簡易檢索 / 詳目顯示

回結果列表
研究生： 余政翰
Yu, Zheng-Han
論文名稱： 利用卷積神經網路分類基底細胞癌應用於倍頻顯微影像
Convolutional Neural Network Classification of Basal Cell Carcinoma in Harmonically Generated Microscopy Images
指導教授： 李國君
Lee, Gwo-Giun (Chris)
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： 2016
畢業學年度： 104
語文別： 英文
論文頁數： 66
中文關鍵詞： 生物醫學影像 、光學虛擬活體組織切片 、二倍頻顯微技術 、三倍頻顯微技術 、基底細胞癌 、卷積神經網路 、影像分割 、特徵萃取 、Frangi filter 、賈伯濾波器 、大津演算法
外文關鍵詞： biomedical image, optical in vivo virtual biopsy, Second Harmonic Generation (SHG), Third Harmonic Generation (THG), Basal Cell Carcinoma (BCC), Convolutional Neural Network (CNN), image segmentation, feature extraction, Frangi filter, Gabor filter, Otsu’s method
相關次數： 點閱：132  下載：2 
分享至:
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一種皮膚惡性腫瘤，會造成局部神經或組織的損傷，由於生長緩慢不痛，若未能及早發現，會使腫瘤擴大而有切除之困難。本篇論文提出一個電腦輔助診斷的方法，透過賈伯濾波器依據受感染三倍頻影像中的樹枝狀黑色素細胞的特性萃取出尺度特徵，並提供給Frangi濾波器使其能夠自動化地選擇適合尺度範圍，且準確的分割出受感染的基底細胞。接著利用大量的正常和受感染的膠原蛋白纖維影像訓練卷積神經網路，並根據影像處理的經驗初始化卷積層，使其能準確且快速的區分影像中皮膚是否感染基底細胞癌。實驗結果顯示此演算法能準確的分類大量的醫學影像，節省大量的人力和時間的消耗，其在生物醫學影像分析上具有極高的發展潛力。

    Basal cell carcinoma (BCC) is the most common form of skin cancer, which can cause local damage of nerves or tissues. Since the tumor growth of BCC is slow and not painful, it would lead that the tumor detection is too late to remove the expansion of tumor. This thesis proposes a method of computer-aided diagnosis, which use the Gabor filter to extract characteristic scale information according to the characteristic of infected dendritic melanocytes in the third harmonic generation image. Scale information of image which is extracted by Gabor filter provide for Frangi filter so that it can automatically adjust scale range and more accurate segment the infected basal cells in medical image. And then, we use large number of normal and infected collagen fibers images to train convolution neural network and initialize the kernels of convolution layer according to the experience of image processing, so that it can accurately and fast distinguish between normal and diseased skin in medical image. Experimental results show that this algorithm can accurately classify a large number of medical image, and reduce time-consuming and labor-consuming, which has potential development in biomedical image analysis.

    摘 要 i Abstract iii 誌 謝 v Table of Contents vii List of Tables xi List of Figures xiii Chapter 1 Introduction 1 1.1 Introduction 1 1.2 Background Information 2 1.2.1 Traditional Biopsy Methodology 2 1.2.2 Physical Background of the Acquired Images 2 1.2.3 Human Skin 4 1.2.4 Basal Cell Carcinoma 7 1.3 Motivation 8 1.4 Organization of this Thesis 8 Chapter 2 Surveys of Related Works in the Literatures 9 2.1 Feature Extraction 9 2.1.1 Fourier Transform 9 2.1.2 Wavelet Transform 11 2.1.3 Gabor Filter 13 2.1.4 Frangi Filter 18 2.2 Classification 20 2.2.1 K-means Clustering 20 2.2.2 Neural Networks 22 2.2.3 Auto-encoder 23 2.2.4 Convolutional Neural Network (CNN) 24 2.2.5 Convolutional Auto-encoder (CAE) 26 2.3 Image Segmentation 26 2.3.1 Image Thresholding 27 2.3.2 Otsu’s Method 27 2.3.3 Region Growing 28 Chapter 3 Proposed Algorithms 29 3.1 Basal Cell Carcinoma Segmentation and Classification 29 3.2 Dendritic Melanocytes Segmentation 29 3.2.1 Scale Detection of Dendritic Melanocytes 31 3.2.2 Dendritic Melanocytes Enhancement 35 3.2.2.1 Scale-space Representation With Gaussian kernel 35 3.2.2.2 Structure Analysis 37 3.2.2.3 Vessel Structures Enhancement 40 3.2.3 Refined Region of Dendritic Melanocytes 42 3.3 Basal Cell Carcinoma Classification 44 3.3.1 Handcrafted Kernel Initialization with Gabor Filter of Data Representation 45 3.3.2 Classifier of Convolutional Neural Network 48 3.3.3 Optimization of Convolutional Neural Network 48 Chapter 4 Experimental Results 50 4.1 Dendritic Melanocytes Segmentation 50 4.2 Basal Cell Carcinoma Classification 55 4.3 Comparison with Previous Works 59 Chapter 5 Conclusion and Future Works 60 5.1 Conclusions 60 5.2 Future Works 61 Acknowledgments 62 References 63

    [1] C.-K. Sun, "Higher Harmonic Generation Microscopy," in Microscopy Techniques: -/-, J. Rietdorf, Ed., ed Berlin, Heidelberg: Springer Berlin Heidelberg, 2005, pp. 17-56.
    [2] S.-Y. Chen, S.-U. Chen, H.-Y. Wu, W.-J. Lee, Y.-H. Liao, and C.-K. Sun, "In vivo virtual biopsy of human skin by using noninvasive higher harmonic generation microscopy," Selected Topics in Quantum Electronics, IEEE Journal of, vol. 16, pp. 478-492, 2010.
    [3] M.-R. Tsai, C.-H. Chen, and C.-K. Sun, "Third and second harmonic generation imaging of human articular cartilage," Proceeding of SPIE, San Iose, CA, vol. 7183, pp. 71831V-1, 2009.
    [4] C.-K. Sun, S.-W. Chu, S.-Y. Chen, T.-H. Tsai, T.-M. Liu, C.-Y. Lin, et al., "Higher harmonic generation microscopy for developmental biology," Journal of Structural Biology, vol. 147, pp. 19-30, 7// 2004.
    [5] J. T. Lear and A. G. Smith, "Basal cell carcinoma," Postgraduate Medical Journal, vol. 73, pp. 538-542, 1997.
    [6] M.-R. Tsai, Y.-H. Cheng, J.-S. Chen, Y.-S. Sheen, Y.-H. Liao, and C.-K. Sun, "Differential diagnosis of nonmelanoma pigmented skin lesions based on harmonic generation microscopy," Journal of Biomedical Optics, vol. 19, pp. 036001-036001, 2014.
    [7] T. Sikora, "The MPEG-7 visual standard for content description-an overview," Circuits and Systems for Video Technology, IEEE Transactions on, vol. 11, pp. 696-702, 2001.
    [8] A. V. Oppenheim, A. S. Willsky, and S. H. Nawab, Signals and systems: Prentice Hall, 1997.
    [9] Graps, Amara. "An introduction to wavelets." IEEE computational science and engineering 2.2 (1995): 50-61.
    [10] E. Sejdić, I. Djurović, and J. Jiang, "Time–frequency feature representation using energy concentration: An overview of recent advances," Digital Signal Processing, vol. 19, pp. 153-183, 2009/01/01 2009.
    [11] S. G. Mallat, “A theory for multiresolution signal decomposition: The wavelet representation,” IEEE Trans. Pattern Anal. and Machine Intell., vol. 11, no. 7, pp. 674 - 693, 1989.
    [12] D. Gabor, "Theory of communication," Journal of the Institution of Electrical Engineers - Part III: Radio and Communication Engineering, vol. 93, pp. 429-457, 1946.
    [13] Q. Li, J. You, L. Zhang, and P. Bhattacharya, "A multiscale approach to retinal vessel segmentation using Gabor filters and scale multiplication," Systems, Man and Cybernetics, pp. 3521-3527, 2006.
    [14] J. V. Soares, J. J. Leandro, R. M. Cesar, H. F. Jelinek, and M. J. Cree, "Retinal vessel segmentation using the 2-D Gabor wavelet and supervised classification," Medical Imaging, IEEE Transactions, vol. 25, pp. 1214-1222, 2006.
    [15] J. G. Daugman, "Uncertainty relation for resolution in space, spatial frequency, and orientation optimized by two-dimensional visual cortical filters," JOSA A, vol. 2, pp. 1160-1169, 1985.
    [16] A. F. Frangi, W. J. Niessen, K. L. Vincken, and M. A. Viergever, "Multiscale vessel enhancement filtering," Medical Image Computing and Computer-Assisted Interventation—MICCAI’98, ed: Springer, pp. 130-137, 1998.
    [17] S. You, E. Bas, D. Erdogmus, and J. Kalpathy-Cramer, "Principal Curved Based Retinal Vessel Segmentation towards Diagnosis of Retinal Diseases," Healthcare Informatics, Imaging and Systems Biology (HISB), 2011 First IEEE International Conference, pp. 331-337, 2011.
    [18] T. Lindeberg, Scale-space theory in computer vision: Springer, 1993.
    [19] Strang, Gilbert. "Introduction to linear algebra." (2011).
    [20] J. A. Hartigan and M. A. Wong, "Algorithm AS 136: A k-means clustering algorithm," Applied statistics, pp. 100-108, 1979.
    [21] T. Kohonen, "An introduction to neural computing," Neural networks, vol. 1, pp. 3-16, 1988.
    [22] Bengio, Yoshua. "Learning deep architectures for AI." Foundations and trends® in Machine Learning 2.1 (2009): 1-127.
    [23] Lecun, Y. (1989). Generalization and network design strategies. In R. Pfeifer, Z. Schreter, F. Fogelman, & L. Steels (Eds.), Connectionism in perspective. Zurich, Switzerland: Elsevier.
    [24] Y. Lecun, L. Bottou, Y. Bengio, and P. Haffner, "Gradient-based learning applied to document recognition," Proceedings of the IEEE, vol. 86, pp. 2278-2324, 1998.
    [25] G. Hinton, S. Osindero, et al., "A Fast Learning Algorithm for Deep Belief Nets," Neural Computation, vol. 18, pp. 1527-1554, 2006.
    [26] Krizhevsky, Alex, Ilya Sutskever, and Geoffrey E. Hinton. "Imagenet classification with deep convolutional neural networks." Advances in neural information processing systems. 2012.
    [27] Szegedy, Christian, et al. "Going deeper with convolutions." Proceedings of the IEEE Conference on Computer Vision and Pattern Recognition. 2015.
    [28] J. Masci, U. Meier, D. Cireşan, and J. Schmidhuber, "Stacked convolutional auto-encoders for hierarchical feature extraction," presented at the Proceedings of the 21th international conference on Artificial neural networks - Volume Part I, Espoo, Finland, 2011.
    [29] R.C. Gonzalez and R.E. Woods, Digital Image Processing: Prentice-Hall, Englewood Cliffs, NJ, 2002.
    [30] N. Otsu, "A threshold selection method from gray-level histograms," Automatica, vol. 11, pp. 23-27, 1975.
    [31] R. Adams and L. Bischof, "Seeded region growing," Pattern Analysis and Machine Intelligence, IEEE Transactions, vol. 16, pp. 641-647, 1994.
    [32] C. Cheng-Syun, "Analysisof Collagen Fiber Features in Medical Images," Master of Science, Department of Electrical Engineering, National Cheng Kung Unversity, 2015.
    [33] Gwo Giun (Chris) Lee, Cheng-Syun Cai, Yi-Hua Liao, Wei-Hung Weng, Chi-Kuang Sun, Ming-Rung Tsai, Shi-Yu Hung, Chun-Hsi Huang, Han-Ting Shih, Zheng-Han Yu, "Quantitative Gabor Feature Analysis of Collagen Fibers in Harmonically Generated Microscopy (HGM) Imaging," OMICS International Global Submit and Expo on Multimedia and Applications ETMN Pre-conference Workshop 2015, Birmingham, Aug. 2015.
    [34] Javier R. Movellan: “Tutorial on Gabor Filters,” Tutorial paper [Online] http://mplab.ucsd.edu/tutorials/pdfs/gabor.pdf.
    [35] Glorot, Xavier, Antoine Bordes, and Yoshua Bengio. "Deep Sparse Rectifier Neural Networks." Aistats. Vol. 15. No. 106. 2011.
    [36] Bottou, Léon. "Stochastic gradient descent tricks." Neural Networks: Tricks of the Trade. Springer Berlin Heidelberg, 2012. 421-436.
    [37] Bishop, Christopher M. "Pattern recognition." Machine Learning 128 (2006).
    [38] Y. Jia. Caffe | Deep Learning Framework. Available: http://caffe.berkeleyvision.org/
    [39] K. Lesack and C. Naugler, "Performance of a simple chromatin-rich segmentation algorithm in quantifying basal cell carcinoma from histology images," BMC Research Notes, vol. 5, pp. 1-9, 2012.
    [40] I. Kopriva, A. Peršin, N. Puizina-Ivić, and L. Mirić, "Robust demarcation of basal cell carcinoma by dependent component analysis-based segmentation of multi-spectral fluorescence images," Journal of Photochemistry and Photobiology B: Biology, vol. 100, pp. 10-18, 7/2/ 2010.
    [41] J. Arevalo, A. Cruz-Roa, V. Arias, E. Romero, and F. A. González, "An unsupervised feature learning framework for basal cell carcinoma image analysis," Artificial Intelligence in Medicine, vol. 64, pp. 131-145, 6// 2015.
    [42] Glorot, Xavier, and Yoshua Bengio. "Understanding the difficulty of training deep feedforward neural networks." Aistats. Vol. 9. 2010.

    下載圖示
    2026-01-01公開
    QR CODE