Cargando…
Longitudinal detection of new MS lesions using deep learning
The detection of new multiple sclerosis (MS) lesions is an important marker of the evolution of the disease. The applicability of learning-based methods could automate this task efficiently. However, the lack of annotated longitudinal data with new-appearing lesions is a limiting factor for the trai...
Autores principales: | , , , |
---|---|
Formato: | Online Artículo Texto |
Lenguaje: | English |
Publicado: |
Frontiers Media S.A.
2022
|
Materias: | |
Acceso en línea: | https://www.ncbi.nlm.nih.gov/pmc/articles/PMC10406205/ https://www.ncbi.nlm.nih.gov/pubmed/37555158 http://dx.doi.org/10.3389/fnimg.2022.948235 |
_version_ | 1785085699540647936 |
---|---|
author | Kamraoui, Reda Abdellah Mansencal, Boris Manjon, José V. Coupé, Pierrick |
author_facet | Kamraoui, Reda Abdellah Mansencal, Boris Manjon, José V. Coupé, Pierrick |
author_sort | Kamraoui, Reda Abdellah |
collection | PubMed |
description | The detection of new multiple sclerosis (MS) lesions is an important marker of the evolution of the disease. The applicability of learning-based methods could automate this task efficiently. However, the lack of annotated longitudinal data with new-appearing lesions is a limiting factor for the training of robust and generalizing models. In this study, we describe a deep-learning-based pipeline addressing the challenging task of detecting and segmenting new MS lesions. First, we propose to use transfer-learning from a model trained on a segmentation task using single time-points. Therefore, we exploit knowledge from an easier task and for which more annotated datasets are available. Second, we propose a data synthesis strategy to generate realistic longitudinal time-points with new lesions using single time-point scans. In this way, we pretrain our detection model on large synthetic annotated datasets. Finally, we use a data-augmentation technique designed to simulate data diversity in MRI. By doing that, we increase the size of the available small annotated longitudinal datasets. Our ablation study showed that each contribution lead to an enhancement of the segmentation accuracy. Using the proposed pipeline, we obtained the best score for the segmentation and the detection of new MS lesions in the MSSEG2 MICCAI challenge. |
format | Online Article Text |
id | pubmed-10406205 |
institution | National Center for Biotechnology Information |
language | English |
publishDate | 2022 |
publisher | Frontiers Media S.A. |
record_format | MEDLINE/PubMed |
spelling | pubmed-104062052023-08-08 Longitudinal detection of new MS lesions using deep learning Kamraoui, Reda Abdellah Mansencal, Boris Manjon, José V. Coupé, Pierrick Front Neuroimaging Neuroimaging The detection of new multiple sclerosis (MS) lesions is an important marker of the evolution of the disease. The applicability of learning-based methods could automate this task efficiently. However, the lack of annotated longitudinal data with new-appearing lesions is a limiting factor for the training of robust and generalizing models. In this study, we describe a deep-learning-based pipeline addressing the challenging task of detecting and segmenting new MS lesions. First, we propose to use transfer-learning from a model trained on a segmentation task using single time-points. Therefore, we exploit knowledge from an easier task and for which more annotated datasets are available. Second, we propose a data synthesis strategy to generate realistic longitudinal time-points with new lesions using single time-point scans. In this way, we pretrain our detection model on large synthetic annotated datasets. Finally, we use a data-augmentation technique designed to simulate data diversity in MRI. By doing that, we increase the size of the available small annotated longitudinal datasets. Our ablation study showed that each contribution lead to an enhancement of the segmentation accuracy. Using the proposed pipeline, we obtained the best score for the segmentation and the detection of new MS lesions in the MSSEG2 MICCAI challenge. Frontiers Media S.A. 2022-08-25 /pmc/articles/PMC10406205/ /pubmed/37555158 http://dx.doi.org/10.3389/fnimg.2022.948235 Text en Copyright © 2022 Kamraoui, Mansencal, Manjon and Coupé. 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 | Neuroimaging Kamraoui, Reda Abdellah Mansencal, Boris Manjon, José V. Coupé, Pierrick Longitudinal detection of new MS lesions using deep learning |
title | Longitudinal detection of new MS lesions using deep learning |
title_full | Longitudinal detection of new MS lesions using deep learning |
title_fullStr | Longitudinal detection of new MS lesions using deep learning |
title_full_unstemmed | Longitudinal detection of new MS lesions using deep learning |
title_short | Longitudinal detection of new MS lesions using deep learning |
title_sort | longitudinal detection of new ms lesions using deep learning |
topic | Neuroimaging |
url | https://www.ncbi.nlm.nih.gov/pmc/articles/PMC10406205/ https://www.ncbi.nlm.nih.gov/pubmed/37555158 http://dx.doi.org/10.3389/fnimg.2022.948235 |
work_keys_str_mv | AT kamraouiredaabdellah longitudinaldetectionofnewmslesionsusingdeeplearning AT mansencalboris longitudinaldetectionofnewmslesionsusingdeeplearning AT manjonjosev longitudinaldetectionofnewmslesionsusingdeeplearning AT coupepierrick longitudinaldetectionofnewmslesionsusingdeeplearning |