ABI-Net: Attention-Based Inception U-Net for Brain Tumor Segmentation From Multimodal MRI Images
Magnetic Resonance Imaging (MRI) is widely used for glioma evaluation, but manual segmentation is impractical due to the large data volume. Automated techniques are necessary for precise clinical measurements. U-Net has shown promise in volumetric segmentation, but brain tumor segmentation remains c...
Saved in:
| Main Authors: | , , , |
|---|---|
| Format: | Article |
| Language: | English |
| Published: |
IEEE
2025-01-01
|
| Series: | IEEE Access |
| Subjects: | |
| Online Access: | https://ieeexplore.ieee.org/document/11071545/ |
| Tags: |
Add Tag
No Tags, Be the first to tag this record!
|
| _version_ | 1849772660011040768 |
|---|---|
| author | Evans Kipkoech Rutoh Qin ZhiGuang Joyce C. Bore-Norton Noor Bahadar |
| author_facet | Evans Kipkoech Rutoh Qin ZhiGuang Joyce C. Bore-Norton Noor Bahadar |
| author_sort | Evans Kipkoech Rutoh |
| collection | DOAJ |
| description | Magnetic Resonance Imaging (MRI) is widely used for glioma evaluation, but manual segmentation is impractical due to the large data volume. Automated techniques are necessary for precise clinical measurements. U-Net has shown promise in volumetric segmentation, but brain tumor segmentation remains challenging due to tumor diversity in type, location, and structure. This study introduces ABI-Net, an advanced U-Net variant integrating Attention-based Inception blocks for improved segmentation of brain tumor sub-regions in 3D multimodal MRI images. ABI-Net leverages the Inception module for spatial feature extraction and an attention mechanism to enhance cancerous region detection. Trained on the BraTS 2020 dataset, ABI-Net achieved dice scores of 0.8354, 0.8505, and 0.8782 for enhancing tumor (ET), tumor core (TC), and whole tumor (WT), respectively, outperforming state-of-the-art models. On the validation dataset (125 patients without segmentation masks), ABI-Net obtained average dice scores of 0.8189, 0.8401, and 0.8673 for ET, TC, and WT. ABI-Net provides an accurate, efficient solution for automated brain tumor segmentation, with significant potential for clinical applications, including diagnosis, treatment planning, and patient monitoring. |
| format | Article |
| id | doaj-art-53e841c371dd4e7ab9988e15f5b71564 |
| institution | DOAJ |
| issn | 2169-3536 |
| language | English |
| publishDate | 2025-01-01 |
| publisher | IEEE |
| record_format | Article |
| series | IEEE Access |
| spelling | doaj-art-53e841c371dd4e7ab9988e15f5b715642025-08-20T03:02:16ZengIEEEIEEE Access2169-35362025-01-011313489813491610.1109/ACCESS.2025.358592611071545ABI-Net: Attention-Based Inception U-Net for Brain Tumor Segmentation From Multimodal MRI ImagesEvans Kipkoech Rutoh0https://orcid.org/0009-0004-8307-1476Qin ZhiGuang1Joyce C. Bore-Norton2Noor Bahadar3https://orcid.org/0000-0001-9576-5345School of Computer Science and Engineering, University of Electronic Science and Technology of China, Chengdu, ChinaSchool of Computer Science and Engineering, University of Electronic Science and Technology of China, Chengdu, ChinaDepartment of Systems and Analytics, Cleveland Clinic, Cleveland, OH, USAKey Laboratory of Molecular Epigenetics of the Ministry of Education (MOE), Northeast Normal University, Changchun, Jilin, ChinaMagnetic Resonance Imaging (MRI) is widely used for glioma evaluation, but manual segmentation is impractical due to the large data volume. Automated techniques are necessary for precise clinical measurements. U-Net has shown promise in volumetric segmentation, but brain tumor segmentation remains challenging due to tumor diversity in type, location, and structure. This study introduces ABI-Net, an advanced U-Net variant integrating Attention-based Inception blocks for improved segmentation of brain tumor sub-regions in 3D multimodal MRI images. ABI-Net leverages the Inception module for spatial feature extraction and an attention mechanism to enhance cancerous region detection. Trained on the BraTS 2020 dataset, ABI-Net achieved dice scores of 0.8354, 0.8505, and 0.8782 for enhancing tumor (ET), tumor core (TC), and whole tumor (WT), respectively, outperforming state-of-the-art models. On the validation dataset (125 patients without segmentation masks), ABI-Net obtained average dice scores of 0.8189, 0.8401, and 0.8673 for ET, TC, and WT. ABI-Net provides an accurate, efficient solution for automated brain tumor segmentation, with significant potential for clinical applications, including diagnosis, treatment planning, and patient monitoring.https://ieeexplore.ieee.org/document/11071545/Attention mechanismbrain tumor segmentationinception blocksU-Netclinical applications |
| spellingShingle | Evans Kipkoech Rutoh Qin ZhiGuang Joyce C. Bore-Norton Noor Bahadar ABI-Net: Attention-Based Inception U-Net for Brain Tumor Segmentation From Multimodal MRI Images IEEE Access Attention mechanism brain tumor segmentation inception blocks U-Net clinical applications |
| title | ABI-Net: Attention-Based Inception U-Net for Brain Tumor Segmentation From Multimodal MRI Images |
| title_full | ABI-Net: Attention-Based Inception U-Net for Brain Tumor Segmentation From Multimodal MRI Images |
| title_fullStr | ABI-Net: Attention-Based Inception U-Net for Brain Tumor Segmentation From Multimodal MRI Images |
| title_full_unstemmed | ABI-Net: Attention-Based Inception U-Net for Brain Tumor Segmentation From Multimodal MRI Images |
| title_short | ABI-Net: Attention-Based Inception U-Net for Brain Tumor Segmentation From Multimodal MRI Images |
| title_sort | abi net attention based inception u net for brain tumor segmentation from multimodal mri images |
| topic | Attention mechanism brain tumor segmentation inception blocks U-Net clinical applications |
| url | https://ieeexplore.ieee.org/document/11071545/ |
| work_keys_str_mv | AT evanskipkoechrutoh abinetattentionbasedinceptionunetforbraintumorsegmentationfrommultimodalmriimages AT qinzhiguang abinetattentionbasedinceptionunetforbraintumorsegmentationfrommultimodalmriimages AT joycecborenorton abinetattentionbasedinceptionunetforbraintumorsegmentationfrommultimodalmriimages AT noorbahadar abinetattentionbasedinceptionunetforbraintumorsegmentationfrommultimodalmriimages |