AG-MS3D-CNN multiscale attention guided 3D convolutional neural network for robust brain tumor segmentation across MRI protocols

Abstract Accurate segmentation of brain tumors from multimodal Magnetic Resonance Imaging (MRI) plays a critical role in diagnosis, treatment planning, and disease monitoring in neuro-oncology. Traditional methods of tumor segmentation, often manual and labour-intensive, are prone to inconsistencies...

Full description

Saved in:
Bibliographic Details
Main Authors: Umesh Kumar Lilhore, R. Sunder, Sarita Simaiya, Majed Alsafyani, M. D. Monish Khan, Roobaea Alroobaea, Hamed Alsufyani, Abdullah M. Baqasah
Format: Article
Language:English
Published: Nature Portfolio 2025-07-01
Series:Scientific Reports
Subjects:
Online Access:https://doi.org/10.1038/s41598-025-09351-x
Tags: Add Tag
No Tags, Be the first to tag this record!
_version_ 1849763431891075072
author Umesh Kumar Lilhore
R. Sunder
Sarita Simaiya
Majed Alsafyani
M. D. Monish Khan
Roobaea Alroobaea
Hamed Alsufyani
Abdullah M. Baqasah
author_facet Umesh Kumar Lilhore
R. Sunder
Sarita Simaiya
Majed Alsafyani
M. D. Monish Khan
Roobaea Alroobaea
Hamed Alsufyani
Abdullah M. Baqasah
author_sort Umesh Kumar Lilhore
collection DOAJ
description Abstract Accurate segmentation of brain tumors from multimodal Magnetic Resonance Imaging (MRI) plays a critical role in diagnosis, treatment planning, and disease monitoring in neuro-oncology. Traditional methods of tumor segmentation, often manual and labour-intensive, are prone to inconsistencies and inter-observer variability. Recently, deep learning models, particularly Convolutional Neural Networks (CNNs), have shown great promise in automating this process. However, these models face challenges in terms of generalization across diverse datasets, accurate tumor boundary delineation, and uncertainty estimation. To address these challenges, we propose AG-MS3D-CNN, an attention-guided multiscale 3D convolutional neural network for brain tumor segmentation. Our model integrates local and global contextual information through multiscale feature extraction and leverages spatial attention mechanisms to enhance boundary delineation, particularly in complex tumor regions. We also introduce Monte Carlo dropout for uncertainty estimation, providing clinicians with confidence scores for each segmentation, which is crucial for informed decision-making. Furthermore, we adopt a multitask learning framework, which enables the simultaneous segmentation, classification, and volume estimation of tumors. To ensure robustness and generalizability across diverse MRI acquisition protocols and scanners, we integrate a domain adaptation module into the network. Extensive evaluations on the BraTS 2021 dataset and additional external datasets, such as OASIS, ADNI, and IXI, demonstrate the superior performance of AG-MS3D-CNN compared to existing state-of-the-art methods. Our model achieves high Dice scores and shows excellent robustness, making it a valuable tool for clinical decision support in neuro-oncology.
format Article
id doaj-art-b8aaa506e26346c1954b400b05b54a9d
institution DOAJ
issn 2045-2322
language English
publishDate 2025-07-01
publisher Nature Portfolio
record_format Article
series Scientific Reports
spelling doaj-art-b8aaa506e26346c1954b400b05b54a9d2025-08-20T03:05:25ZengNature PortfolioScientific Reports2045-23222025-07-0115112510.1038/s41598-025-09351-xAG-MS3D-CNN multiscale attention guided 3D convolutional neural network for robust brain tumor segmentation across MRI protocolsUmesh Kumar Lilhore0R. Sunder1Sarita Simaiya2Majed Alsafyani3M. D. Monish Khan4Roobaea Alroobaea5Hamed Alsufyani6Abdullah M. Baqasah7School of Computer Science and Engineering, Galgotias UniversitySchool of Computer Science and Engineering, Galgotias UniversitySchool of Computer Science and Engineering, Galgotias UniversityDepartment of Computer Science, College of Computers and Information Technology, Taif UniversityArba Minch UniversityDepartment of Computer Science, College of Computers and Information Technology, Taif UniversityDepartment of Computer Science, College of Computing and Informatics, Saudi Electronic UniversityDepartment of Information Technology, College of Computers and Information Technology, Taif UniversityAbstract Accurate segmentation of brain tumors from multimodal Magnetic Resonance Imaging (MRI) plays a critical role in diagnosis, treatment planning, and disease monitoring in neuro-oncology. Traditional methods of tumor segmentation, often manual and labour-intensive, are prone to inconsistencies and inter-observer variability. Recently, deep learning models, particularly Convolutional Neural Networks (CNNs), have shown great promise in automating this process. However, these models face challenges in terms of generalization across diverse datasets, accurate tumor boundary delineation, and uncertainty estimation. To address these challenges, we propose AG-MS3D-CNN, an attention-guided multiscale 3D convolutional neural network for brain tumor segmentation. Our model integrates local and global contextual information through multiscale feature extraction and leverages spatial attention mechanisms to enhance boundary delineation, particularly in complex tumor regions. We also introduce Monte Carlo dropout for uncertainty estimation, providing clinicians with confidence scores for each segmentation, which is crucial for informed decision-making. Furthermore, we adopt a multitask learning framework, which enables the simultaneous segmentation, classification, and volume estimation of tumors. To ensure robustness and generalizability across diverse MRI acquisition protocols and scanners, we integrate a domain adaptation module into the network. Extensive evaluations on the BraTS 2021 dataset and additional external datasets, such as OASIS, ADNI, and IXI, demonstrate the superior performance of AG-MS3D-CNN compared to existing state-of-the-art methods. Our model achieves high Dice scores and shows excellent robustness, making it a valuable tool for clinical decision support in neuro-oncology.https://doi.org/10.1038/s41598-025-09351-xBrain tumor segmentationMedical image analysis3D CNNUncertainty EstimationAttention-guided model
spellingShingle Umesh Kumar Lilhore
R. Sunder
Sarita Simaiya
Majed Alsafyani
M. D. Monish Khan
Roobaea Alroobaea
Hamed Alsufyani
Abdullah M. Baqasah
AG-MS3D-CNN multiscale attention guided 3D convolutional neural network for robust brain tumor segmentation across MRI protocols
Scientific Reports
Brain tumor segmentation
Medical image analysis
3D CNN
Uncertainty Estimation
Attention-guided model
title AG-MS3D-CNN multiscale attention guided 3D convolutional neural network for robust brain tumor segmentation across MRI protocols
title_full AG-MS3D-CNN multiscale attention guided 3D convolutional neural network for robust brain tumor segmentation across MRI protocols
title_fullStr AG-MS3D-CNN multiscale attention guided 3D convolutional neural network for robust brain tumor segmentation across MRI protocols
title_full_unstemmed AG-MS3D-CNN multiscale attention guided 3D convolutional neural network for robust brain tumor segmentation across MRI protocols
title_short AG-MS3D-CNN multiscale attention guided 3D convolutional neural network for robust brain tumor segmentation across MRI protocols
title_sort ag ms3d cnn multiscale attention guided 3d convolutional neural network for robust brain tumor segmentation across mri protocols
topic Brain tumor segmentation
Medical image analysis
3D CNN
Uncertainty Estimation
Attention-guided model
url https://doi.org/10.1038/s41598-025-09351-x
work_keys_str_mv AT umeshkumarlilhore agms3dcnnmultiscaleattentionguided3dconvolutionalneuralnetworkforrobustbraintumorsegmentationacrossmriprotocols
AT rsunder agms3dcnnmultiscaleattentionguided3dconvolutionalneuralnetworkforrobustbraintumorsegmentationacrossmriprotocols
AT saritasimaiya agms3dcnnmultiscaleattentionguided3dconvolutionalneuralnetworkforrobustbraintumorsegmentationacrossmriprotocols
AT majedalsafyani agms3dcnnmultiscaleattentionguided3dconvolutionalneuralnetworkforrobustbraintumorsegmentationacrossmriprotocols
AT mdmonishkhan agms3dcnnmultiscaleattentionguided3dconvolutionalneuralnetworkforrobustbraintumorsegmentationacrossmriprotocols
AT roobaeaalroobaea agms3dcnnmultiscaleattentionguided3dconvolutionalneuralnetworkforrobustbraintumorsegmentationacrossmriprotocols
AT hamedalsufyani agms3dcnnmultiscaleattentionguided3dconvolutionalneuralnetworkforrobustbraintumorsegmentationacrossmriprotocols
AT abdullahmbaqasah agms3dcnnmultiscaleattentionguided3dconvolutionalneuralnetworkforrobustbraintumorsegmentationacrossmriprotocols