Cargando…

Quantifying brain tissue volume in multiple sclerosis with automated lesion segmentation and filling

Lesion filling has been successfully applied to reduce the effect of hypo-intense T1-w Multiple Sclerosis (MS) lesions on automatic brain tissue segmentation. However, a study of fully automated pipelines incorporating lesion segmentation and lesion filling on tissue volume analysis has not yet been...

Descripción completa

Detalles Bibliográficos
Autores principales: Valverde, Sergi, Oliver, Arnau, Roura, Eloy, Pareto, Deborah, Vilanova, Joan C., Ramió-Torrentà, Lluís, Sastre-Garriga, Jaume, Montalban, Xavier, Rovira, Àlex, Lladó, Xavier
Formato: Online Artículo Texto
Lenguaje:English
Publicado: Elsevier 2015
Materias:
Acceso en línea:https://www.ncbi.nlm.nih.gov/pmc/articles/PMC4644250/
https://www.ncbi.nlm.nih.gov/pubmed/26740917
http://dx.doi.org/10.1016/j.nicl.2015.10.012
_version_ 1782400641115619328
author Valverde, Sergi
Oliver, Arnau
Roura, Eloy
Pareto, Deborah
Vilanova, Joan C.
Ramió-Torrentà, Lluís
Sastre-Garriga, Jaume
Montalban, Xavier
Rovira, Àlex
Lladó, Xavier
author_facet Valverde, Sergi
Oliver, Arnau
Roura, Eloy
Pareto, Deborah
Vilanova, Joan C.
Ramió-Torrentà, Lluís
Sastre-Garriga, Jaume
Montalban, Xavier
Rovira, Àlex
Lladó, Xavier
author_sort Valverde, Sergi
collection PubMed
description Lesion filling has been successfully applied to reduce the effect of hypo-intense T1-w Multiple Sclerosis (MS) lesions on automatic brain tissue segmentation. However, a study of fully automated pipelines incorporating lesion segmentation and lesion filling on tissue volume analysis has not yet been performed. Here, we analyzed the % of error introduced by automating the lesion segmentation and filling processes in the tissue segmentation of 70 clinically isolated syndrome patient images. First of all, images were processed using the LST and SLS toolkits with different pipeline combinations that differed in either automated or manual lesion segmentation, and lesion filling or masking out lesions. Then, images processed following each of the pipelines were segmented into gray matter (GM) and white matter (WM) using SPM8, and compared with the same images where expert lesion annotations were filled before segmentation. Our results showed that fully automated lesion segmentation and filling pipelines reduced significantly the % of error in GM and WM volume on images of MS patients, and performed similarly to the images where expert lesion annotations were masked before segmentation. In all the pipelines, the amount of misclassified lesion voxels was the main cause in the observed error in GM and WM volume. However, the % of error was significantly lower when automatically estimated lesions were filled and not masked before segmentation. These results are relevant and suggest that LST and SLS toolboxes allow the performance of accurate brain tissue volume measurements without any kind of manual intervention, which can be convenient not only in terms of time and economic costs, but also to avoid the inherent intra/inter variability between manual annotations.
format Online
Article
Text
id pubmed-4644250
institution National Center for Biotechnology Information
language English
publishDate 2015
publisher Elsevier
record_format MEDLINE/PubMed
spelling pubmed-46442502016-01-06 Quantifying brain tissue volume in multiple sclerosis with automated lesion segmentation and filling Valverde, Sergi Oliver, Arnau Roura, Eloy Pareto, Deborah Vilanova, Joan C. Ramió-Torrentà, Lluís Sastre-Garriga, Jaume Montalban, Xavier Rovira, Àlex Lladó, Xavier Neuroimage Clin Regular Article Lesion filling has been successfully applied to reduce the effect of hypo-intense T1-w Multiple Sclerosis (MS) lesions on automatic brain tissue segmentation. However, a study of fully automated pipelines incorporating lesion segmentation and lesion filling on tissue volume analysis has not yet been performed. Here, we analyzed the % of error introduced by automating the lesion segmentation and filling processes in the tissue segmentation of 70 clinically isolated syndrome patient images. First of all, images were processed using the LST and SLS toolkits with different pipeline combinations that differed in either automated or manual lesion segmentation, and lesion filling or masking out lesions. Then, images processed following each of the pipelines were segmented into gray matter (GM) and white matter (WM) using SPM8, and compared with the same images where expert lesion annotations were filled before segmentation. Our results showed that fully automated lesion segmentation and filling pipelines reduced significantly the % of error in GM and WM volume on images of MS patients, and performed similarly to the images where expert lesion annotations were masked before segmentation. In all the pipelines, the amount of misclassified lesion voxels was the main cause in the observed error in GM and WM volume. However, the % of error was significantly lower when automatically estimated lesions were filled and not masked before segmentation. These results are relevant and suggest that LST and SLS toolboxes allow the performance of accurate brain tissue volume measurements without any kind of manual intervention, which can be convenient not only in terms of time and economic costs, but also to avoid the inherent intra/inter variability between manual annotations. Elsevier 2015-10-28 /pmc/articles/PMC4644250/ /pubmed/26740917 http://dx.doi.org/10.1016/j.nicl.2015.10.012 Text en © 2015 The Authors http://creativecommons.org/licenses/by-nc-nd/4.0/ This is an open access article under the CC BY-NC-ND license (http://creativecommons.org/licenses/by-nc-nd/4.0/).
spellingShingle Regular Article
Valverde, Sergi
Oliver, Arnau
Roura, Eloy
Pareto, Deborah
Vilanova, Joan C.
Ramió-Torrentà, Lluís
Sastre-Garriga, Jaume
Montalban, Xavier
Rovira, Àlex
Lladó, Xavier
Quantifying brain tissue volume in multiple sclerosis with automated lesion segmentation and filling
title Quantifying brain tissue volume in multiple sclerosis with automated lesion segmentation and filling
title_full Quantifying brain tissue volume in multiple sclerosis with automated lesion segmentation and filling
title_fullStr Quantifying brain tissue volume in multiple sclerosis with automated lesion segmentation and filling
title_full_unstemmed Quantifying brain tissue volume in multiple sclerosis with automated lesion segmentation and filling
title_short Quantifying brain tissue volume in multiple sclerosis with automated lesion segmentation and filling
title_sort quantifying brain tissue volume in multiple sclerosis with automated lesion segmentation and filling
topic Regular Article
url https://www.ncbi.nlm.nih.gov/pmc/articles/PMC4644250/
https://www.ncbi.nlm.nih.gov/pubmed/26740917
http://dx.doi.org/10.1016/j.nicl.2015.10.012
work_keys_str_mv AT valverdesergi quantifyingbraintissuevolumeinmultiplesclerosiswithautomatedlesionsegmentationandfilling
AT oliverarnau quantifyingbraintissuevolumeinmultiplesclerosiswithautomatedlesionsegmentationandfilling
AT rouraeloy quantifyingbraintissuevolumeinmultiplesclerosiswithautomatedlesionsegmentationandfilling
AT paretodeborah quantifyingbraintissuevolumeinmultiplesclerosiswithautomatedlesionsegmentationandfilling
AT vilanovajoanc quantifyingbraintissuevolumeinmultiplesclerosiswithautomatedlesionsegmentationandfilling
AT ramiotorrentalluis quantifyingbraintissuevolumeinmultiplesclerosiswithautomatedlesionsegmentationandfilling
AT sastregarrigajaume quantifyingbraintissuevolumeinmultiplesclerosiswithautomatedlesionsegmentationandfilling
AT montalbanxavier quantifyingbraintissuevolumeinmultiplesclerosiswithautomatedlesionsegmentationandfilling
AT roviraalex quantifyingbraintissuevolumeinmultiplesclerosiswithautomatedlesionsegmentationandfilling
AT lladoxavier quantifyingbraintissuevolumeinmultiplesclerosiswithautomatedlesionsegmentationandfilling