New multiple sclerosis lesion segmentation and detection using pre-activation U-Net

Automated segmentation of new multiple sclerosis (MS) lesions in 3D MRI data is an essential prerequisite for monitoring and quantifying MS progression. Manual delineation of such lesions is time-consuming and expensive, especially because raters need to deal with 3D images and several modalities. I...

Full description

Saved in:
Bibliographic Details
Published in:Frontiers in neuroscience Vol. 16; p. 975862
Main Authors: Ashtari, Pooya, Barile, Berardino, Van Huffel, Sabine, Sappey-Marinier, Dominique
Format: Journal Article
Language:English
Published: Lausanne Frontiers Research Foundation 26.10.2022
Frontiers
Frontiers Media S.A
Subjects:
Brain cancer
Computer Science
Experiments
Lesions
Medical Imaging
Multiple sclerosis
Neural networks
Neuroscience
new lesions
pre-activation
Segmentation
Semantics
U-Net
ISSN:1662-453X, 1662-4548, 1662-453X
Online Access:Get full text
Tags: Add Tag
No Tags, Be the first to tag this record!
Description
Summary:Automated segmentation of new multiple sclerosis (MS) lesions in 3D MRI data is an essential prerequisite for monitoring and quantifying MS progression. Manual delineation of such lesions is time-consuming and expensive, especially because raters need to deal with 3D images and several modalities. In this paper, we propose Pre-U-Net, a 3D encoder-decoder architecture with pre-activation residual blocks, for the segmentation and detection of new MS lesions. Due to the limited training set and the class imbalance problem, we apply intensive data augmentation and use deep supervision to train our models effectively. Following the same U-shaped architecture but different blocks, Pre-U-Net outperforms U-Net and Res-U-Net on the MSSEG-2 dataset, achieving a Dice score of 40.3% on new lesion segmentation and an F 1 score of 48.1% on new lesion detection. The codes and trained models are publicly available at https://github.com/pashtari/xunet .
Bibliography:ObjectType-Article-1
SourceType-Scholarly Journals-1
ObjectType-Feature-2
content type line 14
content type line 23
This article was submitted to Brain Imaging Methods, a section of the journal Frontiers in Neuroscience
Edited by: Michel Dojat, Institut National de la Santé et de la Recherche Médicale (INSERM), France
Reviewed by: Shen Zhao, Sun Yat-sen University, China; Cédric Meurée, Inria Rennes—Bretagne Atlantique Research Centre, France
ISSN:1662-453X
1662-4548
1662-453X
DOI:10.3389/fnins.2022.975862