A 3D lightweight network with Roberts edge enhancement model (LR-Net) for brain tumor segmentation

Abstract In clinical medicine, a reliable and resource-friendly computer-aided diagnosis (CAD) method for brain tumor segmentation is essential to enhance diagnostic accuracy and therapeutic outcomes, particularly in regions with uneven healthcare resource distribution. Convolutional neural networks...

Full description

Saved in:
Bibliographic Details
Main Authors: Qingxu Meng, Weijiang Wang, Hang Qi, Hua Dang, Minli Jia, Xiaohua Wang
Format: Article
Language:English
Published: Nature Portfolio 2025-06-01
Series:Scientific Reports
Subjects:
Online Access:https://doi.org/10.1038/s41598-025-03151-z
Tags: Add Tag
No Tags, Be the first to tag this record!
_version_ 1850138026700701696
author Qingxu Meng
Weijiang Wang
Hang Qi
Hua Dang
Minli Jia
Xiaohua Wang
author_facet Qingxu Meng
Weijiang Wang
Hang Qi
Hua Dang
Minli Jia
Xiaohua Wang
author_sort Qingxu Meng
collection DOAJ
description Abstract In clinical medicine, a reliable and resource-friendly computer-aided diagnosis (CAD) method for brain tumor segmentation is essential to enhance diagnostic accuracy and therapeutic outcomes, particularly in regions with uneven healthcare resource distribution. Convolutional neural networks (CNNs) perform extremely well in processing local detailed features. However, there restricted receptive field renders them incapable of capturing global context information. Although the combination of CNNs and Transformers balances the ability to capture local detailed features and global context information, it inevitably increases the model’s parameters and computational cost, which restricts its equal deployment in real medical scenarios. To address this issue, We propose a Lightweight Network with Roberts edge enhancement (LR-Net) for brain tumor segmentation that achieves an optimal balance between parameters and diagnostic accuracy. We propose a 3D Spatial Shift Convolution and Pixel Shuffle (SSCPS) module, the SSCPS module present a low-parameter, low-computational-cost spatial shift convolution that overcomes the limitation of receptive field and improves the ability to extract global contextual information, Pixel Shuffle (PS) module extracts spatial information from feature dimensions, efficiently replacing traditional upsampling module. The Channel Dilation Mechanism in SSCPS module dynamically adjust the number of output channels to maintain the range and depth of network feature aggregation. Additionally, the network leverages a combination of Channel Attention and Roberts Edge Enhancement (CAREE) module, to improve the channel aggregation capability and sensitivity of fuzzy boundaries. Our method achieved Dice of 0.806, 0.881, and 0.860 in BraTS2019, BraTS2020, and BraTS2021 datasets, while the parameters is only 4.72 M, which is only 3.03% of UNETR’s and 28.92% of UNet3D’s. This balance of efficiency and accuracy makes the proposed network well-suited for practical clinical applications.
format Article
id doaj-art-c5be1646f87a4557ab3c607fe0c52c43
institution OA Journals
issn 2045-2322
language English
publishDate 2025-06-01
publisher Nature Portfolio
record_format Article
series Scientific Reports
spelling doaj-art-c5be1646f87a4557ab3c607fe0c52c432025-08-20T02:30:41ZengNature PortfolioScientific Reports2045-23222025-06-0115111710.1038/s41598-025-03151-zA 3D lightweight network with Roberts edge enhancement model (LR-Net) for brain tumor segmentationQingxu Meng0Weijiang Wang1Hang Qi2Hua Dang3Minli Jia4Xiaohua Wang5School of Integrated Circuits and Electronics, Beijing Institute of TechnologySchool of Integrated Circuits and Electronics, Beijing Institute of TechnologySchool of Integrated Circuits and Electronics, Beijing Institute of TechnologySchool of Integrated Circuits and Electronics, Beijing Institute of TechnologySchool of Integrated Circuits and Electronics, Beijing Institute of TechnologySchool of Integrated Circuits and Electronics, Beijing Institute of TechnologyAbstract In clinical medicine, a reliable and resource-friendly computer-aided diagnosis (CAD) method for brain tumor segmentation is essential to enhance diagnostic accuracy and therapeutic outcomes, particularly in regions with uneven healthcare resource distribution. Convolutional neural networks (CNNs) perform extremely well in processing local detailed features. However, there restricted receptive field renders them incapable of capturing global context information. Although the combination of CNNs and Transformers balances the ability to capture local detailed features and global context information, it inevitably increases the model’s parameters and computational cost, which restricts its equal deployment in real medical scenarios. To address this issue, We propose a Lightweight Network with Roberts edge enhancement (LR-Net) for brain tumor segmentation that achieves an optimal balance between parameters and diagnostic accuracy. We propose a 3D Spatial Shift Convolution and Pixel Shuffle (SSCPS) module, the SSCPS module present a low-parameter, low-computational-cost spatial shift convolution that overcomes the limitation of receptive field and improves the ability to extract global contextual information, Pixel Shuffle (PS) module extracts spatial information from feature dimensions, efficiently replacing traditional upsampling module. The Channel Dilation Mechanism in SSCPS module dynamically adjust the number of output channels to maintain the range and depth of network feature aggregation. Additionally, the network leverages a combination of Channel Attention and Roberts Edge Enhancement (CAREE) module, to improve the channel aggregation capability and sensitivity of fuzzy boundaries. Our method achieved Dice of 0.806, 0.881, and 0.860 in BraTS2019, BraTS2020, and BraTS2021 datasets, while the parameters is only 4.72 M, which is only 3.03% of UNETR’s and 28.92% of UNet3D’s. This balance of efficiency and accuracy makes the proposed network well-suited for practical clinical applications.https://doi.org/10.1038/s41598-025-03151-z3D spatial shift convolutionRoberts edge enhancementResource-friendly modelBrain tumor segmentationDeep learning
spellingShingle Qingxu Meng
Weijiang Wang
Hang Qi
Hua Dang
Minli Jia
Xiaohua Wang
A 3D lightweight network with Roberts edge enhancement model (LR-Net) for brain tumor segmentation
Scientific Reports
3D spatial shift convolution
Roberts edge enhancement
Resource-friendly model
Brain tumor segmentation
Deep learning
title A 3D lightweight network with Roberts edge enhancement model (LR-Net) for brain tumor segmentation
title_full A 3D lightweight network with Roberts edge enhancement model (LR-Net) for brain tumor segmentation
title_fullStr A 3D lightweight network with Roberts edge enhancement model (LR-Net) for brain tumor segmentation
title_full_unstemmed A 3D lightweight network with Roberts edge enhancement model (LR-Net) for brain tumor segmentation
title_short A 3D lightweight network with Roberts edge enhancement model (LR-Net) for brain tumor segmentation
title_sort 3d lightweight network with roberts edge enhancement model lr net for brain tumor segmentation
topic 3D spatial shift convolution
Roberts edge enhancement
Resource-friendly model
Brain tumor segmentation
Deep learning
url https://doi.org/10.1038/s41598-025-03151-z
work_keys_str_mv AT qingxumeng a3dlightweightnetworkwithrobertsedgeenhancementmodellrnetforbraintumorsegmentation
AT weijiangwang a3dlightweightnetworkwithrobertsedgeenhancementmodellrnetforbraintumorsegmentation
AT hangqi a3dlightweightnetworkwithrobertsedgeenhancementmodellrnetforbraintumorsegmentation
AT huadang a3dlightweightnetworkwithrobertsedgeenhancementmodellrnetforbraintumorsegmentation
AT minlijia a3dlightweightnetworkwithrobertsedgeenhancementmodellrnetforbraintumorsegmentation
AT xiaohuawang a3dlightweightnetworkwithrobertsedgeenhancementmodellrnetforbraintumorsegmentation
AT qingxumeng 3dlightweightnetworkwithrobertsedgeenhancementmodellrnetforbraintumorsegmentation
AT weijiangwang 3dlightweightnetworkwithrobertsedgeenhancementmodellrnetforbraintumorsegmentation
AT hangqi 3dlightweightnetworkwithrobertsedgeenhancementmodellrnetforbraintumorsegmentation
AT huadang 3dlightweightnetworkwithrobertsedgeenhancementmodellrnetforbraintumorsegmentation
AT minlijia 3dlightweightnetworkwithrobertsedgeenhancementmodellrnetforbraintumorsegmentation
AT xiaohuawang 3dlightweightnetworkwithrobertsedgeenhancementmodellrnetforbraintumorsegmentation