臺灣博碩士論文加值系統

免疫風濕科在檢查自身免疫疾病的主要依據是抗核抗體（ANA），而人類上皮細胞癌（Human Epithelioma Type 2, HEp-2）是最常被用來識別抗核抗體的細胞，因為如果給予超過一百種不同的自身抗體（Autoantibody），觀察HEp-2細胞即可辨別出超過三十種的細胞核及細胞質樣式，所以醫師在診斷疾病時，會藉由觀察HEp-2細胞，來預測病人的疾病。目前辨別樣式是仰賴專家觀察螢光顯微鏡下的載玻片來完成，此人工方式需要具有高度專業之技術人員來操作且耗時。
目前研究自動化分類ANA影像流程的影像處理方法及資料探勘技術眾多，本研究從眾多方法中找出分類結果正確率較高，進而協助醫師診斷疾病之方法。評估重點在邊緣檢測、特徵選擇及分類方法。流程開始會先載入ANA影像，將其轉為灰階，利用邊緣檢測方法定位出細胞位置，再利用不同的特徵選擇機制篩選重要特徵，最後以分類法預測影像類別。
實驗結果顯示使用Canny邊緣檢測，經紋理分析得到特徵，由支援向量機（SVM）進行特徵選擇，最後結合SVM分類方法具有最高的正確率（97.00%）。因此，根據實驗結果，我們建議實務上操作可以此組合方法來辨識ANA，輔助醫師診斷疾病。

The expert of immunology and rheumatology department inspects autoimmunedisease by recognizing antinuclear autoantibodies(ANA) patterns. HEp-2 cells are used for identification of ANA. This technique can recognize over thirty different nuclear and cytoplasmic patterns, which are given by upwards of 100 different autoantibodies. Therefore, physician diagnoses patients’ disease by inspecting HEp-2 cells. So far, identification of ANA is completed by inspecting the slides with the help of a fluorescent microscope. This manual procedure requires highly specialized technicians and consuming time.
There are many image processing and data mining methods for classifying ANA images automatically. This research attempts to find the cascaded method having highest accuracy from different image processing methods. These methods include edge detection, feature selection, and classification. Initially, we acquire ANA images and transfer them to be gray-level images. Edge detection methods are then used to locate cells. The next step is to find important features. Finally, we use classification methods to predict images’ classes.
The result shows that the optimal cascaded method is the combination of Canny (edge detection method), support vector machine (feature selection method), and support vector machine (classification method). The accuracy rate is about 97.00%. Therefore, we suggest that physician can identify ANA by using this cascaded method to diagnose disease in practice.

第一章　緒論 1
第一節 研究背景 1
第二節 研究動機與目的 2
第三節 研究架構 4
第二章　文獻探討 6
第一節 數位影像處理 6
第二節 特徵選擇 13
第三節 分類法 15
第四節 ANA螢光顯影處理 20
第三章　研究方法 22
第一節 研究流程 22
第二節 數位影像處理 23
第三節 特徵選擇 29
第四節 分類 31
第五節 評估 35
第四章　實驗結果與分析 38
第一節 研究資料來源 38
第二節 實驗流程與參數設定 38
第三節 實驗結果與分析 43
第五章　研究結論與未來研究方向 49
第一節 結論與貢獻 49
第二節 未來研究方向 50
參考文獻 51
附錄一　特徵選擇 55
附錄二　實驗結果 59
附錄三　中英文名詞對照 67

一、 中文文獻
[1] 丁一賢，陳牧言，2003，資料探勘，台中：滄海書局。
[2] 吳成柯、戴善榮、程湘君、雲立實譯，Rafael C. Gonzalez, Richard E. Woods著，2001，數位影像處理，台北：儒林圖書有限公司。
[3] 林群雄、吳建樺，2006，使用多類支持向量機混合三角偵測做人臉辨識，電子商務與數位生活研討會，台北大學。
[4] 曹又仁，2005，結合小波轉換與紋&;#63972;特徵之彩色影像檢&;#63850;，國立中山大學機械與機電工程研究所碩士論文。
[5] 曾憲雄、蔡秀滿、蘇東興、曾秋蓉、王慶堯，2005，資料探勘，台北：旗標出版股份有限公司。
[6] 單維彰，2000，&;#63829;波初步，台&;#63843;：全華科技圖書有限公司。
[7] 黃嘉政，2007，應用資料探勘技術於抗核抗體螢光顯影分析，國立嘉義大學資訊管理研究所碩士論文。
[8] 繆紹綱譯，Rafael C. Gonzalez, Richard E. Woods, and Steven L. Eddins著，2005，數位影像處理－運用MATLAB，台北：東華書局。
二、 英文文獻
[1] Almuallim, H. and Dietterich., T.G., “Learning Boolean Concepts in the Presence of Many Irrelevent Features,” Aritificial Intellgence(1) 1994, pp. 279-305.
[2] Ben-Bassat, M., “Pattern recognition and reduction of dimensionality. In Krishnaiah, P.R. and Kanal, L.N., editors, Handbook of statistics-II,” North Holland, 1982.
[3] Blum, A. and Langley, P., “Selection of Relevant Features And Examples In Machine Learning,” Artificial Intelligence(97) 1997, pp. 245-271.
[4] Boland, M.V., Markey, M.K., and Murphy, R.F., “Automated Recognition of Patterns Characteristic of Subcellular Structures in Fluorescence Microscopy Images,” Cytometry (33) 1998, pp. 366-375.
[5] Canny, J., “A Computational Approach To Edge Detection,” IEEE Transactions on Pattern Analysis and Machine Intelligence(8) 1986, pp.679-698.
[6] Chen, E.L., Chung P.C., Chen, C.L., Tsai, H.M., and Chang, C.I., “An Automatic Diagnostic System for CT Liver Image Classification,” IEEE Transactions on Biomedical Engineering (45) 1998, pp. 783-794.
[7] Castellano, G., Bonilha, L., Li, L.M., and Cendes, F., “Texture Analysis of Medical Images,” Clinical Radiology (59) 2004, pp. 1061-1069.
[8] Chang, Y., Stanley, R.J., Moss, R.H., and Stoecker, W.V., “A Systematic Heuristic Approach for Feature Selection For Melanoma Discrimination Using Clinical Images,” Skin Research and Technology (11) 2005, pp. 165-178.
[9] Dash, M. and Liu, H., “Feature Selection Methods For Classifications,” Intelligent Data Analysis: An International Journal(13) 1997, pp. 131-156.
[10] Ding, L. and Goshtasby, A., “On the Canny Edge Detector,” Pattern Recognition (34) 2001, pp. 721-725.
[11] Dhawan, A., Medical Image Analysis, John Wiley, New York, 2003.
[12] Fu, J.C., Lee, S.K., Wong, S.T.C., Yeh, J.Y., Wang, A.H., and Wu, H.K., “Image Segmentaion Feature Selectioin and Pattern Classification for Mammographic Microcalcifications,” Computerized Medical Imaging and Graphics (29) 2005, pp. 419-429.
[13] Gonzalez, R.C., and Woods R.E., Digital Image Processing (2nd ed.), Prentice Hall, 2002.
[14] Gonzalez, R.C., Woods R.E., and Eddins, S.L., Digital Image Processing Using MATLAB (1st ed.), Prentice Hall, 2003.
[15] Gletsos, M., Mougiakakou, S.G., Matsopoulos, G.K., Nikita, K.S., Nikita, A.S., and Kelekis, D., “A Computer-Aided Diagnostic System to Characterize CT Focal Liver Lesions : Design and Optimization of a Neural Network Classifier,” IEEE Transactions on Biomedical Engineering (7) 2003, pp. 153-162.
[16] Hahm, D. and Anderer, U., “Establishment of HEp-2 Cell Preparation for Automated Analysis of ANA Fluorescence Pattern,” Cytometry (69) 2006, pp. 178-181.
[17] Haralick, R.M., Shanmugam, K., and Dinstein I., “Textural Features for Image Classification,” IEEE Transaction on Systems, Man, and Cybernetcs(3) 1973, pp. 610-621.
[18] Huang, Y.L., Chung, C.W., Hsieh, T.Y., and Jao, Y.L., “Outline Detection for the HEp-2 Cell in Indirect Immunofluorescence Images Using Watershed Segmentation,” IEEE International Conference on Sensor Network, Ubiquitous, and Trustworthy Computing, 2008, pp. 423-427.
[19] Kantardzic, M., Data Mining : Concepts, Models, Methods, and Algorithms, John Wiley, New York, 2003.
[20] Keerthi, S.S., Shevade, S.K., Bhattacharyya, C., and Murthy K.R.K., “Improvements to Platt’s SMO Algorithm for SVM Classifier Design,” Neural Computation(13) 2001, pp. 637-649.
[21] Kira, K. and Rendell, I.A., “The Feature Selection Problem : Traditional Methods and A New Algorithm,” Proceedings of 10th Nat Conf Artifi Intell, 1992, pp. 129-134.
[22] Kohavi, R.(1995), “Wrappers For Performance Enhancement And Oblivious Decision Graphs,” PhD Thesis, Department of Computer Science, Standford University, Stanford, CA.
[23] Koller, D. and Sahami, M., “Toward Optimal Feature Selection,” Machine Learning: Proceedings of the Thirteenth International Conference, 1996, pp. 284-292
[24] Li, Y. and Zou, X., “Image Edge Detection By Means Of Bivariate Non-Tensor Product Wavelet,” Journal of Jilin University (42) 2004, pp. 483-488.
[25] Liu, H. and Motoda H., Feature Selection For Knowledge Discovery And Data Mining, Kluwer Academic Publishers, 1998.
[26] Merphy, R.F., Boland, M.V., and Velliste M., “Towards a Systematics for Protein Subcellular Location : Quantitative Description of Protein Localization Patterns and Automated Analysis of Fluorescence Microscope Images,” Proceedings of the Eighth International Conference on Intelligent Systems for Molecular Biology, 2000, pp. 251-259.
[27] Michael, M., and Gordon, P.C., “Did Tom Tattoo The Girl? Differential Effects Of Reader’s Interpretation On The Time Course Of Reanalysis,” AMLaP, 2004.
[28] Mitchell, M.T., Machine Learning, McGraw Hill, New York, 1997.
[29] Mitra, S. and Acharya, T., Data Mining : Multimedia, Soft Computing, and Bioinformatics, Wiley-Interscience, 2003.
[30] Nattkemper, T.W., Wersing, H., and Walter Schubert, H.R., “A Neural Network Architecture for Automatic Segmentation of Fluorescence Micrographs,” Neurocomputing (48) 2002, pp. 357-367.
[31] Perner, P., “Classification of HEp-2 Cells Using Fluorescent Image Analysis and Data Mining,” Medical Data Analysis (2199) 2001, pp. 219-224.
[32] Perner, P., Perner, H., and Muller, B., “Mining Knowledge for HEp-2 Cell Image Classification,” Journal Artificial Intelligence in Medicine (26) 2002, pp. 161-173.
[33] Quinlan, J.R., C4.5 : Programs for Machine Learning, Morgan Kaufmann, 1993.
[34] Svolos, A.E. and Pokropek, A.T., “Time and Space Results of Dynamic Texture Feature Extraction in MR and CT Image Analysis,” IEEE Transactions on Information Technology in Biomedicine(2) 1998 pp. 48-54.
[35] Sack, U., Knoechner, S., Warschkau, H., Pigla, U., Emmrich, F., and Kamprad, M., “Computer-Assisted Classification of HEp-2 Immunofluorescence Patterns in Autoimmune Diagnostics,” Autoimmunity Reviews (2) 2003, pp. 298-304.
[36] Shah, P.S.K. and Gandhi, V., ”Image Classification Based on Textural Features Using Artificial Neural Network(ANN),” IE(I) Journal-ET (84) 2004, pp. 72-77.
[37] Siedlecki, W. and Kulikowski, C.A., “On Automatic Feature Selection,” International Jorunal of Pattern Recognition and Artificial Intelligence(2) 1988, pp. 197-220.
[38] Sim, J. and Wright C.C., ” The Kappa Statistic in Reliability Studies : Use, Interpretation, and Sample Size Requirements,” Phys Ther. 2005, 85 : pp 257-268.
[39] Tang, X., ”Texture Information in Run-Length Matrices,” IEEE Transactions on Image Processing(7) 1998, pp. 1620-1609.
[40] Vapnik, V.N., “An overview of statistical learning theory,” IEEE Transactions on Networks(10) 1999, pp. 988-999.
[41] Witten, I.H. and Frank, E., Data Mining: Practical Machine Learning Tools and Techniques (2nd ed.), Morgan Kaufmann, 2005.
[42] Yang, F. and Jiang, T., “Cell Image Segmentation with Kernel-Based Dynamic Clustering and An Ellipsoidal Cell Shape Model,” Journal of Biomedical Information (34) 2001, pp. 67-73.
[43] Zhang, J. and Tan, T., “Brief Review of Invariant Texture Analysis Methods,” Pattern Recognition (35) 2002, pp. 735-747.