English  |  正體中文  |  简体中文  |  Items with full text/Total items : 27308/39152
Visitors : 2448611      Online Users : 132
RC Version 4.0 © Powered By DSPACE, MIT. Enhanced by NTU Library IR team.
Scope Adv. Search
LoginUploadHelpAboutAdminister

Please use this identifier to cite or link to this item: http://ntour.ntou.edu.tw:8080/ir/handle/987654321/49385

Title: 電腦斷層掃描影像之自動肝腫瘤切割及其紋理為主的預後分析
Automatic Liver Tumor Segmentation on CT Scans and Its Application to Texture-based Prognostic Analysis
Authors: Lee, Shang-Hung
李尚紘
Contributors: NTOU:Department of Computer Science and Engineering
國立臺灣海洋大學:資訊工程學系
Keywords: 電腦輔助分析系統;肝腫瘤切割;CT掃描影像;紋理特徵;邏輯回歸分析;預後分析
Computer-aided analysis system;tumor Segmentation;CT image;texture features;logistic regression;survival prediction
Date: 2017
Issue Date: 2018-08-22T06:57:11Z
Abstract: 在本論文,提出基於電腦斷層掃描影像(Computed Tomography Scans; CT Scans)的肝腫瘤紋理特徵分析及預後分析方法,透過區域成長方法(Region Growing)影像切割方法,定位出肝臟的區塊,再利用自動影像切割方法GrabCut, 切割出肝臟區域的腫瘤。本系統之特徵點選取方法分兩部分:使用尺度不變特徵轉換(Scale-invariant Feature Transform; SIFT)演算法選取影像中肝臟區塊內具有代表性的特徵點;肝腫瘤區域依隨機方式選取一定數量的特徵點,以每個特徵點為中心從影像中定一感興趣區塊(Regions of Interest; ROI),接下來本論文使用灰度共生矩陣(Gray-level Co-occurrence Matrix, GLCM)表示ROI的紋理特徵。為了進一步提升肝腫瘤的紋理特徵的解析能力,我們使用分群演算法將每一張影像的ROI紋理特徵分為4群及其代表紋理特徵,標示每張影像的腫瘤群代表特徵為腫瘤紋理特徵,及肝臟群的代表特徵為肝紋理特徵用以製作訓練支援向量機(Support Vector Machine, SVM)分類器的訓練樣本,得到紋理特徵為主的肝腫瘤分類器。在測試階段,依相同的特徵處理方式,偵測腫瘤位置及其紋理特徵,輸入到SVM分類器判斷該區域是否確定為腫瘤紋理特徵。 最後,在訓練階段,本論文蒐集所有的腫瘤紋理特徵,及相關病歷資料,利用邏輯回歸方法(Logistic Regression)建立預後分析模型。在測試(診斷)階段,輸入腫瘤紋理特徵到預後分析模型,預測各種治療方式的存活機率,實驗結果證實本論文提出的預後分析方法的有效性。
This thesis presents an approach to extracting discriminative tumor texture features in computed tomography (CT) scans, which are used to combine with patient treatment records for survival prediction. The liver region is first located by using a region growing image segmentation method. Next, we use GrabCut method to segment the tumors in the liver region. Two sets of feature points are detected in the system: (1) Scale-invariant Feature Transform (SIFT) feature points are detected in the liver region; (2) randomly sampling several points in the liver tumor region as tumor feature points. Using each feature point as the center of a region of interest (ROI), this thesis computes Gray-level Co-occurrence Matrix (GLCM) which is further used to derive the texture features of the ROI. Multiple ROIs and thus multiple texture feature vectors are derived in an input CT image. These textures are collected and clustered into four clusters, where each of them is represented by a representative texture feature vector. To further enhance the discriminative powder of the texture features, for each CT image, we select two representative texture feature vectors which are from the two clusters with the highest probability belonging to the tumor region and the liver region, respectively. The resulting tumor texture (liver) feature vector is then labeled as a positive (negative) example in order to train a tumor Support Vector Machine (SVM) classifier. In the diagnosis stage, the tumor SVM classifies an input texture feature vector and the classification result detects the liver tumor location in a CT image. The detected tumor texture feature vector of a CT image that belongs to a patient is then associate with the treatment record of the patient in order to construct a training dataset for learning survival prediction model using logistic regression. In diagnosis stage, to input a tumor texture feature vector and the possible treatments to the survival prediction model, the system computes the survival probabilities and generates a treatment prediction report, which suggests the most suitable treatment for the corresponding patient. Experimental results show that the proposed method gives good performance in terms of survival prediction.
URI: http://ethesys.lib.ntou.edu.tw/cgi-bin/gs32/gsweb.cgi?o=dstdcdr&s=G0010257044.id
http://ntour.ntou.edu.tw:8080/ir/handle/987654321/49385
Appears in Collections:[資訊工程學系] 博碩士論文

Files in This Item:

File Description SizeFormat
index.html0KbHTML17View/Open


All items in NTOUR are protected by copyright, with all rights reserved.

 


著作權政策宣告: 本網站之內容為國立臺灣海洋大學所收錄之機構典藏,無償提供學術研究與公眾教育等公益性使用,請合理使用本網站之內容,以尊重著作權人之權益。
網站維護: 海大圖資處 圖書系統組
DSpace Software Copyright © 2002-2004  MIT &  Hewlett-Packard  /   Enhanced by   NTU Library IR team Copyright ©   - Feedback