HistoSeg++: Delving deeper with attention and multiscale feature fusion for biomarker segmentation
It addresses the need for improved multiscale context capture and upsampling in medical image segmentation, but the gains are incremental over existing Nested-UNet variants.
The paper proposes HistoSeg++, a Nested-UNet architecture with attention and multiscale feature fusion for biomarker segmentation, achieving superior generalization performance over existing Nested-UNet methods on three public benchmarks.
Segmentation of biomarkers in medical images is frequently viewed as a first step towards medical image analysis in any bioinformatics or biomedical application. Despite progress, existing methods still struggle to capture information at multiple scales and to perform upsampling effectively across different datasets. These shortcomings often result in suboptimal generalization capabilities. Recently, architectures belonging to the Nested-UNet family excel in capturing multiscale contextual information and upsample them effectively. In this work, We propose a novel Nested-UNet architecture that effectively captures multi-scale contextual information. It includes inner and outer attention units to enhance focus during upsampling, along with channel-wise feature recalibration using squeeze-and-excitation modules, leading to improved segmentation performance. Additionally, the architecture integrates an edge-aware loss to emphasize boundary accuracy by assigning greater importance to edge regions. Tested extensively on three publicly available benchmark datasets. Our method demonstrates a generalization performance superior to existing Nested-UNet methods. Code: https://github.com/saadwazir/histosegplusplus