MEASegNet: 3D U-Net with Multiple Efficient Attention for Segmentation of Brain Tumor Images

Brain tumors are a type of disease that affects people’s health and have received extensive attention. Accurate segmentation of Magnetic Resonance Imaging (MRI) images for brain tumors is essential for effective treatment strategies. However, there is scope for enhancing the segmentation accuracy of...

Full description

Saved in:
Bibliographic Details
Main Authors: Ruihao Zhang, Peng Yang, Can Hu, Bin Guo
Format: Article
Language:English
Published: MDPI AG 2025-03-01
Series:Applied Sciences
Subjects:
Online Access:https://www.mdpi.com/2076-3417/15/7/3791
Tags: Add Tag
No Tags, Be the first to tag this record!
_version_ 1849730823398359040
author Ruihao Zhang
Peng Yang
Can Hu
Bin Guo
author_facet Ruihao Zhang
Peng Yang
Can Hu
Bin Guo
author_sort Ruihao Zhang
collection DOAJ
description Brain tumors are a type of disease that affects people’s health and have received extensive attention. Accurate segmentation of Magnetic Resonance Imaging (MRI) images for brain tumors is essential for effective treatment strategies. However, there is scope for enhancing the segmentation accuracy of established deep learning approaches, such as 3D U-Net. In pursuit of improved segmentation precision for brain tumor MRI images, we propose the MEASegNet, which incorporates multiple efficient attention mechanisms into the 3D U-Net architecture. The encoder employs Parallel Channel and Spatial Attention Block (PCSAB), the bottleneck layer leverages Channel Reduce Residual Atrous Spatial Pyramid Pooling (CRRASPP) attention, and the decoder layer incorporates Selective Large Receptive Field Block (SLRFB). Through the integration of various attention mechanisms, we enhance the capacity for detailed feature extraction, facilitate the interplay among distinct features, and ensure the retention of more comprehensive feature information. Consequently, this leads to an enhancement in the segmentation precision of 3D U-Net for brain tumor MRI images. In conclusion, our extensive experimentation on the BraTS2021 dataset yields Dice scores of 92.50%, 87.49%, and 84.16% for Whole Tumor (WT), Tumor Core (TC), and Enhancing Tumor (ET), respectively. These results indicate a marked improvement in segmentation accuracy over the conventional 3D U-Net.
format Article
id doaj-art-6aa62b2b939b4969ab7f8d2bf76f783b
institution DOAJ
issn 2076-3417
language English
publishDate 2025-03-01
publisher MDPI AG
record_format Article
series Applied Sciences
spelling doaj-art-6aa62b2b939b4969ab7f8d2bf76f783b2025-08-20T03:08:44ZengMDPI AGApplied Sciences2076-34172025-03-01157379110.3390/app15073791MEASegNet: 3D U-Net with Multiple Efficient Attention for Segmentation of Brain Tumor ImagesRuihao Zhang0Peng Yang1Can Hu2Bin Guo3College of Computer and Information Engineering, Xinjiang Agricultural University, Urumqi 830052, ChinaCollege of Computer and Information Engineering, Xinjiang Agricultural University, Urumqi 830052, ChinaSchool of Computer and Soft, Hohai University, Nanjing 211100, ChinaCollege of Computer and Information Engineering, Xinjiang Agricultural University, Urumqi 830052, ChinaBrain tumors are a type of disease that affects people’s health and have received extensive attention. Accurate segmentation of Magnetic Resonance Imaging (MRI) images for brain tumors is essential for effective treatment strategies. However, there is scope for enhancing the segmentation accuracy of established deep learning approaches, such as 3D U-Net. In pursuit of improved segmentation precision for brain tumor MRI images, we propose the MEASegNet, which incorporates multiple efficient attention mechanisms into the 3D U-Net architecture. The encoder employs Parallel Channel and Spatial Attention Block (PCSAB), the bottleneck layer leverages Channel Reduce Residual Atrous Spatial Pyramid Pooling (CRRASPP) attention, and the decoder layer incorporates Selective Large Receptive Field Block (SLRFB). Through the integration of various attention mechanisms, we enhance the capacity for detailed feature extraction, facilitate the interplay among distinct features, and ensure the retention of more comprehensive feature information. Consequently, this leads to an enhancement in the segmentation precision of 3D U-Net for brain tumor MRI images. In conclusion, our extensive experimentation on the BraTS2021 dataset yields Dice scores of 92.50%, 87.49%, and 84.16% for Whole Tumor (WT), Tumor Core (TC), and Enhancing Tumor (ET), respectively. These results indicate a marked improvement in segmentation accuracy over the conventional 3D U-Net.https://www.mdpi.com/2076-3417/15/7/37913D U-Netbrain tumor segmentationattention mechanism
spellingShingle Ruihao Zhang
Peng Yang
Can Hu
Bin Guo
MEASegNet: 3D U-Net with Multiple Efficient Attention for Segmentation of Brain Tumor Images
Applied Sciences
3D U-Net
brain tumor segmentation
attention mechanism
title MEASegNet: 3D U-Net with Multiple Efficient Attention for Segmentation of Brain Tumor Images
title_full MEASegNet: 3D U-Net with Multiple Efficient Attention for Segmentation of Brain Tumor Images
title_fullStr MEASegNet: 3D U-Net with Multiple Efficient Attention for Segmentation of Brain Tumor Images
title_full_unstemmed MEASegNet: 3D U-Net with Multiple Efficient Attention for Segmentation of Brain Tumor Images
title_short MEASegNet: 3D U-Net with Multiple Efficient Attention for Segmentation of Brain Tumor Images
title_sort measegnet 3d u net with multiple efficient attention for segmentation of brain tumor images
topic 3D U-Net
brain tumor segmentation
attention mechanism
url https://www.mdpi.com/2076-3417/15/7/3791
work_keys_str_mv AT ruihaozhang measegnet3dunetwithmultipleefficientattentionforsegmentationofbraintumorimages
AT pengyang measegnet3dunetwithmultipleefficientattentionforsegmentationofbraintumorimages
AT canhu measegnet3dunetwithmultipleefficientattentionforsegmentationofbraintumorimages
AT binguo measegnet3dunetwithmultipleefficientattentionforsegmentationofbraintumorimages