Please use this identifier to cite or link to this item: http://hdl.handle.net/11455/96873
標題: 一個使用階層支援向量機的監督式電腦斷層影像分群方法
A Supervised Clustering Method for Medical Computed Tomography Images Using Hierarchical Support Vector Machines
作者: 林毓潔
Yu-Chieh Lin
關鍵字: 醫療影像分析
腹部斷層掃描影像
影像分割
種子式區域成長
紋理分割
機器學習法
支援向量機
medical image analysis
abdominal CT image
image segmentation, seeded region growing, texture segmentation
machine learning
support vector machine
引用: [1] D. Ziou and S. Tabbone. “Edge detection techniques-an overview,” Department of Math Information, Univ. of Sherbrooke, 1998. [2] A. Tremeau and N. Nolel, “A region growing and merging algorithm to color segmentation, Pattern Recognition,” vol. 30, no.7 pp. 1191 -1203, July. 1997. [3] Y. L. Chang and X. Li, “Adaptive Image Region-Growing,” IEEE Trans. On Image processing, vol.3, no.6, pp. 868-872, Nov. 1994. [4] D. Lin, C. Lei and S. Hung, “Computer-Aided Kidney Segmentation on Abdominal CT Images,” IEEE Information Technology in Biomedicine, vol. 10, no. 1, pp. 59-65, Jan. 2006. [5] L. Rusko, G. Bekes, G. Nemeth, andM. Fidrich, “Fully automatic liver segmentation for contrast-enhanced CT images,” in Proc. MICCAI Workshop 3-D Segment. Clinic, Grand Challenge, pp. 143-150, 2007. [6] W. Deng, W. Xiao, H. Deng and J. Liu, “MRI brain tumor segmentation with region growing method based on the gradients and variances along and inside of the boundary curve,” IEEE Trans. On 2010 3rd International Conference on Biomedical Engineering and Informatics , vol.1, pp. 393-396, 16-18 Oct. 2010. [7] T. F. Cootes, C. J. Taylor, D. H. Cooper, and J. Graham, “Active shape models—Their training and application,” Comput. Vis. Image Underst., vol. 61, no. 1, pp. 38-59, Jan. 1995. [8] T. F. Cootes, G. Edwards, and C. Taylor, “Active appearance models,” IEEE Trans. Pattern Anal. Mach. Intell., vol. 23, no. 6, pp. 681-685, Jun. 2001. [9] H. Ling, S. K. Zhou, Y.Zheng, B. Georgescu,M. Suehling, and D. Comaniciu, “Hierarchical, learning-based automatic liver segmentation,” in Proc. IEEE Comput. Soc. Conf. Comput. Vis. Pattern Recogn., pp. 1-8, 2008. [10] X. Chen, J. Udupa, U. Bagci, Y. Zhuge, and J. Yao, “Medical image segmentation by combining graph cuts and oriented active appearance models,” IEEE Trans. Image Process., vol. 21, no. 4, pp. 2035-2046, Apr. 2012. [11] J.R. Quinlan, “C4.5: Programs for Empirical Learning,” Morgan Kaufmann Publishers Inc., San Francisco, CA. USA, 1993. [12] I.J. Good, “The Estimation of Probabilities; an Essay on Modern Bayesian Methods,” M.I.T. Press, 1965. [13] R.E. Fan, P.H. Chen, C.J. Lin, “Working Set Selection Using Second Order Information for Training Support Vector Machines,” Journal of Machine Learning Research, 6, pp. 1889-1918, 2005. [14] D. Paterson, “Artificial Neural Networks,” Prentice Hall, Singapore, 1996. [15] D. I. Kosmopoulos and F. L. Tzevelekou, “Automated Pressure Ulcer Lesion Diagnosis for Telemedicine Systems,” IEEE Trans. On Engineering in Medicine and Biology Magazine, vol. 26, no. 5, Sept.-Oct. 2007. [16] F. Veredas, H. Mesa and L. Morente, “Binary Tissue Classification on Wound Images With Neural Networks and Bayesian Classifiers,” IEEE Trans. on Medical Imaging, vol. 29, no. 2, Feb. 2010.
摘要: 醫學影像分析可以幫助醫生將放射影像使用於計算機輔助診斷,並且被廣泛的使用於影像分割、病變偵測及分類。對於醫生來說,假如以人工的分式去讀取並辨認每一張影像,是非常耗時的。在本論文研究中,我們提出一個監督式的分群方法用於有效的分類其腹部斷層掃描影像,架構的主要內容為:(ㄧ)、腹部斷層掃描影像採用種子式區域成長法(Seed Region Growing, SRG)進行分割;(二)、我們將腹部斷層掃描影像分成七個部位:膽囊、肝臟、腎臟、脾臟、胃部、骨頭和其他類,我們定義器官類為膽囊、肝臟、腎臟及脾臟,而非器官類為胃部、骨頭及其他類,接著利用多階層支援向量機(Support Vector Machines, SVM)將資料做分群;(三)、由支援向量機分群的結果劃定每個部位成不同的顏色,以利辨識。由實驗結果顯示,我們所提出的方法可以自動且有效地識別腹部斷層掃描影像中的臟器,且為了評估所提方法能有效的將腹部影像做正確分類,我們使用混淆矩陣(Confusion Matrix)的方法,實際執行20張測試影像,並隨機選擇當中的10張影像作為訓練樣本(Training data),另外10張當作測試影像(Testing data),顯示所提方法在測試影像評估所提方法之效能顯示其正確率達到86%以上;回響率值也有84.8%,證明所提方法確實能有效的檢測影像中的目標器官與非器官。
Medical image analysis helps physicians in computer assisted diagnosis from radiological images. Such image analysis has been widely used for the segmentation, detection, and classification of various lesions. It is time consuming for physicians to read and identify abnormalities from the medical image manually. In this paper, a supervised clustering method is proposed to provide visual representation of organs and tissues in the CT images. The main elements of the proposed framework include: (1) the input abdominal CT image is automatically segmented in to regions by seeded region growing (SRG) method; (2) using hierarchical support vector machines (SVM) to divide abdominal CT image into seven parts: gallbladder, liver, kidneys, spleen, stomach, bones and other parts; and (3) delineate the regions into different colors result by the support vector machine (SVM) classifier. Experimental results demonstrate that our proposed method can automatically segment and recognize the organs in the abdominal CT image effectively. Furthermore, we use confusion matrix to evaluate our method. We took 20 images, then randomly chose 10 images as training data and other 10 images as testing data. The accuracy of our proposed method is up to 86% and the recall is 84.8%. The prediction shows our proposed method can effectively delineate regions which we defined.
URI: http://hdl.handle.net/11455/96873
文章公開時間: 2020-05-10
Appears in Collections:資訊科學與工程學系所

文件中的檔案:

取得全文請前往華藝線上圖書館



Items in DSpace are protected by copyright, with all rights reserved, unless otherwise indicated.