English  |  正體中文  |  简体中文  |  Items with full text/Total items : 17918/22933 (78%)
Visitors : 7435843      Online Users : 57
RC Version 7.0 © Powered By DSPACE, MIT. Enhanced by NTU Library IR team.
Scope Tips:
  • please add "double quotation mark" for query phrases to get precise results
  • please goto advance search for comprehansive author search
  • Adv. Search
    HomeLoginUploadHelpAboutAdminister Goto mobile version
    Please use this identifier to cite or link to this item: https://ir.csmu.edu.tw:8080/ir/handle/310902500/4157


    Title: 3D肝部腫瘤影像檢索系統暨輔助腫瘤分區範圍判斷系統
    A system of 3D image retrieval and judgment of partitions of the tumor located in the liver
    Authors: 鄭文斌
    Wen-Pin,Cheng
    Contributors: 中山醫學大學;健康管理學院;應用資訊科學學系碩士班;徐麗蘋
    Keywords: 相似性擷取;影像表示法;影像檢索;電腦斷層影像
    similarity retrieval;image representation;image retrieval;computer tomography image
    Date: 2011
    Issue Date: 2011-10-25T07:14:25Z (UTC)
    Abstract: 由於儲存在醫學資料庫中大量的影像資料不斷成長,有效的影像索引和檢索就變得非常重要。因此,需要發展一個疾病診斷的醫學影像檢索系統是當務之急。在這篇論文中,系統為協助診斷肝臟腫瘤和放射治療計畫的準備,提供3D影像檢索的功能,以及肝臟腫瘤分區位置判斷。在這系統中,著重在發展一個有效率且實用的方法,可以有效地檢索辨識出資料庫中相似的已知3D醫學影像病歷。此外,為了協助醫生規畫放射治療,也可以判斷腫瘤在肝臟的分區位置。
    為了有效地檢索出相似的影像,我們已經開發了一個影像表示法,它可以捕捉腫瘤的形狀、大小和位置。這個影像表示法保有影像scaling-、translation-和rotation-invariance等特性,並且這些特性對於高準確性的影像檢索系統是必要的。為了滿足不同要求的醫生,一些相似性的措施和檢索方法,也根據我們的影像表示法被提出。最後,基於我們的影像表示法也提供肝臟腫瘤的分區位置判斷。實驗結果顯示,系統在於輔助醫生診斷肝腫瘤和放射治療規畫方面都有良好的表現。
    Because the amount of pictorial information stored in medical databases is growing, efficient image indexing and retrieval becomes very important. Therefore, the need to develop a medical image retrieval system for disease diagnosis is urgent. In this thesis, a system for assisting in diagnosing the liver tumors and planning the corresponding radiation treatment is proposed. The proposed system provides the capabilities of 3D image retrieval as well as judging in which partitions of the liver the tumor is located. In the proposed system, the emphasis is on the development of an efficient and practical database for recognizing and retrieving similar patterns with known diagnoses in 3D medical images in an efficient manner. Furthermore, in order to assist physician in planning the radiation treatment, it can also judge the partitions of the liver in which the tumor is located.
    To retrieve similar images efficiently, we have developed an image representation which can capture the shape, size and location of the tumor. The image representation has the properties of image scaling-, translation- and rotation-invariance, and these properties are necessary for an image retrieval system which works to a high degree of accuracy. To satisfy the different requirements of physicians, some similarity measures and a retrieval method based on our image representation approach are also proposed. Finally, a method based on our image representation to judge the partitions of liver where the tumor is located is also provided. Experiment results showed that the system has a good performance in terms of assisting physician in diagnosing the liver tumor and planning the radiation treatment.
    URI: https://ir.csmu.edu.tw:8080/ir/handle/310902500/4157
    Appears in Collections:[ Department of Medical Informatics (including MS Program) ] Electronic Theses and Dissertation

    Files in This Item:

    File Description SizeFormat
    index.html碩士論文0KbHTML697View/Open


    SFX Query

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


    DSpace Software Copyright © 2002-2004  MIT &  Hewlett-Packard  /   Enhanced by   NTU Library IR team Copyright ©   - Feedback