Advanced multi-label brain hemorrhage segmentation using an attention-based residual U-Net model
Abstract Objective This study aimed to develop and assess an advanced Attention-Based Residual U-Net (ResUNet) model for accurately segmenting different types of brain hemorrhages from CT images. The goal was to overcome the limitations of manual segmentation and current automated methods regarding...
Saved in:
| Main Authors: | , , , , |
|---|---|
| Format: | Article |
| Language: | English |
| Published: |
BMC
2025-07-01
|
| Series: | BMC Medical Informatics and Decision Making |
| Subjects: | |
| Online Access: | https://doi.org/10.1186/s12911-025-03131-3 |
| Tags: |
Add Tag
No Tags, Be the first to tag this record!
|
| _version_ | 1849343465920397312 |
|---|---|
| author | Xinxin Lin Enmiao Zou Wenci Chen Xinxin Chen Le Lin |
| author_facet | Xinxin Lin Enmiao Zou Wenci Chen Xinxin Chen Le Lin |
| author_sort | Xinxin Lin |
| collection | DOAJ |
| description | Abstract Objective This study aimed to develop and assess an advanced Attention-Based Residual U-Net (ResUNet) model for accurately segmenting different types of brain hemorrhages from CT images. The goal was to overcome the limitations of manual segmentation and current automated methods regarding precision and generalizability. Materials and methods A dataset of 1,347 patient CT scans was collected retrospectively, covering six types of hemorrhages: subarachnoid hemorrhage (SAH, 231 cases), subdural hematoma (SDH, 198 cases), epidural hematoma (EDH, 236 cases), cerebral contusion (CC, 230 cases), intraventricular hemorrhage (IVH, 188 cases), and intracerebral hemorrhage (ICH, 264 cases). The dataset was divided into 80% for training using a 10-fold cross-validation approach and 20% for testing. All CT scans were standardized to a common anatomical space, and intensity normalization was applied for uniformity. The ResUNet model included attention mechanisms to enhance focus on important features and residual connections to support stable learning and efficient gradient flow. Model performance was assessed using the Dice Similarity Coefficient (DSC), Intersection over Union (IoU), and directed Hausdorff distance (dHD). Results The ResUNet model showed excellent performance during both training and testing. On training data, the model achieved DSC scores of 95 ± 1.2 for SAH, 94 ± 1.4 for SDH, 93 ± 1.5 for EDH, 91 ± 1.4 for CC, 89 ± 1.6 for IVH, and 93 ± 2.4 for ICH. IoU values ranged from 88 to 93, with dHD between 2.1- and 2.7-mm. Testing results confirmed strong generalization, with DSC scores of 93 for SAH, 93 for SDH, 92 for EDH, 90 for CC, 88 for IVH, and 92 for ICH. IoU values were also high, indicating precise segmentation and minimal boundary errors. Conclusions The ResUNet model outperformed standard U-Net variants, achieving higher multi-label segmentation accuracy. This makes it a valuable tool for clinical applications that require fast and reliable brain hemorrhage analysis. Future research could investigate semi-supervised techniques and 3D segmentation to further enhance clinical use. Clinical trial number Not applicable. |
| format | Article |
| id | doaj-art-a409fec0be0a427c930f90e0c53d2c86 |
| institution | Kabale University |
| issn | 1472-6947 |
| language | English |
| publishDate | 2025-07-01 |
| publisher | BMC |
| record_format | Article |
| series | BMC Medical Informatics and Decision Making |
| spelling | doaj-art-a409fec0be0a427c930f90e0c53d2c862025-08-20T03:42:57ZengBMCBMC Medical Informatics and Decision Making1472-69472025-07-0125111510.1186/s12911-025-03131-3Advanced multi-label brain hemorrhage segmentation using an attention-based residual U-Net modelXinxin Lin0Enmiao Zou1Wenci Chen2Xinxin Chen3Le Lin4Department of General Practice, The Second Affiliated Hospital, Yuying Children’s Hospital of Wenzhou Medical UniversityDepartment of General Rehabilitation, The Second Affiliated Hospital, Yuying Children’s Hospital of Wenzhou Medical UniversityDepartment of Rehabilitation, Wenzhou Hospital of Integrated Traditional Chinese and Western MedicineDepartment of Orthopaedic Trauma, The Second Affiliated Hospital, Yuying Children’s Hospital of Wenzhou Medical UniversityDepartment of General Rehabilitation, The Second Affiliated Hospital, Yuying Children’s Hospital of Wenzhou Medical UniversityAbstract Objective This study aimed to develop and assess an advanced Attention-Based Residual U-Net (ResUNet) model for accurately segmenting different types of brain hemorrhages from CT images. The goal was to overcome the limitations of manual segmentation and current automated methods regarding precision and generalizability. Materials and methods A dataset of 1,347 patient CT scans was collected retrospectively, covering six types of hemorrhages: subarachnoid hemorrhage (SAH, 231 cases), subdural hematoma (SDH, 198 cases), epidural hematoma (EDH, 236 cases), cerebral contusion (CC, 230 cases), intraventricular hemorrhage (IVH, 188 cases), and intracerebral hemorrhage (ICH, 264 cases). The dataset was divided into 80% for training using a 10-fold cross-validation approach and 20% for testing. All CT scans were standardized to a common anatomical space, and intensity normalization was applied for uniformity. The ResUNet model included attention mechanisms to enhance focus on important features and residual connections to support stable learning and efficient gradient flow. Model performance was assessed using the Dice Similarity Coefficient (DSC), Intersection over Union (IoU), and directed Hausdorff distance (dHD). Results The ResUNet model showed excellent performance during both training and testing. On training data, the model achieved DSC scores of 95 ± 1.2 for SAH, 94 ± 1.4 for SDH, 93 ± 1.5 for EDH, 91 ± 1.4 for CC, 89 ± 1.6 for IVH, and 93 ± 2.4 for ICH. IoU values ranged from 88 to 93, with dHD between 2.1- and 2.7-mm. Testing results confirmed strong generalization, with DSC scores of 93 for SAH, 93 for SDH, 92 for EDH, 90 for CC, 88 for IVH, and 92 for ICH. IoU values were also high, indicating precise segmentation and minimal boundary errors. Conclusions The ResUNet model outperformed standard U-Net variants, achieving higher multi-label segmentation accuracy. This makes it a valuable tool for clinical applications that require fast and reliable brain hemorrhage analysis. Future research could investigate semi-supervised techniques and 3D segmentation to further enhance clinical use. Clinical trial number Not applicable.https://doi.org/10.1186/s12911-025-03131-3CTBrain hemorrhageSegmentationAttention-based residual U-NetDeep learningMedical imaging |
| spellingShingle | Xinxin Lin Enmiao Zou Wenci Chen Xinxin Chen Le Lin Advanced multi-label brain hemorrhage segmentation using an attention-based residual U-Net model BMC Medical Informatics and Decision Making CT Brain hemorrhage Segmentation Attention-based residual U-Net Deep learning Medical imaging |
| title | Advanced multi-label brain hemorrhage segmentation using an attention-based residual U-Net model |
| title_full | Advanced multi-label brain hemorrhage segmentation using an attention-based residual U-Net model |
| title_fullStr | Advanced multi-label brain hemorrhage segmentation using an attention-based residual U-Net model |
| title_full_unstemmed | Advanced multi-label brain hemorrhage segmentation using an attention-based residual U-Net model |
| title_short | Advanced multi-label brain hemorrhage segmentation using an attention-based residual U-Net model |
| title_sort | advanced multi label brain hemorrhage segmentation using an attention based residual u net model |
| topic | CT Brain hemorrhage Segmentation Attention-based residual U-Net Deep learning Medical imaging |
| url | https://doi.org/10.1186/s12911-025-03131-3 |
| work_keys_str_mv | AT xinxinlin advancedmultilabelbrainhemorrhagesegmentationusinganattentionbasedresidualunetmodel AT enmiaozou advancedmultilabelbrainhemorrhagesegmentationusinganattentionbasedresidualunetmodel AT wencichen advancedmultilabelbrainhemorrhagesegmentationusinganattentionbasedresidualunetmodel AT xinxinchen advancedmultilabelbrainhemorrhagesegmentationusinganattentionbasedresidualunetmodel AT lelin advancedmultilabelbrainhemorrhagesegmentationusinganattentionbasedresidualunetmodel |