乳癌為全世界女性死亡率排名第二之癌症，每八個女性就有一位得到乳癌。多發性之乳癌，治癒後仍有機率轉移造成身體損害。為了預知乳癌是否轉移，早期治療病患以增加存活率，乳癌預後相對重要。本文共蒐集162位乳癌病患與70位正常人舌象特徵，由自動化舌診系統依脾胃區、肝膽左區、肝膽右區、腎區、心肺區等舌面分區，分別擷取舌色、舌形、津液、舌苔、舌質、裂紋、瘀點、齒痕、朱點等九項特徵。經曼-惠特尼檢定推導乳癌病患與正常人具顯著差異之舌頭分區特徵(p<0.05)，計有舌苔整體(p=0.007)、舌苔脾胃區(p=0.020)、舌苔最大面積(p=0.002)、薄苔(p=0.000)、齒痕數量(p=0.050)、朱點數量(p=0.000)、朱點脾胃區個數(p=0.000)、朱點肝膽左區(p=0.002)、朱點肝膽右區(p=0.000)、朱點心肺區個數(p=0.003)等項目，將蒐集之資料區分為訓練資料和測試資料兩群組。選擇55位乳癌病患與60位正常人當作訓練資料而5位乳癌病患與10位正常人當作測試資料。訓練資料主要著重比較乳癌患者與正常人舌象之顯著差異特徵。將曼-惠特尼檢定中具顯著差異之舌象特徵視為因子進行邏輯迴歸分析，移除一項最不顯著之特徵(p>0.05)並進行邏輯迴歸分析，透過三次特徵之移除和分析，檢定出獨立顯著特徵，計有舌苔整體(p=0.011)、舌苔脾胃區(p=0.006)、舌苔最大面積(p=0.003)、薄苔(p=0.019)、朱點數量(p=0.017)、朱點脾胃區個數(p=0.002)、朱點心肺區個數(p=0.016)有獨立顯著意義，為了證實獨立顯著特徵重要性，移除了一個獨立顯著特徵，薄苔(p=0.019)，並進行邏輯迴歸分析，檢定顯著特徵，計有舌苔整體(p=0.037)、舌苔脾胃區(p=0.005)、舌苔最大面積(p=0.001)、朱點數量(p=0.008)、朱點脾胃區個數(p=0.002)、朱點心肺區個數(p=0.005)，並建立三組預測罹患乳癌與否之邏輯迴歸模型。模型(一)為以曼-惠特尼檢定中具顯著差異之十項舌象特徵為因子進行預測，正確率為80%，模型(二)為以邏輯迴歸分析檢定出七項獨立顯著舌象特徵為因子進行預測，正確率為80%。模型(三)為驗證獨立顯著特徵重要而檢定出六項獨立顯著舌象特徵為因子進行預測，正確率為67%。

Breast cancer ranks second in the cancer fatality rate among females worldwide. One out of every eight women gets BC during lifetime. The reasons leading to breast cancer are multiple. Even after breast cancer is cured, there is still some metastasis probability which may damage body and threat to life. The prognosis of breast cancer is important to predict the metastasis of breast cancer and reach early treatment so that it can increase the survival rate. The tongue features for 60 breast cancer patients and 70 normal persons are extracted by the Automatic Tongue Diagnosis System (ATDS). A total of nine tongue features, namely, tongue color, tongue quality, tongue fissure, tongue fur, red dot, ecchymosis, tooth mark, saliva, and tongue shape are identified for each tongue. Features extracted are further sub-divided according to the areas located, i.e., spleen-stomach, liver-gall-left, liver-gall-right, kidney, and heart-lung area. The purpose focuses on inducing significant tongue features (p<0.05) to discriminate breast cancer patients from normal persons. The Mann-Whitney test shows that the amount of tongue fur (p=0.007), the tongue fur in the spleen-stomach area (p=0.020), maximum covering area of tongue fur (p=0.002), thin tongue fur (p=0.000), the number of tooth mark (p=0.050), the number of red dot (p=0.000), red dot in the spleen-stomach area (p=0.000), red dot in the liver-gall-left area (p=0.002), red dot in the liver-gall-right area (p=0.000), red dot in the heart-lung area (p=0.003) demonstrate significant differences. Next, the data collected are classified into two groups. The training group consists of 55 breast cancer patients and 60 normal persons, while the testing group is composed of 5 breast cancer patients and 10 normal persons. The logistic regression by utilizing these 10 tongue features with significant differences in Mann-Whitney test as factors is performed. Then we remove one of the 10 tongue features which is not the most significant differences (p>0.05) and perform logistic regression three times. Among them, the amount of tongue fur (p=0.011), the tongue fur in the spleen-stomach area (p=0.006), the maximum covering area of tongue fur (p=0.003), thin tongue fur (p=0.019), the number of red dot (p=0.017), red dot in the spleen-stomach area (p=0.002), red dot in the heart-lung area (p=0.016) reveal independently significant meaning. To prove the importance of independently significant meaning, we remove an independently significant meaning, thin tongue fur (p=0.019), and perform logistic regression. Among them, the amount of tongue fur (p=0.037), the tongue fur in the spleen-stomach area (p=0.005), the maximum covering area of tongue fur (p=0.001), the number of red dot (p=0.008), red dot in the spleen-stomach area (p=0.002), red dot in the heart-lung area (p=0.005) reveal independently significant meaning. The tongue features of the testing group are employed in the aforementioned three models to test the power of significant tongue features identified in predicting breast cancer. An accuracy of 80% is reached through Model I by applying the 10 significant tongue features obtained through Mann-Whitney test. For the second model employing 7 tongue features induced by logistic regression with independently significant meaning, 80% accuracy is achieved. The third model employing 6 tongue features induced by logistic regression with independently significant meaning, 67% accuracy is achieved and proves the important prediction of independently significant meaning.

論文審定書 i
摘要 ii
Abstract iii
目 錄 v
圖　次 vi
表 次 vii
第一章 簡介 1
1.1舌診辨證 1
1.2乳癌預後 4
1.3乳癌與中醫舌診之關聯 7
第二章 相關研究 9
2.1 舌診與特定疾病 9
2.2 乳癌預後之因子 13
第三章 研究方法 15
3.1 研究架構 15
3.1.1 資料蒐集 15
3.1.2 資料分類 17
3.2 自動化舌診系統 18
3.2.1 自動化舌診系統之舌頭分類特徵 20
3.3 舌象差異特徵統計分析 22
3.3.1 無母數統計分析 23
3.3.2 Mann–Whitney U Test 23
3.3.3 雙樣本T檢定 24
3.3.4 邏輯式迴歸 25
第四章 實驗結果 27
4.1乳癌患者與正常人舌頭差異特徵 27
4.1.1 模型 I 28
4.1.2 模型 II 30
4.1.3 模型 III 34
4.2乳癌腫瘤發病部位和乳癌期數 36
第五章 結論與未來展望 37
5.1 研究結論 37
5.2 未來展望 37
參考文獻 39
附錄 44

[1] System, apparatus, method and program for tongue diagnosis, JP2009-028058A, Feb. 12, 2009.
[2] Katrina Armstrong, Elizabeth A. Handorf, Jinbo Chen, Mirar N. Bristol Demeter, "Breast Cancer Risk Prediction and Mammography Biopsy Decisions : A Model-Based Study. " American Journal of Preventive Medicine, Vol. 44, pp. 15–22, 2013.
[3] 厚生健康園區:http://www.24drs.com/webmd/chinese_t.asp?who=1662.58263.
[4] http://www.reocities.com/my686chen/breast3.html.
[5] Elizabeth Meade, Maura Dowling, "Early breast cancer: diagnosis, treatment and survivorship," British Journal of Nursing, Vol. 21, Iss. 17 - Supplement, pp. S4 - S7, 27 Sep 2012.
[6] MahjabeenMirza Beg, Monika Jain, "An analysis of the methods employed for breast cancer diagnosis," International Journal of Research in Computer Science, 2 (3): pp. 25-29, April 2012.
[7] Hjerl et al. (2003) Depression as a prognostic factor for breast cancer mortality. Psychosomatics. 44:24-30.
[8] Wasif N, Maggard MA, Ko CY, Giuliano AE., "Invasive lobular vs. ductal breast cancer: a stage-matched comparison of outcomes." Ann SurgOncol., Vol. 17, pp. 1862–1869, 2010.
[9] Jenn Lung Su, "Standardized Tongue Diagnosis (3-3) - The Study of Characteristic for Tongue Image in Specific Disease," Yearbook of Chinese Medicine and Pharmacy, 24(6), pp. 277-298, 2006.
[10] Lun-Chien Lo, John Y. Chiang, Tsung-Lin Cheng and Pei-ShuanShieh, "Visual Agreement Analyses of Traditional Chinese Medicine -A Multiple Dimensional Scaling Approach," Evidence-Based Complementary and Alternative Medicine, Vol. 2012 (2012), Article ID 516473. doi:10.1155/2012/516473.
[11] Lun-Chien Lo, Tsung-Lin Cheng, Wen-Jiuan Chen, Yung-Fu Chen and John Y. Chiang, "The Study on the Agreement between Automatic Tongue Diagnosis System and Traditional Chinese Medicine Practitioners," Evidence-Based Complementary and Alternative Medicine, Vol. 2012 (2012), Article ID 505063. doi:10.1155/2012/505063.
[12] Lun-chien Lo, Tsung-Lin Cheng, Wen-Jiuan Chen, Yung-Fu Chen, John Y. Chiang, "The Study on the Agreement between Automatic Tongue Diagnosis System and Traditional Chinese Medicine Practitioners," Proc. 6th European Congress for Integrative Medicine, Florence, Italy, Sept. 21-22, 2012.
[13] Lun-Chien Lo, Chia-Yun Chen, John Y. Chiang, Tsung-Lin Cheng, Hong-Jen Lin, and Hen-Hong Chang, "Tongue Diagnosis of Traditional Chinese Medicine for Rheumatoid Arthritis," African Journal of Traditional, Complementary and Alternative medicines, (accepted)
[14] Yu Cheng Hsu, Ying-ching Chen, Lunchien Lo, John Y. Chiang, "Automatic Tongue Feature Extraction," Proc. Int'l Computer Symp. (ICS2010), pp. 936-941, Tainan, Taiwan, Dec. 16-18 2010. [EI]
[15] Lun-chien Lo, Mark Chun-cheng Hou, Ying-ling Chen, John Y. Chiang and Jeng-jiunShyu, "Automatic Tongue Diagnosis System," Proc. 2nd Int'l Conf. on BioMedical Engineering and Informatics (BMEI'09), pp. 140-144, Tianjin, China, 17-19 October, 2009.
[16] Michael P. Fay, Michael A. Proschan, "Wilcoxon-Mann-Whitney or t-test? On assumptions for hypothesis tests and multiple interpretations of decision rules." PMC, Vol. 4, pp. 1-39, 2010.
[17] Hans van der Heijden, "Decision support for selecting optimal logistic regression models," Expert Systems with Applications, Vol. 39, Iss. 10, pp. 8573-8583, 2012.
[18] Donald W. Zimmerman, "Correcting Two-Sample z and t Tests for Correlation: An Alternative to One-Sample Tests on Difference Scores," International Journal of Methodology and Experimental Psychology, pp. 391-418, 33, 2012.
[19] 李燕，『大腸癌患者化療前後舌象變化的臨床研究』，北京中醫藥大學(2007)。
[20] 吳君德，『腫瘤患者舌象特點的臨床研究』，北京中醫藥大學(2011)。
[21] 姚嫱，『乳腺癌和肺癌患者舌象特點及客觀量化的研究』，遼寧中醫雜誌，02期，第163-164頁，2008。
[22] 富琦，王皓，韓冬，張萃，王笑民，『乳腺癌術後患者化療前後中醫證候變化的臨床研究』，北京中醫藥，1期，2012。
[23] 龔一萍，倪美文，陳海燕，陳素珍;，卜佳俊，連奕劭，『癌症與非癌症腻苔的定量研究』，中華中醫藥雜誌，9期，2007。
[24] 王冬，『中醫舌診對肺癌的診斷應用價值研究』，河北醫科大學，2009。
[25] 韓垚，『高血壓病舌診定量診斷與中醫證型的研究』，中國中醫科學院，2006。
[26] Marianne Ewertz, Maj-Britt Jensen, Katrín Á. Gunnarsdóttir, Inger Højris, Erik H. Jakobsen, Dorte Nielsen, Lars E. Stenbygaard, Ulla B. Tange and Søren Cold, "Effect of Obesity on Prognosis After Early-Stage Breast Cance," American Society of Clinical Oncology, 2010.
[27] 張志楓，王子焱，應荐，許家佗，沈雪勇，周昌樂，楊華元，史美育，吳芸， 嚴竹娟，『乳腺增生病患者舌面與增生组織體表红外輻射强度相關性分析』，中西醫結合學報，第5卷，第6期，第625-629頁，2007。
[28] Shuangge Ma, Michael R Kosorok, "Detection of gene pathways with predictive power for breast cancer prognosis," BMC Bioinformatics, 2010.
[29] 張昭威，『運用資料探勘方法建構乳癌預後模式』，朝陽科技大學工業工程與管理系碩士論文(2010)。
[30] Rebecca Siegel MPH, DeepaNaishadham MA, MS, AhmedinJemal DVM, PhD, "Cancer statistics, 2012," A Cancer Journal for Clinicians, Vol. 62, Iss. 1, pp. 10–29, January/February 2012.
[31] JiatuoXu, LipingTu, HongfuRen and Zhifeng Zhang, "A medical image color correction method base on supervised color constancy," IEEE International Symposium on IT in Medicine and Education, pp.673 - 678, 12-14 Dec. 2008.
[32] JiatuoXu, LipingTu, Zhifeng Zhang, Li Zhang and Changle Zhou, "The region partition of quality and coating for tongue image based on color image segmentation method," IEEE International Symposium on IT in Medicine and Education, pp.817 - 821, 12-14 Dec. 2008.
[33] Wang X., "A New Tongue Colorchecker Design by Space Representation for Precise Correction," IEEE Transactions on Information Technology in Biomedicine,Issue 99, pp.1, 2012.
[34] Miaojing Shi, Guo-Zheng Li, Fufeng Li, Chao Xu, "A novel tongue segmentation approach utilizing double geodesic flow." Proc. International Conference on Computer Science and Education, pp. 21-25, 2012.
[35] Chao Liang, Dongcheng Shi, "A Prior Knowledge-Based Algorithm for Tongue Body Segmentation," Pro. International Conference on Computer Science and Electronics Engineering, pp. 245-247, 2012.
[36] M. Nicolao, M. G. Täuber& P. Heusser, "How should complementary and alternative medicine be taught to medical students in Switzerland? A survey of medical experts and students," Medical Teacher, 32: pp. 50–55, 2010.
[37] G. G. Zhang, W. Lee, B, Bausell, L. Lao, B. Handwerger and B. Berman, "Variability in the Traditional Chinese Medicine (TCM) Diagnoses and Herbal Prescriptions Provided by Three TCM Practitioners for 40 Patients with Rheumatoid Arthritis, " J. Altern. Complement. Med., 11: pp. 415-421, 2005.
[38] T. Kaptchuk, "Chinese Medicine: The Web That Has No Weaver," 2nd ed., London: Rider, 2000.
[39] K. A. O'Brien, E. Abbas, J. Zhang, Z. X. Guo, R. Luo, A. Bensoussan, and P. A. Komesaroff, "An investigation into the reliability of Chinese medicine diagnosis according to Eight Guiding Principles and Zang-Fu Theory in Australians with hypercholesterolemia, " J. Altern. Complement. Med., vol. 15, no. 5, pp. 259-266, 2009.
[40] K. A. O'Brien, E. Abbas, P. Movsessian, M. Hook, P. A. Komesaroff , and S. Birch, "Investigating the Reliability of Japanese Toyohari Meridian Therapy Diagnosis, " J. Altern. Complement. Med., vol. 15, no. 10, pp. 1099-1105, 2009.
[41] S. Mist, C. Ritenbaugh and M. Aickin, "Effects of Questionnaire-Based Diagnosis and Training on Inter-Rater Reliability among Practitioners of Traditional Chinese Medicine," J. Altern. Complement. Med., vol. 15, no. 7, pp. 703-709, 2009.
[42] K. A. O'Brien and S. Birch, "A review of the reliability of Traditional East Asian Medicine diagnoses," J. Altern. Complement. Med., vol. 15, no. 4, pp. 353-366, 2009.
[43] R. R. Coeytaux, W. Chen, C. E. Lindemuth, Y. Tan, and A. C. Reilly, "Variability in the diagnosis and point selection for persons with frequent headache by traditional Chinese acupuncture," J. Altern. Complement. Med.,vol. 12, no. 9, pp. 863-872, 2006.
[44] N. Wiseman and A. Ellis, "Fundamentals of Chinese Medicine: Zhong Yi XueJi Chu," Brookline, MA: Paradigm Publications, 1996.
[45] B. Kirschbaum, "Atlas of Chinese Tongue Diagnosis," Seattle: Eastland Press, 2000.
[46] 周學海，『重訂診家直訣』，文興出版社2006，ISBN: 9868174082。
[47] 俞根，『重訂通俗傷寒論』，中國中醫藥處版社2011，ISBN: 9787513202411。