Full-Text Search:
Home|Journal Papers|About CNKI|User Service|FAQ|Contact Us|中文
《Chinese Journal of Medical Imaging》 2010-06
Add to Favorite Get Latest Update

A Study of Medical Image Segmentation Based on Human Interactive Region Merges of Watershed

Lü,Xiaoqi 2 Fan,Yunzhou Gu,Yu Liu,Jing School of Information Engineering,Inner Mongolia University of Science and Technology,Baotou,Inner Mongolia 014010  
Purpose To solve the problems of over-segmentation and improve the merger method in the watershed algorithm.Materials and Methods The main measure was to implement the third partial merger based on the former two mergers and to keep the region of interest using human-machine interactive methods.Results Using the improved method,the problems of over-segmentation were well restrained.In addition,the small regions with pathological changes were well segmented.Conclusions The method of human interaction is better than the traditional watershed approach.
【Fund】: 国家自然科学基金(60761002):基于非刚性配准的多模医学图像融合技术研究
【CateGory Index】: R445
Download(CAJ format) Download(PDF format)
CAJViewer7.0 supports all the CNKI file formats; AdobeReader only supports the PDF format.
©2006 Tsinghua Tongfang Knowledge Network Technology Co., Ltd.(Beijing)(TTKN) All rights reserved