Fourier Transform	28
3.2	Gabor Filter	30
4	Classification	32
4.1	K-means Clustering	32
4.2	Artificial Neural Network	34
5	Learning Technique	39
5.1	Optimizer	39
5.1.1	Stochastic Gradient Descent	39
5.1.2	Momentum	40
5.1.3	AdaGrad	41
5.1.4	Adam	42
5.2	Convolutional Neural Network (CNN)	43
5.2.1	VGGNet	44
5.2.2	ResNet	45
5.3	Dropout	48
5.4	Feature Visualization	49
5.4.1	Deconvolutional Method	49
5.4.2	Optimization Method	50
6	Dermoscopy Data	52
6.1	PH2 Database	52
6.2	HAM10000 Dataset	53
Chapter 3	Proposed Algorithms	55
1	Data Augmentation	55
2	Image Preprocessing	56
3	CNN Structure	59
3.1	Pooling Method	62
3.2	Gabor Filter Design	63
3.3	Pyramidal Feature Hierarchy	70
Chapter 4	Experiment	72
1	Experimental Data	72
1.1	HAM10000 Data Subset Used to Train CNN Design	72
1.2	Hualian Tzu Chi Hospital Data Subset Used to Train CNN Design	74
2	Experimental Environment	75
3	Experiment	76
3.1	Model Comparison	76
3.1.1	Experimental Design	76
3.1.2	Experimental Result	77
3.1.3	Discussion	78
3.2	Learning Rate Adjustment	80
3.2.1	Experimental Design	80
3.2.2	Experimental Result	81
3.3	Pooling Method Chosen	86
3.3.1	Experimental Design	86
3.3.2	Experimental Result	88
3.3.3	Discussion	89
3.4	Hidden Layer	90
3.4.1	Experimental Design	90
3.4.2	Experimental Result	91
3.4.3	Discussion	92
3.5	Data Imbalance	93
3.5.1	Experimental Design	93
3.5.2	Experimental Result	94
3.5.3	Discussion	96
3.6	Automatic White Balance	97
3.6.1	Experimental Design	97
3.6.2	Experimental Result	97
3.6.3	Discussion	99
3.7	Contrast Limited Adaptive Histogram Equalization	101
3.7.1	Experimental Design	101
3.7.2	Experimental Result	101
3.7.3	Discussion	103
3.8	Combine CNN model with Gabor Filter	105
3.8.1	Experimental Design	105
3.8.2	Experimental Result	106
3.8.3	Discussion	109
3.9	Pyramidal Feature Hierarchy	112
3.9.1	Experimental Design	112
3.9.2	Experimental Result	113
3.9.3	Discussion	114
3.10	Different Dataset	118
3.10.1	Experimental Design	118
3.10.2	Experimental Result	119
3.10.3	Discussion	122
3.11	Feature Visualization	125
3.11.1	Experimental Design	125
3.11.2	Observation	129
Chapter 5	Compare with Previous Work	147
Chapter 6	Conclusion and Future Works	152
1	Conclusions	152
2	Future Works	154
Acknowledgments	155
References	156
                                    

[1] E. Mclafferty, C. Hendry, and A. Farley, "The integumentary system: anatomy, physiology and function of skin," Nursing Standard (through 2013), vol. 27, no. 3, p. 35, 2012.
[2] M. Richardson, "Understanding the structure and function of the skin," Nursing times, vol. 99, no. 31, pp. 46-48, 2003.
[3] H. Yousef and S. Sharma, "Anatomy, Skin (Integument), Epidermis," StatPearls. Treasure Island (FL); StatPearls Publishing LLC.: St. Petersburg, FA, USA, 2018.
[4] G. J. Tortora and B. Derrickson, Principles of anatomy & physiology. John Wiley & Sons, Incorporated, 2017.
[5] Y.-Y. Chou, "Convolutional Neural Network Analytics of Melasma in Harmonically Generated Microscopy Images," Department of Electrical Engineering, National Chen Kung University, 2018.
[6] Y. ı. Tüzün, Z. Kutlubay, B. Engin, and S. Serdaroğlu, "Basal cell carcinoma," in Skin Cancer Overview: IntechOpen, 2011.
[7] (2016). Key Statistics for Basal and Squamous Cell Skin Cancers [Online]. Available: https://www.cancer.org/cancer/basal-and-squamous-cell-skin-cancer/about/key-statistics.html#written_by.
[8] S. A. Gandhi and J. Kampp, "Skin cancer epidemiology, detection, and management," Medical Clinics, vol. 99, no. 6, pp. 1323-1335, 2015.
[9] (2018). 105年癌症登記年報 [Online]. Available: https://www.hpa.gov.tw/Pages/Detail.aspx?nodeid=269&pid=10227.
[10] P. A. Wu and J. K. Robinson, "Epidemiology, pathogenesis, and clinical features of basal cell carcinoma," UpToDate. Waltham, MA: UpToDate Inc. https://www. uptodate. com. Accesed on October, vol. 21, 2018.
[11] C. Vornicescu, C. S. Melincovici, O. Soriţău, S. C. Şenilă, and C. M. Mihu, "Basal cell carcinoma: review of etiopathogenesis, diagnosis and management," Human & Veterinary Medicine, vol. 10, no. 1, 2018.
[12] M. Mackiewicz-Wysocka, M. Bowszyc-Dmochowska, D. Strzelecka-Węklar, A. Dańczak-Pazdrowska, and Z. Adamski, "Basal cell carcinoma–diagnosis," Contemporary Oncology, vol. 17, no. 4, p. 337, 2013.
[13] L. M. Stanoszek, G. Y. Wang, and P. W. Harms, "Histologic mimics of basal cell carcinoma," Archives of pathology & laboratory medicine, vol. 141, no. 11, pp. 1490-1502, 2017.
[14] A. Marghoob and R. Braun, An atlas of dermoscopy. CRC Press, 2012.
[15] S. W. Menzies, K. Westerhoff, H. Rabinovitz, A. W. Kopf, W. H. McCarthy, and B. Katz, "Surface microscopy of pigmented basal cell carcinoma," Archives of dermatology, vol. 136, no. 8, pp. 1012-1016, 2000.
[16] M. Ulrich et al., "The sensitivity and specificity of optical coherence tomography for the assisted diagnosis of nonpigmented basal cell carcinoma: an observational study," British Journal of Dermatology, vol. 173, no. 2, pp. 428-435, 2015.
[17] A. A. Marghoob, R. P. Usatine, and N. Jaimes, "Dermoscopy for the family physician," American family physician, vol. 88, no. 7, 2013.
[18] C. Benvenuto-Andrade et al., "Differences between polarized light dermoscopy and immersion contact dermoscopy for the evaluation of skin lesions," Archives of dermatology, vol. 143, no. 3, pp. 329-338, 2007.
[19] S. N. Snow et al., "Metastatic basal cell carcinoma. Report of five cases," Cancer, vol. 73, no. 2, pp. 328-335, 1994.
[20] R. B. Oliveira, J. P. Papa, A. S. Pereira, and J. M. R. Tavares, "Computational methods for pigmented skin lesion classification in images: review and future trends," Neural Computing and Applications, vol. 29, no. 3, pp. 613-636, 2018.
[21] J. Glaister, R. Amelard, A. Wong, and D. A. Clausi, "MSIM: Multistage illumination modeling of dermatological photographs for illumination-corrected skin lesion analysis," IEEE Transactions on Biomedical Engineering, vol. 60, no. 7, pp. 1873-1883, 2013.
[22] Z. Liu and J. Zerubia, "Skin image illumination modeling and chromophore identification for melanoma diagnosis," Physics in Medicine & Biology, vol. 60, no. 9, p. 3415, 2015.
[23] J. Quintana, R. Garcia, and L. Neumann, "A novel method for color correction in epiluminescence microscopy," Computerized Medical Imaging and Graphics, vol. 35, no. 7-8, pp. 646-652, 2011.
[24] Q. Abbas, I. F. Garcia, M. Emre Celebi, W. Ahmad, and Q. Mushtaq, "A perceptually oriented method for contrast enhancement and segmentation of dermoscopy images," Skin Research and Technology, vol. 19, no. 1, pp. e490-e497, 2013.
[25] G. Schaefer, M. I. Rajab, M. E. Celebi, and H. Iyatomi, "Colour and contrast enhancement for improved skin lesion segmentation," Computerized Medical Imaging and Graphics, vol. 35, no. 2, pp. 99-104, 2011.
[26] Q. Abbas, I. Fondón, and M. Rashid, "Unsupervised skin lesions border detection via two-dimensional image analysis," Computer methods and programs in biomedicine, vol. 104, no. 3, pp. e1-e15, 2011.
[27] K. Kiani and A. R. Sharafat, "E-shaver: An improved DullRazor® for digitally removing dark and light-colored hairs in dermoscopic images," Computers in biology and medicine, vol. 41, no. 3, pp. 139-145, 2011.
[28] R. Garnavi, M. Aldeen, M. E. Celebi, A. Bhuiyan, C. Dolianitis, and G. Varigos, "Automatic segmentation of dermoscopy images using histogram thresholding on optimal color channels," International Journal of Medicine and Medical Sciences, vol. 1, no. 2, pp. 126-134, 2010.
[29] M. Sadeghi, M. Razmara, T. K. Lee, and M. S. Atkins, "A novel method for detection of pigment network in dermoscopic images using graphs," Computerized Medical Imaging and Graphics, vol. 35, no. 2, pp. 137-143, 2011.
[30] M. Emre Celebi et al., "Border detection in dermoscopy images using statistical region merging," Skin Research and Technology, vol. 14, no. 3, pp. 347-353, 2008.
[31] Q. Abbas, I. F. Garcia, M. E. Celebi, W. Ahmad, and Q. Mushtaq, "Unified approach for lesion border detection based on mixture modeling and local entropy thresholding," Skin Research and Technology, vol. 19, no. 3, pp. 314-319, 2013.
[32] M. E. Celebi, H. A. Kingravi, Y. A. Aslandogan, and W. V. Stoecker, "Detection of blue-white veil areas in dermoscopy images using machine learning techniques," in Medical Imaging 2006: Image Processing, 2006, vol. 6144: International Society for Optics and Photonics, p. 61445T.
[33] G. Di Leo, G. Fabbrocini, A. Paolillo, O. Rescigno, and P. Sommella, "Towards an automatic diagnosis system for skin lesions: estimation of blue-whitish veil and regression structures," in 2009 6th International Multi-Conference on Systems, Signals and Devices, 2009: IEEE, pp. 1-6.
[34] G. S. Vennila, L. P. Suresh, and K. Shunmuganathan, "Dermoscopic image segmentation and classification using machine learning algorithms," in 2012 International Conference on Computing, Electronics and Electrical Technologies (ICCEET), 2012: IEEE, pp. 1122-1127.
[35] A. Pennisi, D. D. Bloisi, D. Nardi, A. R. Giampetruzzi, C. Mondino, and A. Facchiano, "Skin lesion image segmentation using Delaunay Triangulation for melanoma detection," Computerized Medical Imaging and Graphics, vol. 52, pp. 89-103, 2016.
[36] J. Qi, M. Le, C. Li, and P. Zhou, "Global and local information based deep network for skin lesion segmentation," arXiv preprint arXiv:1703.05467, 2017.
[37] R. H. Johr, "Dermoscopy: alternative melanocytic algorithms—the ABCD rule of dermatoscopy, menzies scoring method, and 7-point checklist," Clinics in dermatology, vol. 20, no. 3, pp. 240-247, 2002.
[38] T. Sikora, "The MPEG-7 visual standard for content description-an overview," IEEE Transactions on circuits and systems for video technology, vol. 11, no. 6, pp. 696-702, 2001.
[39] Y. Zhou, M. Smith, L. Smith, and R. Warr, "A new method describing border irregularity of pigmented lesions," Skin Research and Technology, vol. 16, no. 1, pp. 66-76, 2010.
[40] R. Suganya, "An automated computer aided diagnosis of skin lesions detection and classification for dermoscopy images," in 2016 International Conference on Recent Trends in Information Technology (ICRTIT), 2016: IEEE, pp. 1-5.
[41] M. Rastgoo, R. Garcia, O. Morel, and F. Marzani, "Automatic differentiation of melanoma from dysplastic nevi," Computerized Medical Imaging and Graphics, vol. 43, pp. 44-52, 2015.
[42] R. M. Haralick and K. Shanmugam, "Textural features for image classification," IEEE Transactions on systems, man, and cybernetics, no. 6, pp. 610-621, 1973.
[43] D. Nie, "Classification of melanoma and clark nevus skin lesions based on Medical Image Processing Techniques," in 2011 3rd International Conference on Computer Research and Development, 2011, vol. 3: IEEE, pp. 31-34.
[44] J. F. Alcón et al., "Automatic imaging system with decision support for inspection of pigmented skin lesions and melanoma diagnosis," IEEE journal of selected topics in signal processing, vol. 3, no. 1, pp. 14-25, 2009.
[45] N. Cheerla and D. Frazier, "Automatic melanoma detection using multi-stage neural networks," International Journal of Innovative Research in Science, Engineering and Technology, vol. 3, no. 2, pp. 9164-9183, 2014.
[46] D. Ruiz, V. Berenguer, A. Soriano, and B. SáNchez, "A decision support system for the diagnosis of melanoma: A comparative approach," Expert Systems with Applications, vol. 38, no. 12, pp. 15217-15223, 2011.
[47] L. R. Bareiro Paniagua, D. N. Leguizamón Correa, D. P. Pinto-Roa, J. L. Vázquez Noguera, S. Toledo, and A. Lizza, "Computerized Medical Diagnosis of Melanocytic Lesions based on the ABCD approach," CLEI Electronic Journal, vol. 19, no. 2, pp. 6-6, 2016.
[48] P. Kharazmi, H. Lui, Z. J. Wang, and T. K. Lee, "Automatic detection of basal cell carcinoma using vascular-extracted features from dermoscopy images," in 2016 IEEE Canadian Conference on Electrical and Computer Engineering (CCECE), 2016: IEEE, pp. 1-4.
[49] A. Esteva et al., "Dermatologist-level classification of skin cancer with deep neural networks," Nature, vol. 542, no. 7639, p. 115, 2017.
[50] C.-L. Wang, "Automatic White Balancing Algorithm with Detection of Potential White Color Areas," Department of Electrical Engineering, National Cheng Kung University, 2007.
[51] N. A. Ibraheem, M. M. Hasan, R. Z. Khan, and P. K. Mishra, "Understanding color models: a review," ARPN Journal of science and technology, vol. 2, no. 3, pp. 265-275, 2012.
[52] G. Buchsbaum, "A spatial processor model for object colour perception," Journal of the Franklin institute, vol. 310, no. 1, pp. 1-26, 1980.
[53] R. C. Gonzalez and R. E. Woods, Digital Image Processing. Prentice-Hall,Inc. Upper Saddle River,New Jersey, 2002.
[54] D. Sundararajan, "Image Enhancement in the Spatial Domain," in Digital Image Processing: Springer, 2017, pp. 23-64.
[55] S. M. Pizer et al., "Adaptive histogram equalization and its variations," Computer vision, graphics, and image processing, vol. 39, no. 3, pp. 355-368, 1987.
[56] K. Zuiderveld, "Contrast limited adaptive histogram equalization," in Graphics gems IV, 1994: Academic Press Professional, Inc., pp. 474-485.
[57] M. Sonka, V. Hlavac, and R. Boyle, Image processing, analysis, and machine vision. Cengage Learning, 2014.
[58] T. Lee, V. Ng, R. Gallagher, A. Coldman, and D. McLean, "Dullrazor®: A software approach to hair removal from images," Computers in biology and medicine, vol. 27, no. 6, pp. 533-543, 1997.
[59] E. Meskini, M. Helfroush, K. Kazemi, and M. Sepaskhah, "A New Algorithm for Skin Lesion Border Detection in Dermoscopy Images," Journal of biomedical physics & engineering, vol. 8, no. 1, p. 117, 2018.
[60] N. Otsu, "A threshold selection method from gray-level histograms," IEEE transactions on systems, man, and cybernetics, vol. 9, no. 1, pp. 62-66, 1979.
[61] J. M. Prewitt, "Object enhancement and extraction," Picture processing and Psychopictorics, vol. 10, no. 1, pp. 15-19, 1970.
[62] S. Bhardwaj and A. Mittal, "A survey on various edge detector techniques," Procedia Technology, vol. 4, pp. 220-226, 2012.
[63] A. V. Oppenheim, A. S. Willsky, and S. H. Nawab, Signals & Systems. Pearson College Div, 1996.
[64] I. Fogel and D. Sagi, "Gabor filters as texture discriminator," Biological cybernetics, vol. 61, no. 2, pp. 103-113, 1989.
[65] Q. Li, J. You, L. Zhang, and P. Bhattacharya, "A multiscale approach to retinal vessel segmentation using Gabor filters and scale multiplication," in 2006 IEEE International Conference on Systems, Man and Cybernetics, 2006, vol. 4: IEEE, pp. 3521-3527.
[66] J. G. Daugman, "Two-dimensional spectral analysis of cortical receptive field profiles," Vision research, vol. 20, no. 10, pp. 847-856, 1980.
[67] O. S. Al-Kadi, "A gabor filter texture analysis approach for histopathological brain tumor subtype discrimination," arXiv preprint arXiv:1704.05122, 2017.
[68] R. Sathya and A. Abraham, "Comparison of supervised and unsupervised learning algorithms for pattern classification," International Journal of Advanced Research in Artificial Intelligence, vol. 2, no. 2, pp. 34-38, 2013.
[69] L. Breiman, "Random forests," Machine learning, vol. 45, no. 1, pp. 5-32, 2001.
[70] C. Cortes and V. Vapnik, "Support-vector networks," Machine learning, vol. 20, no. 3, pp. 273-297, 1995.
[71] M. W. Gardner and S. Dorling, "Artificial neural networks (the multilayer perceptron)—a review of applications in the atmospheric sciences," Atmospheric environment, vol. 32, no. 14-15, pp. 2627-2636, 1998.
[72] J. A. Hartigan and M. A. Wong, "Algorithm AS 136: A k-means clustering algorithm," Journal of the Royal Statistical Society. Series C (Applied Statistics), vol. 28, no. 1, pp. 100-108, 1979.
[73] G. Hamerly and C. Elkan, "Alternatives to the k-means algorithm that find better clusterings," in Proceedings of the eleventh international conference on Information and knowledge management, 2002: ACM, pp. 600-607.
[74] L. Amayreh and M. Saka, "Failure load prediction of castellated beams using artificial neural networks," 2005.
[75] S. S. Haykin and K. Elektroingenieur, Neural networks and learning machines. Pearson education Upper Saddle River, 2009.
[76] E. W. Weisstein. (2002). Hyperbolic Tangent [Online]. Available: http://mathworld.wolfram.com/HyperbolicTangent.html.
[77] B. Xu, N. Wang, T. Chen, and M. Li, "Empirical evaluation of rectified activations in convolutional network," arXiv preprint arXiv:1505.00853, 2015.
[78] Y. LeCun, Y. Bengio, and G. Hinton, "Deep learning," nature, vol. 521, no. 7553, p. 436, 2015.
[79] H. Robbins and S. Monro, "A stochastic approximation method," The annals of mathematical statistics, pp. 400-407, 1951.
[80] N. Qian, "On the momentum term in gradient descent learning algorithms," Neural networks, vol. 12, no. 1, pp. 145-151, 1999.
[81] J. Duchi, E. Hazan, and Y. Singer, "Adaptive subgradient methods for online learning and stochastic optimization," Journal of Machine Learning Research, vol. 12, no. Jul, pp. 2121-2159, 2011.
[82] D. P. Kingma and J. Ba, "Adam: A method for stochastic optimization," arXiv preprint arXiv:1412.6980, 2014.
[83] Y. LeCun, L. Bottou, Y. Bengio, and P. Haffner, "Gradient-based learning applied to document recognition," Proceedings of the IEEE, vol. 86, no. 11, pp. 2278-2324, 1998.
[84] K. Simonyan and A. Zisserman, "Very deep convolutional networks for large-scale image recognition," arXiv preprint arXiv:1409.1556, 2014.
[85] 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, pp. 770-778.
[86] N. Srivastava, G. Hinton, A. Krizhevsky, I. Sutskever, and R. Salakhutdinov, "Dropout: a simple way to prevent neural networks from overfitting," The Journal of Machine Learning Research, vol. 15, no. 1, pp. 1929-1958, 2014.
[87] M. D. Zeiler and R. Fergus, "Visualizing and understanding convolutional networks," in European conference on computer vision, 2014: Springer, pp. 818-833.
[88] D. Erhan, Y. Bengio, A. Courville, and P. Vincent, "Visualizing higher-layer features of a deep network," University of Montreal, vol. 1341, no. 3, p. 1, 2009.
[89] C. Olah, A. Mordvintsev, and L. Schubert, "Feature visualization," Distill, vol. 2, no. 11, p. e7, 2017.
[90] T. Mendonça, P. M. Ferreira, J. S. Marques, A. R. Marcal, and J. Rozeira, "PH 2-A dermoscopic image database for research and benchmarking," in 2013 35th annual international conference of the IEEE engineering in medicine and biology society (EMBC), 2013: IEEE, pp. 5437-5440.
[91] Z. Ma and J. M. R. Tavares, "A novel approach to segment skin lesions in dermoscopic images based on a deformable model," IEEE journal of biomedical and health informatics, vol. 20, no. 2, pp. 615-623, 2015.
[92] Y. Yuan, M. Chao, and Y.-C. Lo, "Automatic skin lesion segmentation using deep fully convolutional networks with jaccard distance," IEEE transactions on medical imaging, vol. 36, no. 9, pp. 1876-1886, 2017.
[93] 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, vol. 5, p. 180161, 2018.
[94] G. E. Batista, R. C. Prati, and M. C. Monard, "A study of the behavior of several methods for balancing machine learning training data," ACM SIGKDD explorations newsletter, vol. 6, no. 1, pp. 20-29, 2004.
[95] J. Jin, A. Dundar, and E. Culurciello, "Robust convolutional neural networks under adversarial noise," arXiv preprint arXiv:1511.06306, 2015.
[96] P. Ly, D. Bein, and A. Verma, "New Compact Deep Learning Model for Skin Cancer Recognition," in 2018 9th IEEE Annual Ubiquitous Computing, Electronics & Mobile Communication Conference (UEMCON), 2018: IEEE, pp. 255-261.
[97] S. Ioffe and C. Szegedy, "Batch normalization: Accelerating deep network training by reducing internal covariate shift," arXiv preprint arXiv:1502.03167, 2015.
[98] M. Lin, Q. Chen, and S. Yan, "Network in network," arXiv preprint arXiv:1312.4400, 2013.
[99] J. R. Movellan. (2002). Tutorial on Gabor filters.
[100] E. W. Weisstein. Fourier Transform--Gaussian [Online]. Available: http://mathworld.wolfram.com/FourierTransformGaussian.html.
[101] T.-Y. Lin, P. Dollár, R. Girshick, K. He, B. Hariharan, and S. Belongie, "Feature pyramid networks for object detection," in Proceedings of the IEEE Conference on Computer Vision and Pattern Recognition, 2017, pp. 2117-2125.
[102] N. Heller, E. Bussman, A. Shah, J. Dean, and N. Papanikolopoulos, "Computer Aided Diagnosis of Skin Lesions from Morphological Features," 2018.
[103] J. Deng, W. Dong, R. Socher, L.-J. Li, K. Li, and L. Fei-Fei, "Imagenet: A large-scale hierarchical image database," in 2009 IEEE conference on computer vision and pattern recognition, 2009: Ieee, pp. 248-255.
[104] A. Rezvantalab, H. Safigholi, and S. Karimijeshni, "Dermatologist Level Dermoscopy Skin Cancer Classification Using Different Deep Learning Convolutional Neural Networks Algorithms," arXiv preprint arXiv:1810.10348, 2018.
[105] D. Altamura et al., "Dermatoscopy of basal cell carcinoma: morphologic variability of global and local features and accuracy of diagnosis," Journal of the American Academy of Dermatology, vol. 62, no. 1, pp. 67-75, 2010.
[106] W. Tilgen, "Melanocyte carcinogenesis: facts and fancies," in Skin Carcinogenesis in Man and in Experimental Models: Springer, 1993, pp. 59-67.
[107] X. Li, J. Wu, H. Jiang, E. Z. Chen, X. Dong, and R. Rong, "Skin Lesion Classification Via Combining Deep Learning Features and Clinical Criteria Representations," bioRxiv, p. 382010, 2018.
[108] G. Huang, Z. Liu, L. Van Der Maaten, and K. Q. Weinberger, "Densely connected convolutional networks," in Proceedings of the IEEE conference on computer vision and pattern recognition, 2017, pp. 4700-4708.

校內：2025-02-24公開
校外：2025-02-24公開

簡易檢索 / 詳目顯示

相關論文