All Attention U-NET for Semantic Segmentation of Intracranial Hemorrhages In Head CT Images
This work addresses a domain-specific medical imaging problem for specialists diagnosing intracranial hemorrhages, representing an incremental improvement with a novel method for a known bottleneck.
The paper tackled the problem of segmenting intracranial hemorrhages in head CT images, where types have diverse shapes within the same category and confusing similarities between types, by proposing an all attention U-Net that achieved up to a 31.8% improvement over the baseline ResNet50 + U-Net.
Intracranial hemorrhages in head CT scans serve as a first line tool to help specialists diagnose different types. However, their types have diverse shapes in the same type but similar confusing shape, size and location between types. To solve this problem, this paper proposes an all attention U-Net. It uses channel attentions in the U-Net encoder side to enhance class specific feature extraction, and space and channel attentions in the U-Net decoder side for more accurate shape extraction and type classification. The simulation results show up to a 31.8\% improvement compared to baseline, ResNet50 + U-Net, and better performance than in cases with limited attention.