Automated tissue segmentation of MR brain images in the presence of white matter lesions
详细信息 查看全文
- 作者：Sergi Valverde ; a ; svalverde@eia.udg.edu" class="auth_mail" title="E-mail the corresponding author ; Arnau Olivera ; Eloy Rouraa ; Sandra Gonzá ; lez-Villà ; a ; Deborah Paretob ; Joan C. Vilanovac ; Lluí ; s Ramió ; -Torrentà ; d ; À ; lex Rovirab ; Xavier Lladó ; a
- 关键词：Brain ; MRI ; Multiple sclerosis ; Automatic tissue segmentation
- 刊名：Medical Image Analysis
- 出版年：2017
- 出版时间：January 2017
- 年：2017
- 卷：35
- 期：Complete
- 页码：446-457
- 全文大小：3117 K
文摘
- •
We propose an automated brain tissue segmentation method for MS images with lesions.
- •
The approach relies only on T1-w to segment brain tissue but FLAIR is recommended.
- •
We evaluate its accuracy with both the MRBrainS13 challenge and MS data.
- •
Our approach was the best unsupervised ranked method of the challenge (7th position / 31).
- •
With MS data, the performance was similar to or better than the state-of-the-art.