LesionBrain: An Online Tool for White Matter Lesion Segmentation

被引：22

作者：

Coupe, Pierrick ^{[1
,2
]}

Tourdias, Thomas ^{[3
,4
]}

Linck, Pierre ^{[4
,5
]}

Romero, Jose E. ^{[6
]}

Manjon, Jose V. ^{[6
]}

机构：

[1] LaBRI, CNRS, UMR 5800, PICTURA, F-33400 Talence, France

[2] Univ Bordeaux, LaBRI, UMR 5800, PICTURA, F-33400 Talence, France

[3] INSERM, U1215, Neuroctr Magendie, F-33077 Bordeaux, France

[4] Univ Bordeaux, F-33000 Bordeaux, France

[5] CHU Bordeaux, Serv Neurol & Neuroradiol, Bordeaux, France

[6] Univ Politecn Valencia, Inst Aplicac Tecnol Informac & Comunicac Avanzada, Camino Vera S-N, E-46022 Valencia, Spain

来源：

PATCH-BASED TECHNIQUES IN MEDICAL IMAGING, PATCH-MI 2018 | 2018年 / 11075卷

关键词：

White matter lesion segmentation; Patch-based segmentation; Service as a software; NONLOCAL MEANS; BRAIN; HIPPOCAMPUS;

D O I：

10.1007/978-3-030-00500-9_11

中图分类号：

TP301 [理论、方法];

学科分类号：

081202 ;

摘要：

In this paper, we present a new tool for white matter lesion segmentation called lesionBrain. Our method is based on a 3-stage strategy including multimodal patch-based segmentation, patch-based regularization of probability map and patch-based error correction using an ensemble of shallow neural networks. Its robustness and accuracy have been evaluated on the MSSEG challenge 2016 datasets. During our validation, the performance obtained by lesionBrain was competitive compared to recent deep learning methods. Moreover, lesionBrain proposes automatic lesion categorization according to location. Finally, complementary information on gray matter atrophy is included in the generated report. LesionBrain follows a software as a service model in full open access.

引用

页码：95 / 103

页数：9

共 26 条

[1]

[Anonymous], 2016, MSSEG CHALL P MULT S

[2] A reproducible evaluation of ANTs similarity metric performance in brain image registration [J].