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 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.

Keywords: Attention-based residual U-Net; Brain hemorrhage; CT; Deep learning; Medical imaging; Segmentation.

Fig. 1

Study flowchart detailing the workflow from dataset acquisition to model evaluation

Fig. 2

Examples of manual segmentation highlighting the six brain hemorrhage subtypes: SAH, SDH, EDH, CC, IVH, and ICH

Fig. 3

The architecture of the ResUNet

Fig. 4

Comparison of dice coefficient scores for training and test datasets across different hemorrhage subtypes

Fig. 5

Comparison of IoU (Intersection over Union) scores for training and test datasets across different hemorrhage subtypes

Fig. 6

Dice coefficient scores during training phase for different hemorrhage subtypes over 250 epochs

Fig. 7

Dice coefficient scores on test dataset for different hemorrhage subtypes after training

Fig. 8

IoU scores during training phase for different hemorrhage subtypes over 250 epochs

Fig. 9

IoU scores on test dataset for different hemorrhage subtypes over 250 epochs

Fig. 10

Representative patient CT images with overlaid segmentation results showing predicted regions compared to ground truth