{"title":"3D visualization of fuzzy shapes using multichannel MR images","authors":"S. Kumamura, N. Niki, Hiromu Nishitani, H. Sato","doi":"10.1109/NSSMIC.1993.373570","DOIUrl":null,"url":null,"abstract":"The authors describe a method for an accurate extraction image of cerebral soft tissues from MR images in order to realize accurate diagnosis. With MRI it is possible to observe different soft tissues images of an anatomical section using different pulse sequences. However, it is difficult to 3D visualize one soft tissue with fuzzy shapes from MR images. To avoid this difficulty the authors used a combination of multichannel MR images, a fuzzy c-means clustering, and an object connectivity-check. Using volume rendering the authors could visualize a 3D extraction image of the brain and tumor.<<ETX>>","PeriodicalId":287813,"journal":{"name":"1993 IEEE Conference Record Nuclear Science Symposium and Medical Imaging Conference","volume":"18 1","pages":"0"},"PeriodicalIF":0.0000,"publicationDate":"1993-10-31","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":"0","resultStr":null,"platform":"Semanticscholar","paperid":null,"PeriodicalName":"1993 IEEE Conference Record Nuclear Science Symposium and Medical Imaging Conference","FirstCategoryId":"1085","ListUrlMain":"https://doi.org/10.1109/NSSMIC.1993.373570","RegionNum":0,"RegionCategory":null,"ArticlePicture":[],"TitleCN":null,"AbstractTextCN":null,"PMCID":null,"EPubDate":"","PubModel":"","JCR":"","JCRName":"","Score":null,"Total":0}
引用次数: 0
Abstract
The authors describe a method for an accurate extraction image of cerebral soft tissues from MR images in order to realize accurate diagnosis. With MRI it is possible to observe different soft tissues images of an anatomical section using different pulse sequences. However, it is difficult to 3D visualize one soft tissue with fuzzy shapes from MR images. To avoid this difficulty the authors used a combination of multichannel MR images, a fuzzy c-means clustering, and an object connectivity-check. Using volume rendering the authors could visualize a 3D extraction image of the brain and tumor.<>