Dual Attention Residual U-Net for Accurate Brain Ultrasound Segmentation in IVH Detection

2025/05/23 by Yuan, Dan, Feng, Yi, Tang, Ziyun
#Artificial Intelligence (cs.AI) #Computer Vision and Pattern Recognition (cs.CV) #FOS: Computer and information sciences #FOS: Electrical engineering #Image and Video Processing (eess.IV) #electronic engineering #information engineering

paper · doi:10.48550/arxiv.2505.17683

Abstract

Intraventricular hemorrhage (IVH) is a severe neurological complication among premature infants, necessitating early and accurate detection from brain ultrasound (US) images to improve clinical outcomes. While recent deep learning methods offer promise for computer-aided diagnosis, challenges remain in capturing both local spatial details and global contextual dependencies critical for segmenting brain anatomies. In this work, we propose an enhanced Residual U-Net architecture incorporating two complementary attention mechanisms: the Convolutional Block Attention Module (CBAM) and a Sparse Attention Layer (SAL). The CBAM improves the model's ability to refine spatial and channel-wise features, while the SAL introduces a dual-branch design, sparse attention filters out low-confidence query-key pairs to suppress noise, and dense attention ensures comprehensive information propagation. Extensive experiments on the Brain US dataset demonstrate that our method achieves state-of-the-art segmentation performance, with a Dice score of 89.04% and IoU of 81.84% for ventricle region segmentation. These results highlight the effectiveness of integrating spatial refinement and attention sparsity for robust brain anatomy detection. Code is available at: https://github.com/DanYuan001/BrainImgSegment.

Citations

• IMAGGarment: Fine-Grained Garment Generation for Controllable Fashion Design
• Long-Term TalkingFace Generation via Motion-Prior Conditional Diffusion Model
• IMAGDressing-v1: Customizable Virtual Dressing
• A Study on ReLU and Softmax in Transformer
• Sparse Attention with Linear Units
• Medical Transformer: Gated Axial-Attention for Medical Image Segmentation
• An Image is Worth 16x16 Words: Transformers for Image Recognition at Scale
• KiU-Net: Towards Accurate Segmentation of Biomedical Images using\n Over-complete Representations
• UNet 3+: A Full-Scale Connected UNet for Medical Image Segmentation
• UNet 3+: A Full-Scale Connected UNet for Medical Image Segmentation
• Axial-DeepLab: Stand-Alone Axial-Attention for Panoptic Segmentation
• Deep Learning in Medical Ultrasound Image Segmentation: a Review
• Learning to Segment Brain Anatomy from 2D Ultrasound with Less Data
• UNet++: A Nested U-Net Architecture for Medical Image Segmentation
• CBAM: Convolutional Block Attention Module
• Attention U-Net: Learning Where to Look for the Pancreas
• Squeeze-and-Excitation Networks
• V-Net: Fully Convolutional Neural Networks for Volumetric Medical Image Segmentation
• SegNet: A Deep Convolutional Encoder-Decoder Architecture for Image Segmentation
• U-Net: Convolutional Networks for Biomedical Image Segmentation

Related

• Learning to Segment Brain Anatomy from 2D Ultrasound with Less Data
• EUIS-Net: A Convolutional Neural Network for Efficient Ultrasound Image Segmentation
• CV-Attention UNet: Attention-based UNet for 3D Cerebrovascular Segmentation of Enhanced TOF-MRA Images
• MGA-Net: A Novel Mask-Guided Attention Neural Network for Precision Neonatal Brain Imaging
• UESA-Net: U-Shaped Embedded Multidirectional Shrinkage Attention Network for Ultrasound Nodule Segmentation