中醫四診以「望聞問切」作為診斷病人的方法，來了解病人的身體的健康狀況，其中舌頭診斷（tongue diagnosis）重要的診察項目，其在臨床上具有相當重要的診斷價值。又近幾十年來，隨著人工智慧（artificial intelligence）與電腦視覺（computer vision）等電腦科學技術的發展，舌頭診斷電腦化（computerized tongue diagnosis）受到相關研究人員的關注。自動化舌診系統（Automatic Tongue Diagnosis System，ATDS）與舌頭檢測 電腦化系統（computerized tongue examination system，CTES）相繼建立，各式新穎的舌診儀器協助臨床醫師記錄舌象，除透過數位影像以計算出相關舌色與舌質等指標，近年來更使用高光譜影像儀拍攝舌頭，得以用吸收光譜等非可見光之頻譜分析的方法，提供更多的舌象資訊協助醫師臨床診斷。
本研究從彰化基督教醫院（Changhua Christian Hospital）取得小鼠口腔癌（oral cancer）之動物實驗舌頭影像資料，得以研究口腔癌之舌象分析。藉由取得口腔癌小鼠之舌頭影像，經過不同影像處理方式處理，再根據不同影像處理方法計算出多種影像相關之特徵，利用機器學習技術，挑選出可判別罹癌與正常小鼠舌象異同之特徵，並使用支持向量機（Support Vector Machine）建立起預測模型，提供預測未知樣本為口腔癌之可能性，可作為罹患口腔癌之風險標準。

In Traditional Chinese Medicine (TCM), tongue diagnosis is one of the most important approaches for getting significant evidences in diagnosing the patient’s health conditions. With the development of computer vision and machine learning, the computational tongue diagnosis is paid more attention by researchers. We cooperate with Changhua Christian Hospital (CCH) on an mouse animal experiment for researching TCM in oral cancer, being responsible for oral cancer tongue image analysis. We use Machine Learning approaches to find the relevant feature to the oral cancer in tongue image, and build a model for giving a oral cancer risk estimation.

1. Siegel, R., et al., Cancer statistics, 2014. CA: a cancer journal for clinicians, 2014. 64(1): p. 9-29.
2. Situ, B.C.I., Cancer Facts. 2015.
3. Schoop, R.A., M.H. Noteborn, and R.J.B. de Jong, A mouse model for oral squamous cell carcinoma. Journal of molecular histology, 2009. 40(3): p. 177-181.
4. Chiu, C.-C., C.-Y. Lan, and Y.-H. Chang, Objective assessment of blood stasis using computerized inspection of sublingual veins. Computer methods and programs in biomedicine, 2002. 69(1): p. 1-12.
5. Lo, L.-c., et al., The study on the agreement between automatic tongue diagnosis system and traditional chinese medicine practitioners. Evidence-Based Complementary and Alternative Medicine, 2012. 2012.
6. Zhi, L., et al., Classification of hyperspectral medical tongue images for tongue diagnosis. Computerized Medical Imaging and Graphics, 2007. 31(8): p. 672-678.
7. Liu, Z., H. Wang, and Q. Li, Tongue tumor detection in medical hyperspectral images. Sensors, 2011. 12(1): p. 162-174.
8. Yamamoto, S., et al., Regional image analysis of the tongue color spectrum. International journal of computer assisted radiology and surgery, 2011. 6(1): p. 143-152.
9. Michie, D., D.J. Spiegelhalter, and C.C. Taylor, Machine learning, neural and statistical classification. 1994.
10. Møller, M.F., A scaled conjugate gradient algorithm for fast supervised learning. Neural networks, 1993. 6(4): p. 525-533.
11. Hastie, T., R. Tibshirani, and J. Friedman, Unsupervised learning. 2009: Springer.
12. Sanger, T.D., Optimal unsupervised learning in a single-layer linear feedforward neural network. Neural networks, 1989. 2(6): p. 459-473.
13. Sutton, R.S. and A.G. Barto, Reinforcement learning: An introduction. Vol. 1. 1998: MIT press Cambridge.
14. Weiss, S.M. and I. Kapouleas, An empirical comparison of pattern recognition, neural nets and machine learning classification methods. Readings in machine learning, 1990: p. 177-183.
15. Kotsiantis, S.B., I. Zaharakis, and P. Pintelas, Supervised machine learning: A review of classification techniques. 2007.
16. Bishop, C.M., Pattern recognition and machine learning. 2006: springer.
17. Gröger, C., F. Niedermann, and B. Mitschang. Data mining-driven manufacturing process optimization. in Proceedings of the World Congress on Engineering. 2012.
18. Kononenko, I., Machine learning for medical diagnosis: history, state of the art and perspective. Artificial Intelligence in medicine, 2001. 23(1): p. 89-109.
19. Das, S. Filters, wrappers and a boosting-based hybrid for feature selection. in ICML. 2001. Citeseer.
20. Kohavi, R. and G.H. John, Wrappers for feature subset selection. Artificial intelligence, 1997. 97(1): p. 273-324.
21. Kushmerick, N., Wrapper induction: Efficiency and expressiveness. Artificial Intelligence, 2000. 118(1): p. 15-68.
22. Pudil, P., J. Novovičová, and J. Kittler, Floating search methods in feature selection. Pattern recognition letters, 1994. 15(11): p. 1119-1125.
23. Hall, M.A. and L.A. Smith, Feature subset selection: a correlation based filter approach. 1997.
24. SAMPLE, C.D.F.A.S., correlation coefficients covering the cases (i)“The frequency dis-tribution of the values of the correlation coefficient in samples from an indefinitely large population,” Biometrika, Vol. 10, pp. 507v521, 1915. Here the method of defining the sample by the coordinates of. 1921.
25. Coifman, R.R. and M.V. Wickerhauser, Entropy-based algorithms for best basis selection. Information Theory, IEEE Transactions on, 1992. 38(2): p. 713-718.
26. Hearst, M.A., et al., Support vector machines. Intelligent Systems and their Applications, IEEE, 1998. 13(4): p. 18-28.
27. Schölkopf, B. and A. Smola, Support Vector Machines. Encyclopedia of Biostatistics, 1998.
28. Suykens, J.A. and J. Vandewalle, Least squares support vector machine classifiers. Neural processing letters, 1999. 9(3): p. 293-300.