臺灣博碩士論文加值系統

台灣婦女隨著生活型態都市化、飲食習慣日漸西化的影響，乳癌發生率與死亡率逐年增加，而近五年來，乳癌發生率已高居台灣女性癌症發生率的第一位，好發年齡則在四十五至五十五歲之間。乳癌初期可能毫無症狀而導致延誤就醫，當病患被確診為癌症時，大部份的案例已有轉移至淋巴腺的情況，這也提高了乳癌復發的機率，甚至會引發另一種癌症，相對也須付出更大的醫療資源支出及社會成本。

隨著醫療資訊技術不斷的進步及醫療資訊系統的廣泛使用，醫院內資料庫中所儲存的病例資料也因而快速累積，蘊藏於在其中的可用知識也相對提高。乳癌切除手術後的復發預測在醫師對於術後的治療規畫與病況追蹤上有相當大的幫助，過去常利用統計方法進行乳癌的術後復發預測，本研究則嘗試利用資料探勘技術中的C4.5決策樹與支援向量機SVM兩種分類分析技術，建構可預測乳癌術後復發的決策模式。為了提昇預測模式對於乳癌復發案例的分類效能，本研究也嘗試利用Adaboost與Bagging兩種增強委員會方法，期能提升預測模式的分類效能。研究結果顯示，AdaBoost委員會方法較能有效提升C4.5及SVM對乳癌復發的預測效能。

The incidence and mortality rate of breast cancer in Taiwanese Women have increased gradually due to the urban life style and westen style food.In the recent 5 years, the incidence of breast cancer in Taiwanese Women became the first in all cancers. The highest perioid of incidence of breast cancer is between 45 to 55 years old. In the early stage of breast cancer, it is almost asymptoatic and keep the patients from medical help.When the breast cancer was diagnosed, many of them aleady have lymph node metastasis. This situation also lifts the recurrent rate.
Due to the progress of information technology and medical information system, hospitals also have accumlated a large amount of data in the database of information systems. Therefore, much useful medical knowledge could be mined from the history data. The prediction of breast cancer relapse is very helpful for post-operative treatment and followup. The statistical methods had been applied to predict breast cancer relapse. However, this study employed data mining techciques, including C4.5 decision tree and SVM, to construct recurrence prediction models of breast cancer. To improve the prediction efficiency, this study also applied committee machine methods, including AdaBoost and Bagging, to increase the relapse prediction accuracy. The empirical results show that AdaBoost mechanism can ehance prognosis accuracy of C4.5 and SVM models on breast cancer relapse.
Keyword：Breast cancer relapse、C4.5 decision tree、Support Vector Machine、Committee Machine

摘 要 III
ABSTRACT IV
表目錄 VI
圖目錄 VII
第一章 緒論 1
第一節 研究背景 1
第二節 研究動機與目的 3
第三節 論文架構 4
第二章 文獻探討 5
第一節 乳癌復發的預後因子 5
第二節 分類分析技術 11
第三節 分類效能增強的委員會機器 15
第三章 資料搜集與評估方法 19
第一節 資料的蒐集與資料描述 19
第二節 模式建構流程 29
第四章 實證評估 31
第一節 利用病理組織切片資訊建立預測模式 31
第二節 利用FNA細胞影像資料建立預測模式 34
第三節 運用自動屬性挑選機制輔助預測模式的建構 37
第五章 結論與建議 40
第一節 結論 40
第二節 研究限制與建議 42
參考文獻 43

參考文獻
一、英文部分
[ABA88]Allionemi, O.P., Blanco, G., & Alavaikko, M., Improving the prognostic valve of DNA flow cytometry in breast cancer by combining DNA index and S-phase fraction, Cancer,1998,Vol. 62, pp.2183-2190.
[B96]Breiman, L., Bagging Predictors, Machine Learning, 1996,Vol. 24, No. 2, pp.123-140.
[BL97]Berry, M. J. A. & Linoff, G., Data Mining Techniques: For Marketing, Sales and Customer Support, John Wiley & Sons Inc.,1997, pp.286-334.
[BR57]Bloom, H.J, & Richardson, W.W., Histological grading and prognosis in breast cancer, Br J Cancer 11,1957, pp.359-77.
[CHS97]Cabena, P., Hadjinian, P., Stadler, R., Verhees, J., & Zanasi, A., Discovering Data Mining: From Concept to Implementation, Prentice Hall, 1997.
[CLG02]Chan, K. L. , Lee, T. W. , Goldbaum, M. H. , Weinreb, R. N. , & Sejnowski, A. T. J., Comparison of machine learning and traditional classifiers in glaucoma diagnosis. IEEE Transactions on Biomedical Engineering, 2002, Vol. 49, pp.963-974.
[CNK04]Cantu-Paz, E., Newsam, S., & Kamath, C., Feature Selection in Scientific Applications. Proceedings of ACM International Conference on Knowledge Discovery and Data Mining,2004, pp.788-793.
[CS00]Cristianini N., & Shawe-Taylor J., An Introduction to Support Vector Machines and other Kernel-based Learning Methods, Cambridge,2000
[DGA05]Dursun D., Glenn, W., & Amit, K., Predicting breast cancer survivability:a comparison of three data mining methods, artifical intelligence in medicine, 2005, Vol. 34 ,pp.113-27.
[F86]Fisher E. R., Prognostic and therapeutic significance of pathological features of breast cancer. NCL Monogr, 1986, Vol. 1, pp.29-34.
[FS97]Freund, Y. & Schapire, R.E., A decision-theoretic generalization of on-line learning and an application to boosting, Journal of Computer and System Sciences, 1997, Vol. 55, pp.119-139.
[GWS95]Goldhirsch A.,Wood W. C., & Senn H. j., Commentary. Meeting Highlights :International Consensus panel on the treatment of primary breast cancer. J Natl cancer Inst, 1995, pp.87-1441.
[H00]Hall, M., Correlation-based feature selection for discrete and numeric class machine learning, Proceedings of the Seventeenth International Conference on Machine Learning, 2000.
[HC80]Henderson I. C., & Canellous G. P., Cancer of the breast: The past decade, J Natl cancer Inst, 1980, pp.17-30.
[HCH04]Huang, Z., Chen, H., Hsu, Chia-Jung., Chen, Wun-Hwa., & Wu, S., Credit rating analysis with support vector machines and neural networks: a market comparative study, Decision Support Systems, 2004, Vol. 37, pp.543-558 .
[HLVW92]Harris J. R., Lippman M. E., Veronesi U., & Willett W., Breast cancer, part 2, N Eng. J med, 1992, pp.327-473.
[HS98]Hall, M., & Smith, L., Practical Feature Subset Selection for Machine Learning. Proceedings of the 21st Australian Computer Science Conference, 1998, pp.181-191.
[JJGJE03]Jose’ M., Jose’ A., Gonzalo R. J., & Jose’ M. P., A combined neural work and decision trees model for prognosis of breast cancer replase, artificial intelligence in medicine, 2003, pp.45-63.
[KJK03]Kulkarni, A., Jayaraman, V. K., & Kulkarni, B. D., Control of chaotic dynamical system using support vetor machines, Physics Letter A , 2003, Vol. 317, pp.429-435.
[KLR97]Kennedy, L., Lee, Y., Roy, V. B., Reed, C. D., & Lippman, R. P., Solving Data Mining Problems through Pattern Recognition, Prentice Hall,1997
[OGM94]O’Rourke S., Galea M. H.,& Morgan D., Local recurrence after simple mastectomy, Br. J. Surg., 81, 1994,pp.386-9.
[Q86]Quinlan, J. R., Induction of Decision Tree, Machine Learning, 1986, Vol. 1, No. 1, pp.81-106.
[Q93]Quinlan, J. R., C4.5: Programs for Machine Learning, Morgan Kaufmann, 1993.
[RGS89]Rosen P. P., Groshen S., & Saigl E.E., A long-term follow-up study of survival in stage I(T1N0M0) and Stage II(T1N!M0) breast carcinoma, J.Clin.Oncol., 1989, Vol. 7, pp.355-66.
[RHH94]Ries L.A., Henson D. E., & Harras A., Survival from breast cancer according to tumor size and nodal status, Surg. Oncol .Clin. North Am, 1994, Vol. 3, pp.35-52.
[S90]Schapire, R. E., The strength of weak learnability, Machine Learning, 1990, Vol. 5, pp.197-227.
[S94] Street,N. W., Cancer diagnosis and prognosis via linear-programming-based machine learing,Available as UW mathematical programmn technical report, 1994, pp.94-14.
[S99]Simon, H., Neural Networks ： A Comprehensive Foundation, 1999, pp.351-355.
[WBS97]Wong, B. K., Bonovich, T. A., & Selvi, Y., Neural Network Applications in Business: A Review and Analysis of the Literature, Decision Support Systems, 1997, Vol. 19, pp.301-320.
[WEKA]http://www.cs.waikato.ac.nz/~ml/weka/index.html
[WF00]Witten, I. H. & Frank, E., Data Mining: Practical Machine Learning Tools with Java Implementations, Morgan Kaufmann, 2000.
二、中文部分
[王景南03]王景南，多類支向機之研究，元智大學資訊管理研究所碩士論文，2003年。
[林諺熙05]林諺熙，應用支撐向量機法於保險詐欺之預判，國立成功大學工業與資訊管理學系碩士在職專班碩士論文，2005年。
[吳秋文03]吳秋文，乳房疾病與乳癌，吳氏圖書有限公司，2003年。
[黃建銘05]黃建銘，支援向量機的參數選擇，國立台灣科技大學資訊工程所碩士論文，2005年。
[梁定澎04]梁定澎，決策支援系統與企業智慧，台北：智勝圖書公司，2004年。
[楊雅婷02]楊雅婷、郭雅君譯，乳房聖經上冊、下冊，天下生活出版股份有限公司，2002年。
[國家衛生研究院04]乳癌診斷與治療共識，國家衛生研究院癌症研究組，2004年。
[世界衛生組織統計資料] http://www.who.int/features/qa/15/zh/index.html
[行政院衛生署國民健康局癌症年報] http://www.doh.gov.tw/statistic/index.htm