臺灣博碩士論文加值系統

子宮頸癌是全世界婦女中第二常見的癌症，然而子宮頸癌如果能透過篩檢來檢測癌前病變，提早發現提早治療，是能夠大大降低了子宮頸癌發病率和死亡率的。其中陰道鏡檢查是一項很重要的工具。癌前子宮頸細胞病變分類為非典型鱗狀細胞化生不良、柱狀細胞化生不良、輕度、中度、重度細胞化生不良CINI~III(Cervical Intraepithelial Neoplasia I~III)、原位癌。不同的狀況其治療方式與疾病預後有相當的差異。醫師可以藉由陰道鏡檢查根據子宮頸的實際情形來判斷子宮頸的病變程度，以及確定是否需要做切片檢查。然而他並沒有一個很客觀的量化標準，完全必須憑醫師主觀的判斷來決定癌前病變的等級，所以陰道鏡檢查的準確性和醫師的經驗值非常的相關。我們可以運用電腦影像技術輔助來幫助醫師確認病灶位置，並且提供病灶癌化程度的量化數據，藉此讓醫師進行更精準的診斷。而在這些過程中找出病灶所在並且將它切割出來，是一個很重要的步驟，他會影響到癌化程度的量化數據，本論文將針對陰道鏡的子宮頸影像進行切割，所切割出來的影像可以提供醫師參考來確認病灶，並且可以做為癌化程度的特徵抽取及量化之用。

The morbidity and mortality of cervical cancer can be reduced by the screening of the precancerous lesions. Pap smears, colposcopy and biopsy are the most common screening tools. Pap smear is the first-line tool because of its high specificity and low cost. But its false-positive rate is too high and must be confirmed by other tools. Biopsy is a deterministic examination for cervical neoplasia. However, it is not suitable for the high probability of false-positive. Digital colposcopy is a promising technology for the detection of cervical intraepithelial neoplasia. However, there are no quantitative criteria for the differential of precancerous lesions and it is subjected to the variation of inter-observer and intra-observer. Therefore, automated image analysis of colposcopic images is thus necessary for the improvement of diagnosis of colposcopy. The segmenetation of the lession from digital colposcopyic image is a key issue of this analysis. Our goal is to develop a segmentation policy that can separate images into regions which contain the lesion areas. These areas can be provided to the analysis system and help doctor to make the diagnosis.

目　　錄
摘　要…………………………………………………………………………Ⅰ
Abstract………………………………………………………………Ⅱ
誌　謝………………………………………………………………………Ⅲ
目　錄…………………………………………………………………………Ⅳ
圖　目　錄…………………………………………………………………Ⅴ
表　目　錄…………………………………………………………………Ⅵ
第一章 緒論…………………………………………………………………1
1.1研究動機……………………………………………………………1
1.2研究目的……………………………………………………………3
1.3論文架構……………………………………………………………3
第二章 文獻探討………………………………………………………4
2.1子宮頸及子宮頸癌…………………………………………………4
2.2子宮頸癌的診斷………………………………………………………6
2.3陰道鏡檢查及子宮頸癌病灶的判斷…………………………………7
2.4群聚及分群演算法………………………………………………11
2.4.1 k-means clustering…………………………………………12
2.4.2 Fuzzy k-means clustering…………………………………14
2.5自我組織圖網路……………………………………………………15
2.6分群品質測量(Cluster-Quality Measures, CQM)………………18
2.6.1 Global Silhouette Index(GSI)……………………………19
2.6.2 Partition Index(PI)………………………………………20
2.6.3 Separation Index (SI)……………………………………20
2.6.4 Dunn’s Index(DI)…………………………………………21
第三章 研究方法…………………………………………………………22
3.1研究材料與設備……………………………………………………22
3.2研究方法及流程……………………………………………………22
第四章 實驗與討論………………………………………………………33
4.1影像來源……………………………………………………………33
4.2實驗設備……………………………………………………………33
4.3實驗結果與討論……………………………………………………33
4.3.1群數的選擇…………………………………………………34
4.3.2 SOM神經元的數目…………………………………………34
4.3.3 SOM對效率的影響…………………………………………35
第五章 結論…………………………………………………………………37
參考文獻………………………………………………………………………38
圖　　目　　錄
圖1 子宮解剖圖 …………………………………………………………4
圖2 塗抹醋酸前後影像 ……………………………………………………8
圖3 三種癌前病變的陰道鏡…………………………………………………10
圖4 SOM映射方式 ………………………………………………………16
圖5 六角形的鄰近範圍形狀 ……………………………………………18
圖6 分群結果比較…………………………………………………………19
圖7 系統流程圖……………………………………………………………24
圖8 四種分群品質計算分法……………………………………………… 25
圖9 各種群內距離計算的結果 ……………………………………………27
圖 10(a) 陰道鏡子宮頸原圖………………………………………………29
圖 10(b) 所有像素在3維的向量空間……………………………………… 29
圖 10(c) 所有像素均映射到紅色的神經元…………………………… 30
圖 10(d) 將所有神經元抽出………………………………………………30
圖 10(e) 針對神經元分成4群………………………………………………31
圖 10(f) 每個像素根據對應神經元的群聚產生分群結果………………31
圖 10(g) 最後被分成4群的結果…………………………………………32

 
表　　目　　錄
表1 四種分群品質計算方法的分析…………………………………………25
表2 各個癌化等級所預測的分群群數效率…………………………………34
表3 不同神經元數目對correctness的影響…………………………………35
表4 各個癌化等級的分群效率………………………………………………36

[1]S. Y. Park, M. Follen, A. Milbourne, H. Rhodes, A. Malpica, N.Mackinnon, C. MacAulay, M. K. Markey, and R. Richards-Kortum,“Automated image analysis of digital colposcopy for the detection ofcervical noplasia,” J. Biomed. Opt. 13, 014029-1–014029-10 (2008).
[2]Cancer Facts & Figures 2006, available at: http://www.cancer.org.
[3]R. Sankaranarayanan, R. Rajkumar, R. Theresa, P. O. Esmy, C.Mahe, K. R. Bagyalakshmi, S. Thara, L. Frappart, E. Lucas, R. Muwonge,S. Shanthakumari, D. Jeevan, T. M. Subbarao, D. M. Parkin,and J. Cherian, “Initial results from a randomized trial of cervicalvisual screening in rural south India,” Int. J. Cancer 109, 461–467 (2004).
[4]Li Wenjing, VenkataramanSankar, Gustafsson Ulf, Oyama Jody C, Ferris Daron G, Lieberman Rich W, “Using acetowhite opacity index for detecting cervical intraepithelial neoplasia,” j.Biomed. Opt. 14(1), 014020 (2009)
[5]D. Ferris, J. T. Cox, D. M. O’Connor, V. C. Wright, and J. Foerster, Modern Colposcopy, Textbook and Atlas, American Society for Colposcopy and Cervical Pathology, Dubuque, IA (2004).
[6]R. Reid and P. Scalzi, “Genital warts and cervical cancer. VII. Animproved colposcopic index for differentiating benign papillomaviralinfections from high-grade cervical intraepithelial neoplasia,” Am. J.Obstet. Gynecol. 153, 611–618 (1985).
[7]J. T. Cox, M. Schiffman, and D. Solomon, “Prospective follow-upsuggests similar risk of subsequent cervical intraepithelial neoplasiagrade 2 or 3 among women with cervical intraepithelial neoplasiagrade 1 or negative colposcopy and directed biopsy,” Am. J. Obstet.Gynecol. 188, 1406–1412 (2003).
[8]Hudong互動百科, 子宮頸, http://www.hudong.com/wiki/子宫颈
[9]世界最新癌訊，第十輯，2003.12,
http://www.taishan-international.org/edition10.htm#v1
[10]S. Yang, J. Guo, P. King, Y. Sriraja, S. Mitra, B. Nutter, D. Ferris, M.Schiffman, J. Jeronimo, and R. Long, “A multi-spectral digital cervigramanalyzer in the wavelet domain for early detection of cervicalcancer,” Proc. SPIE 5370, 1833–1844 (2004).
[11]S. Gordon, G. Zimmerman, R. Long, S. Antani, J. Jeronimo, and H.Greenspan, “Content analysis of uterine cervix images: initial stepstowards content based indexing and retrieval of cervigrams,” Proc.SPIE 6144, 1549–1556 (2006).
[12]B. W. Pogue, M. A. Mycek, and D. Harper, “Image analysis fordiscrimination of cervical neoplasia,” J. Biomed. Opt. 5, 72–82 (2000).
[13]B. W. Pogue, H. B. Kaufman, A. Zelenchuk, W. Harper, G. C. Burke,E. E. Burke, and D. M. Harper, “Analysis of acetic acid-inducedwhitening of high-grade squamous intraepithelial lesions,” J. Biomed.Opt. 6, 397–403 (2001).
[14]C. J. Balas, G. C. Themelis, E. P. Prokopakis, I. Orfanudaki, E.Koumantakis, and E. S. Helidonis, “In vivo detection and staging ofepithelial dysplasias and malignancies based on the quantitative assessmentof acetic acid-tissue interaction kinetics,” J. Photochem.Photobiol., B 53, 153–157 (1999).
[15]C. Balas, “A novel optical imaging method for the early detection,quantitative grading, and mapping of cancerous and precancerouslesions of cervix,” IEEE Trans. Biomed. Eng. 48, 96–104 (Jan.2001).
[16]H. Kaufman, A. Zelenchuk, R. Flewelling, P. Schmid, and Z. Hed,“Methods of monitoring effects of chemical agents on a sample,”U.S. Patent No. 6,902,935 B2 (June 7, 2005).
[17]Han, J., Kamber, M., & Tung, A. K. H. (2001). Spatial clustering methods in data mining: A survey In H. Miller, & J. Han (Eds.), Geographic data mining and knowledge discovery. Taylor and Francis.
[18]Tain A.K., Murthy M.N., Flynn P.J., Data clustering: a review, ACM Comput. Survey, 31, 3, 264–323(1999).
[19]Ali, R., Ghani, U., Saeed, A., 1998. Data clustering and its applications. Available at: http://www.members.tripod.com/asim_saeed/paper.htm
[20]Hartigan J. A. and Wong M. A. "A K-Means Clustering Algorithm", Applied Statistics, Vol. 28, No. 1, p100-108, (1979).
[21]Nock, R. and Nielsen, F. "On Weighting Clustering", IEEE Trans. on Pattern Analysis and Machine Inteligence, 28 (8), 1–13 (2006).
[22]Ultsch, Alfred Emergence in Self-Organizing Feature Maps, In Proceedings Workshop on Self-Organizing Maps (WSOM ''07). Bielefeld, Germany, (2007).
[23]Rousseeuw, P.J., Silhouettes: A graphical aid to the interpretation and validation of cluster analysis. J. Comput. Appl. Math. 20, 53-65, (1987).
[24]Bolshakova, N., Azuaje, F., Clustering validation techniques for genome expression data. Genomic Signal Processing 83 (4), 825-833, (2003).
[25]Bensaid, A.M., Hall, L.O., Bezdek, J.C., Clarke, L.P., Silbiger, M.L., Arrington, J.A., Murtagh, R.F., Validity-guided (Re) clustering with applications to image segmentation. IEEE Trans. on Fuzzy Systems 4(2), 112-123, (1996).
[26]Dunn, J.C., Well separated clusters and optimal fuzzy partitions. J. Cybernetics 4, 95-104, (1974).
[27]Bezdek, J.C., Pal, N.R., Some new indexes of cluster validity. IEEE Trans. on Systems, Man and Cybernetics, part B 28(3), 301-315, (1988).