Please use this identifier to cite or link to this item: http://repositorio.unicamp.br/jspui/handle/REPOSIP/243535
Type: Artigo
Title: Medical image segmentation using object atlas versus object cloud models
Author: Phellan, Renzo
Falcão, Alexandre X.
Udupa, Jayaram K.
Abstract: Medical image segmentation is crucial for quantitative organ analysis and surgical planning. Since interactive segmentation is not practical in a production-mode clinical setting, automatic methods based on 3D object appearance models have been proposed. Among them, approaches based on object atlas are the most actively investigated. A key drawback of these approaches is that they require a time-costly image registration process to build and deploy the atlas. Object cloud models (OCM) have been introduced to avoid registration, considerably speeding up the whole process, but they have not been compared to object atlas models (OAM). The present paper fills this gap by presenting a comparative analysis of the two approaches in the task of individually segmenting nine anatomical structures of the human body. Our results indicate that OCM achieve a statistically significant better accuracy for seven anatomical structures, in terms of Dice Similarity Coefficient and Average Symmetric Surface Distance.
Medical image segmentation is crucial for quantitative organ analysis and surgical planning. Since interactive segmentation is not practical in a production-mode clinical setting, automatic methods based on 3D object appearance models have been proposed.
Subject: Sistemas fuzzy
Processamento de imagens
Reconhecimento de padrões
Segmentação de imagens médicas
Country: Estados Unidos
Editor: International Society for Optical Engineering
Citation: Medical Image Segmentation Using Object Atlas Versus Object Cloud Models. Spie-int Soc Optical Engineering, v. 9415, p. 2015.
Rights: aberto
Fechado
Identifier DOI: 10.1117/12.2077607
Address: https://spie.org/Publications/Proceedings/Paper/10.1117/12.2077607
Date Issue: 2015
Appears in Collections:IC - Artigos e Outros Documentos

Files in This Item:
File SizeFormat 
000354365300055.pdf564.82 kBAdobe PDFView/Open


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