Cargando…

Automated Segmentation of Infarct Lesions in T1-Weighted MRI Scans Using Variational Mode Decomposition and Deep Learning

Automated segmentation methods are critical for early detection, prompt actions, and immediate treatments in reducing disability and death risks of brain infarction. This paper aims to develop a fully automated method to segment the infarct lesions from T1-weighted brain scans. As a key novelty, the...

Descripción completa

Detalles Bibliográficos
Autores principales: Paing, May Phu, Tungjitkusolmun, Supan, Bui, Toan Huy, Visitsattapongse, Sarinporn, Pintavirooj, Chuchart
Formato: Online Artículo Texto
Lenguaje:English
Publicado: MDPI 2021
Materias:
Acceso en línea:https://www.ncbi.nlm.nih.gov/pmc/articles/PMC7999810/
https://www.ncbi.nlm.nih.gov/pubmed/33802223
http://dx.doi.org/10.3390/s21061952
_version_ 1783670866784026624
author Paing, May Phu
Tungjitkusolmun, Supan
Bui, Toan Huy
Visitsattapongse, Sarinporn
Pintavirooj, Chuchart
author_facet Paing, May Phu
Tungjitkusolmun, Supan
Bui, Toan Huy
Visitsattapongse, Sarinporn
Pintavirooj, Chuchart
author_sort Paing, May Phu
collection PubMed
description Automated segmentation methods are critical for early detection, prompt actions, and immediate treatments in reducing disability and death risks of brain infarction. This paper aims to develop a fully automated method to segment the infarct lesions from T1-weighted brain scans. As a key novelty, the proposed method combines variational mode decomposition and deep learning-based segmentation to take advantages of both methods and provide better results. There are three main technical contributions in this paper. First, variational mode decomposition is applied as a pre-processing to discriminate the infarct lesions from unwanted non-infarct tissues. Second, overlapped patches strategy is proposed to reduce the workload of the deep-learning-based segmentation task. Finally, a three-dimensional U-Net model is developed to perform patch-wise segmentation of infarct lesions. A total of 239 brain scans from a public dataset is utilized to develop and evaluate the proposed method. Empirical results reveal that the proposed automated segmentation can provide promising performances with an average dice similarity coefficient (DSC) of 0.6684, intersection over union (IoU) of 0.5022, and average symmetric surface distance (ASSD) of 0.3932, respectively.
format Online
Article
Text
id pubmed-7999810
institution National Center for Biotechnology Information
language English
publishDate 2021
publisher MDPI
record_format MEDLINE/PubMed
spelling pubmed-79998102021-03-28 Automated Segmentation of Infarct Lesions in T1-Weighted MRI Scans Using Variational Mode Decomposition and Deep Learning Paing, May Phu Tungjitkusolmun, Supan Bui, Toan Huy Visitsattapongse, Sarinporn Pintavirooj, Chuchart Sensors (Basel) Article Automated segmentation methods are critical for early detection, prompt actions, and immediate treatments in reducing disability and death risks of brain infarction. This paper aims to develop a fully automated method to segment the infarct lesions from T1-weighted brain scans. As a key novelty, the proposed method combines variational mode decomposition and deep learning-based segmentation to take advantages of both methods and provide better results. There are three main technical contributions in this paper. First, variational mode decomposition is applied as a pre-processing to discriminate the infarct lesions from unwanted non-infarct tissues. Second, overlapped patches strategy is proposed to reduce the workload of the deep-learning-based segmentation task. Finally, a three-dimensional U-Net model is developed to perform patch-wise segmentation of infarct lesions. A total of 239 brain scans from a public dataset is utilized to develop and evaluate the proposed method. Empirical results reveal that the proposed automated segmentation can provide promising performances with an average dice similarity coefficient (DSC) of 0.6684, intersection over union (IoU) of 0.5022, and average symmetric surface distance (ASSD) of 0.3932, respectively. MDPI 2021-03-10 /pmc/articles/PMC7999810/ /pubmed/33802223 http://dx.doi.org/10.3390/s21061952 Text en © 2021 by the authors. Licensee MDPI, Basel, Switzerland. This article is an open access article distributed under the terms and conditions of the Creative Commons Attribution (CC BY) license (http://creativecommons.org/licenses/by/4.0/).
spellingShingle Article
Paing, May Phu
Tungjitkusolmun, Supan
Bui, Toan Huy
Visitsattapongse, Sarinporn
Pintavirooj, Chuchart
Automated Segmentation of Infarct Lesions in T1-Weighted MRI Scans Using Variational Mode Decomposition and Deep Learning
title Automated Segmentation of Infarct Lesions in T1-Weighted MRI Scans Using Variational Mode Decomposition and Deep Learning
title_full Automated Segmentation of Infarct Lesions in T1-Weighted MRI Scans Using Variational Mode Decomposition and Deep Learning
title_fullStr Automated Segmentation of Infarct Lesions in T1-Weighted MRI Scans Using Variational Mode Decomposition and Deep Learning
title_full_unstemmed Automated Segmentation of Infarct Lesions in T1-Weighted MRI Scans Using Variational Mode Decomposition and Deep Learning
title_short Automated Segmentation of Infarct Lesions in T1-Weighted MRI Scans Using Variational Mode Decomposition and Deep Learning
title_sort automated segmentation of infarct lesions in t1-weighted mri scans using variational mode decomposition and deep learning
topic Article
url https://www.ncbi.nlm.nih.gov/pmc/articles/PMC7999810/
https://www.ncbi.nlm.nih.gov/pubmed/33802223
http://dx.doi.org/10.3390/s21061952
work_keys_str_mv AT paingmayphu automatedsegmentationofinfarctlesionsint1weightedmriscansusingvariationalmodedecompositionanddeeplearning
AT tungjitkusolmunsupan automatedsegmentationofinfarctlesionsint1weightedmriscansusingvariationalmodedecompositionanddeeplearning
AT buitoanhuy automatedsegmentationofinfarctlesionsint1weightedmriscansusingvariationalmodedecompositionanddeeplearning
AT visitsattapongsesarinporn automatedsegmentationofinfarctlesionsint1weightedmriscansusingvariationalmodedecompositionanddeeplearning
AT pintaviroojchuchart automatedsegmentationofinfarctlesionsint1weightedmriscansusingvariationalmodedecompositionanddeeplearning