本研究提供一個有別於現今的方法來討論被診斷有肺腫瘤的病人的病況。目前，病理檢測及臨床分析是主要檢測病人腫瘤情況的方法，而這些方法均需透過如切片、藥物檢測等等的方法對於取得的樣本進行分析。對於這類侵入式的檢測，不僅僅等待結果耗時，有時更會造成預期之外的感染，對病人的病情可能有不良的影響。
以現今的科技技術，科學家能夠輕易的描繪出不同種類的影像圖形，而這項技術也被應用在醫療方面，因此有了醫療影像的概念，而病人體內的狀況因此可以被簡單地了解。另一方面，影像處理的技術及資料處理的方式在現今的科學研究已有相當的發展，透過結合兩者的方式更是提供多種可能性。本論文即是結合兩者特色，應用在腫瘤病情上的描述。
本論文中提供一個方始來描述病人腫瘤的情況，透過結合影像處理及資料處理的方使建立一步同於傳統的方式來預測病人的生存情況及腫瘤的分類。

This study proposes a way to analyze patients’ condition of lung tumor which different from the present examination by pathological and clinical methods. In the medical technique of examination tumor today is mainly based on testing the section of tumors which should accompany with invading into patients’ body. The processes of examination usually take time for result; besides, the unexpected harms of patients, such as infection, probability happen.
There are countless methods to generate image today, and the medical image could be operated in similar way to briefly describe patients’ situation of body inside without invasion of body; the image processing and data mining skill, on the other hand, have been well developed by engineers and scientists. The combination of image processing and data mining is well applied in several fields of researches, and this study gives the possibility of combining these skill to analyze tumors.
The way to analyze tumor situation in this studying is processed by combining image processing and data mining to generate “rules” to predict and class stage of tumor in patients’ survive possibility and stage of tumor.

[1] M.A. PAWITRA, S. SOMPHOB, “A novel Standardized Uptake Value (SUV) calculation of PET DICOM files using MATLAB”, NEW ASPECTS of APPLIED INFORMATICS, BIOMEDICAL ELECTRONICS & INFORMATICS and COMMUNICATIONS, pp.413-416, 2010
[2] M.T. Suzuki, Y. Yaginuma, H. Kodama, “A Texture Energy Measurement Technique for 3D Volumetric Data”, Proceedings of the 2009 IEEE International Conference on Systems, Man, and Cybernetics, pp. 3779- 3785, 2009
[3] X. Tang, “Texture Information in Run-Length Matrices”, IEEE TRANSACTIONS ON IMAGE PROCESSING, VOL. 7, NO. 11, pp. 1602-1609, 1998
[4] A. Eleyan, H. Demirel, “Co-Occurrence based Statistical Approach for Face Recognition”, IS-SCI-IEEE, pp. 611-615, 2009
[5] Z.L. Hu, H. Zheng, J.B. Gui, ”A Fast Reading and Processing Method of Batch Human CT Image Data”, ISECS International Colloquium on Computing, Communication, Control, and Management, pp. 202-204, 2009
[6] E.L. Chen, P.C. Chung, “An Automatic Diagnostic System for CT Liver Image Classification”, IEEE TRANSACTIONS ON BIOMEDICAL ENGINEERING, VOL. 45, NO. 6, pp. 783-794, 1998
[7] Rafael C. Gonzalez, Richard E. Woods, Steven L. Eddins, Digital Image Processing using MATLAB, Mc Graw Hill, 2011
[8] Please refer to the web site below for classifying tumor (http://blog.udn.com/curecancer99/3673497)
[9] Please refer to the WEKA Home Page web site (http://en.wikipedia.org/wiki/Weka_(machine_learning)
[10] Please refer to web site, Wikipedia, for machine learning (http://en.wikipedia.org/wiki/Weka_(machine_learning))