Cargando…

Deep learning-based magnetic resonance image segmentation technique for application to glioma

INTRODUCTION: Brain glioma segmentation is a critical task for medical diagnosis, monitoring, and treatment planning. DISCUSSION: Although deep learning-based fully convolutional neural networks have shown promising results in this field, their unstable segmentation quality remains a major concern....

Descripción completa

Detalles Bibliográficos
Autores principales: Wan, Bing, Hu, Bingbing, Zhao, Ming, Li, Kang, Ye, Xu
Formato: Online Artículo Texto
Lenguaje:English
Publicado: Frontiers Media S.A. 2023
Materias:
Acceso en línea:https://www.ncbi.nlm.nih.gov/pmc/articles/PMC10694355/
http://dx.doi.org/10.3389/fmed.2023.1172767
_version_ 1785153358094401536
author Wan, Bing
Hu, Bingbing
Zhao, Ming
Li, Kang
Ye, Xu
author_facet Wan, Bing
Hu, Bingbing
Zhao, Ming
Li, Kang
Ye, Xu
author_sort Wan, Bing
collection PubMed
description INTRODUCTION: Brain glioma segmentation is a critical task for medical diagnosis, monitoring, and treatment planning. DISCUSSION: Although deep learning-based fully convolutional neural networks have shown promising results in this field, their unstable segmentation quality remains a major concern. Moreover, they do not consider the unique genomic and basic data of brain glioma patients, which may lead to inaccurate diagnosis and treatment planning. METHODS: This study proposes a new model that overcomes this problem by improving the overall architecture and incorporating an innovative loss function. First, we employed DeepLabv3+ as the overall architecture of the model and RegNet as the image encoder. We designed an attribute encoder module to incorporate the patient’s genomic and basic data and the image depth information into a 2D convolutional neural network, which was combined with the image encoder and atrous spatial pyramid pooling module to form the encoder module for addressing the multimodal fusion problem. In addition, the cross-entropy loss and Dice loss are implemented with linear weighting to solve the problem of sample imbalance. An innovative loss function is proposed to suppress specific size regions, thereby preventing the occurrence of segmentation errors of noise-like regions; hence, higher-stability segmentation results are obtained. Experiments were conducted on the Lower-Grade Glioma Segmentation Dataset, a widely used benchmark dataset for brain tumor segmentation. RESULTS: The proposed method achieved a Dice score of 94.36 and an intersection over union score of 91.83, thus outperforming other popular models.
format Online
Article
Text
id pubmed-10694355
institution National Center for Biotechnology Information
language English
publishDate 2023
publisher Frontiers Media S.A.
record_format MEDLINE/PubMed
spelling pubmed-106943552023-12-05 Deep learning-based magnetic resonance image segmentation technique for application to glioma Wan, Bing Hu, Bingbing Zhao, Ming Li, Kang Ye, Xu Front Med (Lausanne) Medicine INTRODUCTION: Brain glioma segmentation is a critical task for medical diagnosis, monitoring, and treatment planning. DISCUSSION: Although deep learning-based fully convolutional neural networks have shown promising results in this field, their unstable segmentation quality remains a major concern. Moreover, they do not consider the unique genomic and basic data of brain glioma patients, which may lead to inaccurate diagnosis and treatment planning. METHODS: This study proposes a new model that overcomes this problem by improving the overall architecture and incorporating an innovative loss function. First, we employed DeepLabv3+ as the overall architecture of the model and RegNet as the image encoder. We designed an attribute encoder module to incorporate the patient’s genomic and basic data and the image depth information into a 2D convolutional neural network, which was combined with the image encoder and atrous spatial pyramid pooling module to form the encoder module for addressing the multimodal fusion problem. In addition, the cross-entropy loss and Dice loss are implemented with linear weighting to solve the problem of sample imbalance. An innovative loss function is proposed to suppress specific size regions, thereby preventing the occurrence of segmentation errors of noise-like regions; hence, higher-stability segmentation results are obtained. Experiments were conducted on the Lower-Grade Glioma Segmentation Dataset, a widely used benchmark dataset for brain tumor segmentation. RESULTS: The proposed method achieved a Dice score of 94.36 and an intersection over union score of 91.83, thus outperforming other popular models. Frontiers Media S.A. 2023-11-20 /pmc/articles/PMC10694355/ http://dx.doi.org/10.3389/fmed.2023.1172767 Text en Copyright © 2023 Wan, Hu, Zhao, Li and Ye. 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 Medicine
Wan, Bing
Hu, Bingbing
Zhao, Ming
Li, Kang
Ye, Xu
Deep learning-based magnetic resonance image segmentation technique for application to glioma
title Deep learning-based magnetic resonance image segmentation technique for application to glioma
title_full Deep learning-based magnetic resonance image segmentation technique for application to glioma
title_fullStr Deep learning-based magnetic resonance image segmentation technique for application to glioma
title_full_unstemmed Deep learning-based magnetic resonance image segmentation technique for application to glioma
title_short Deep learning-based magnetic resonance image segmentation technique for application to glioma
title_sort deep learning-based magnetic resonance image segmentation technique for application to glioma
topic Medicine
url https://www.ncbi.nlm.nih.gov/pmc/articles/PMC10694355/
http://dx.doi.org/10.3389/fmed.2023.1172767
work_keys_str_mv AT wanbing deeplearningbasedmagneticresonanceimagesegmentationtechniqueforapplicationtoglioma
AT hubingbing deeplearningbasedmagneticresonanceimagesegmentationtechniqueforapplicationtoglioma
AT zhaoming deeplearningbasedmagneticresonanceimagesegmentationtechniqueforapplicationtoglioma
AT likang deeplearningbasedmagneticresonanceimagesegmentationtechniqueforapplicationtoglioma
AT yexu deeplearningbasedmagneticresonanceimagesegmentationtechniqueforapplicationtoglioma