Cargando…

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...

Descripción completa

Detalles Bibliográficos
Autores principales: Ashtari, Pooya, Barile, Berardino, Van Huffel, Sabine, Sappey-Marinier, Dominique
Formato: Online Artículo Texto
Lenguaje:English
Publicado: Frontiers Media S.A. 2022
Materias:
Acceso en línea:https://www.ncbi.nlm.nih.gov/pmc/articles/PMC9646406/
https://www.ncbi.nlm.nih.gov/pubmed/36389254
http://dx.doi.org/10.3389/fnins.2022.975862
_version_ 1784827159304470528
author Ashtari, Pooya
Barile, Berardino
Van Huffel, Sabine
Sappey-Marinier, Dominique
author_facet Ashtari, Pooya
Barile, Berardino
Van Huffel, Sabine
Sappey-Marinier, Dominique
author_sort Ashtari, Pooya
collection PubMed
description 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.
format Online
Article
Text
id pubmed-9646406
institution National Center for Biotechnology Information
language English
publishDate 2022
publisher Frontiers Media S.A.
record_format MEDLINE/PubMed
spelling pubmed-96464062022-11-15 New multiple sclerosis lesion segmentation and detection using pre-activation U-Net Ashtari, Pooya Barile, Berardino Van Huffel, Sabine Sappey-Marinier, Dominique Front Neurosci Neuroscience 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. Frontiers Media S.A. 2022-10-26 /pmc/articles/PMC9646406/ /pubmed/36389254 http://dx.doi.org/10.3389/fnins.2022.975862 Text en Copyright © 2022 Ashtari, Barile, Van Huffel and Sappey-Marinier. https://creativecommons.org/licenses/by/4.0/This is an open-access article distributed under the terms of the Creative Commons Attribution License (CC BY). The use, distribution or reproduction in other forums is permitted, provided the original author(s) and the copyright owner(s) are credited and that the original publication in this journal is cited, in accordance with accepted academic practice. No use, distribution or reproduction is permitted which does not comply with these terms.
spellingShingle Neuroscience
Ashtari, Pooya
Barile, Berardino
Van Huffel, Sabine
Sappey-Marinier, Dominique
New multiple sclerosis lesion segmentation and detection using pre-activation U-Net
title New multiple sclerosis lesion segmentation and detection using pre-activation U-Net
title_full New multiple sclerosis lesion segmentation and detection using pre-activation U-Net
title_fullStr New multiple sclerosis lesion segmentation and detection using pre-activation U-Net
title_full_unstemmed New multiple sclerosis lesion segmentation and detection using pre-activation U-Net
title_short New multiple sclerosis lesion segmentation and detection using pre-activation U-Net
title_sort new multiple sclerosis lesion segmentation and detection using pre-activation u-net
topic Neuroscience
url https://www.ncbi.nlm.nih.gov/pmc/articles/PMC9646406/
https://www.ncbi.nlm.nih.gov/pubmed/36389254
http://dx.doi.org/10.3389/fnins.2022.975862
work_keys_str_mv AT ashtaripooya newmultiplesclerosislesionsegmentationanddetectionusingpreactivationunet
AT barileberardino newmultiplesclerosislesionsegmentationanddetectionusingpreactivationunet
AT vanhuffelsabine newmultiplesclerosislesionsegmentationanddetectionusingpreactivationunet
AT sappeymarinierdominique newmultiplesclerosislesionsegmentationanddetectionusingpreactivationunet