透過核磁共振影像（MRI）能夠讓醫師得到腦部組織的病變相關資訊，做診斷與治療，隨著科技的進步，在醫學臨床上越來越多結合電腦輔助量測與診斷，而利用切割演算法準確地切割出所需的病灶區域，便能使醫師減少判斷病灶區域位置的時間。
本研究目的是希望藉由等位函數為基之主動輪廓法(Active Contours using Level Sets, ACLS)切割出腫瘤(Tumor)與水腫區域(Edema)之邊界(Boundary)，在執行切割動作之前，利用影像前處理技術N3將影像去除非均一性(Non-homogeneity Removal)，並探討有無去除非均一性影像對於切割績效之影響；而ACLS演算法之切割(Segmentation)效果會受到演算法中參數組合影響，本研究應用格子點參數搜尋演算法(Grid Search)搜尋最佳參數組合，來探討ACLS切割演算法有無進行參數優化對於切割績效之影響，因此本研究中有四種實驗組合分別為(1)無去除非均一性無參數優化，(2)無去除非均一性有參數優化，(3)有去除非均一性無參數優化，(4)有去除非均一性有參數優化；將四種組合經ACLS切割演算法後，利用Jaccard Similarity衡量前述四種組合之切割績效，透過變異數分析(Analysis of Variance, ANOVA)計算各因子對於影像切割結果是否有顯著差異，隨後進行成對樣本T檢定((Paired-Samples T Test)來檢測各組合之顯著差異關係。
變異數分析(Analysis of Variance, ANOVA)結果顯示，在腫瘤切割績效中，有無去除非均一性對於切割績效有顯著差異(Significance Difference)，而有無執行參數優化之切割績效則無顯著差異，且兩因子交互作用(Interaction)效果未達顯著差異；在水腫切割績效中，有無去除非均一性與有無參數優化皆無顯著差異，而兩因子交互作用效果也未達顯著差異。
成對樣本T檢定分析結果顯示，對於腫瘤區域之切割，去除非均一性且參數優化於測試組資料(Test data set)之Jaccard Similarity平均值為0.7899，切割績效為最佳且顯著優於其他組合；對於水腫區域之切割，去除非均一性且參數優化於測試組資料(Test data set) 之Jaccard Similarity平均值為0.7604，切割績效亦為最佳且亦顯著優於其他組合。

MRI can provide information on pathological changes in brain tissue to the doctors for diagnosis and treatment. With the advancement of technology, clinical practice has integrated computer-aided measurement and diagnosis, and the cutting algorithm can be used to cut out the required focal area accurately, in order to effectively diagnose the focal area.
This study used Active Contours using Level Sets (ACLS) to cut out the boundary of tumor and edema. Before the segmentation, the image preprocessing technique N3 was used for image non-homogeneity removal, and the influence of non-homogeneity removal on segmentation performance was discussed. The segmentation effect of ACLS algorithm was influenced by the parameter combinations in the algorithm. In this study, Grid Search was used to search for the optimum parameter combination, so as to discuss the influence of parameter optimization of ACLS on the segmentation performance. Therefore, there were four experimental combinations in this study: (1) without non-homogeneity removal without parameter optimization, (2) without non-homogeneity removal with parameter optimization, (3) with non-homogeneity removal without parameter optimization and (4) with non-homogeneity removal with parameter optimization. The four combinations were processed by ACLS algorithm, and then the Jaccard Similarity was used to measure the segmentation performance of the four combinations. The Analysis of Variance (ANOVA) was used to calculate whether various factors resulted in significance difference in image segmentation, and then the paired-samples t test was conducted to test the significance difference among various combinations.
The result of ANOVA showed that in the tumor segmentation performance, the non-homogeneity removal results in significance difference in segmentation performance. There was no significance difference in the segmentation performance without parameter optimization, and the interaction between two factors did not reached significance difference. In the edema segmentation performance, there was no significance difference whether or not there were non-homogeneity removal and parameter optimization, and the interaction between two factors had not reached significance difference.
The result of paired-sample t test found that for the segmentation of tumor area, the Jaccard Similarity average value of non-homogeneity removal and parameter optimization in test data set was 0.7899. The segmentation performance was the best and was significantly better than the other combinations. For the segmentation of edema, the Jaccard Similarity average value of non-homogeneity removal and parameter optimization in test data set was 0.7604. The segmentation performance was also the best and was significantly better than the other combinations.

中文摘要 i
ABSTRACT iii
目錄 v
圖目錄 vii
表目錄 ix
第一章 緒論 1
1.1 研究背景與動機 1
1.2 研究範圍與目的 2
1.3 研究方法 3
第二章 文獻探討 5
2.1影像前處理 5
2.1.1非均一性模型 6
2.2影像切割演算法 9
2.2.1統計導向 9
2.2.2邊界導向 10
2.2.3區域導向 11
2.2.4混合模型 13
2.2.5影像切割演算法之優缺點比較 19
2.3啟發式演算法相關研究 20
2.4績效衡量 24
第三章 研究方法 26
3.1 研究架構 26
3.2 影像前處理 28
3.3 定義參數 28
3.4 格子點演算法搜尋最佳參數 30
3.5 ACLS演算法切割影像 31
3.6 績效衡量 38
第四章 實驗結果與分析 40
4.1 實驗樣本 40
4.2 實驗設置與執行 41
4.3 參數選擇 42
4.4 實驗結果 42
4.4.1變異數分析結果 43
4.4.2成對樣本T檢定分析結果 50
第五章 結論與未來研究方向 60
5.1 結論 60
5.2 未來研究方向 62
參考文獻 63

[01]格子點搜尋演算法 http://web.ntpu.edu.tw/~ccw/statmath/M_optimal.pdf
[02]呂世僑，2012，磁振腦瘤影像之強化、邊界檢測及參數優化，國立雲林科技大學工業管理所碩士論文
[03]吳采蓉，2010，應用田口方法於紫外光固化快速原型製程之參數優化，國立彰化師範大學機電工程學系機電工程碩士班碩士論
[04]黃一展，2005，磁振影像腦瘤分割與三維重建，大葉大學工業工程與科技管理所碩士論文
[05]楊淯盛，2008，左心室磁振影像心肌內外膜邊界檢測與參數優化，國立雲林科技大學工業管理所碩士論文
[06]Chan, T. F. and L. A. Vese, 2001, “Active Contours Without Edges”, IEEE Transactions on Image Processing, Vol. 10, No. 2, pp. 266-277.
[07]Chunming Li, 2005, “Level Set Evolution without Re-initialization: A New Variational Formulation”, IEEE Computer Society Conference on Computer Vision and Pattern Recognition, pp. 430–436.
[08]Christopher Conlin, 2012, “Implementation of a non-parametric non-uniformity normalization algorithm with H regularization for correction of MRI shading artifacts.”
[09]C. L. Huang, H. C. Liao, M. C. Chen, 2008, “Prediction model building and feature selection with support vector machines in breast cancer diagnosis”, Expert Systems with Applications, Vol. 34, pp. 578-587.
[10]Dempster A.P., N.M Laird and D.B. Rubin, 1977, “Maximum Likelihood from Incomplete Data via the EM Algorithm”, J. Royal Statistical Soc., Ser. B., Vol. 39, No 1, pp. 1-38.
[11]J. Hwang, J. Kim, Y. Han and H. W. Park, 2011, “An automatic cerebellum extraction method in T1-weighted brain MR images using an active contour model with a shape prior”, Magnetic Resonance Imaging, Vol. 29, pp.1014-1022
[12]Jainy S., Vinod K., Indra G., 2012, “A novel content-based active contour model for brain tumor segmentation”, Image and Vision Computing, Vol. 30, pp.694-715.
[13]John G. Sled May, 1997, “A non-parametric Method for Automatic Correction of Intensity Non-uniformity in MRI Data.” Department of Biomedical Engineering, McGill University.
[14]Li , X., Rooney, W. D., Varallyay , C. G., Gahramanov, S., Muldoon, L. L., Goodman, J. A., Tagge, I. J., Selzer, A. H., Pike, M. M., Neuwelt, E. A., Springer, Jr. C. S., 2010, "Dynamic-contrast-enhanced-MRI with Extravasating Contrast Reagent: Rat cerebral Glioma Blood Volume Determination" , Journal of Magnetic Resonance, Vol.206, No. 2, pp. 190-199.
[15]Lin, C. J., Chang, C. C., Hsu, C. W., “A Practical Guide to Support Vector Classification”,2010, Department of Computer Science National Taiwan University,Taipei 106, Taiwan
[16]Lin, C. J., Chung, C. C. and Hsu, C. W, 2003, "A Practical Guide to Support Vector Classification", Available at: http://www.csie.ntu.edu.tw/~cjlin/papers/guide/guide.pdf.
[17]Mu, T. and Nandi, A.K., 2005, “Detection of breast cancer using v-SVM and RBF networks with self-organization selection of centers”, Third IEEE International Seminar on Medical Applications of Signal Processing.
[18]Osher S. and Sethian J. A., 1988, “Fronts Propagating with Curvature Dependent Speed: Algorithms Based on Hamilton-Jacobi Formulation”, Journal of Computational Physics, Vol. 79, pp. 12-49
[19]Paul A. Y., Joseph P., 2006, Heather C. H., “User-guided 3D active contour segmentation of anatomical structures: Significantly improved efficiency and reliability”, NeuroImage, Vol. 31, pp.1116–1128.
[20]Rafael C. G., Richard E. W., and Steven L. E., 2002, “Digital Image Using MATLAB Processing”, 繆紹綱譯，東華出版社
[21]S. Taheri, S.H. Ong, V.F.H. Chong, 2010, “Level-set Segmentation of Brain Tumors Using a Threshold-based Speed Function”, Image and Vision Computing, Vol. 28, pp.26-37.
[22]Umberto Amato, Michele Larobina, Anestis Antoniadis, Bruno Alfano, 2003, “Segmentation of magnetic resonance brain images through discriminant analysis”, Journal of Neuroscience Methods, Vol. 131, pp.65-74.