GH-UNet: group-wise hybrid convolution-VIT for robust medical image segmentation.
basic_science · Level V
Where this comes from
- Record sourced from PubMed, PMID 40640343.
- Also identified by DOI 10.1038/s41746-025-01829-2 and PMC identifier 12246149.
- Licence recorded as CC BY-NC-ND.
- Because redistribution is not established, this page shows the abstract only. Follow the links below for the full text.
Abstract
Medical image segmentation is vital for accurate diagnosis. While U-Net-based models are effective, they struggle to capture long-range dependencies in complex anatomy. We propose GH-UNet, a Group-wise Hybrid Convolution-ViT model within the U-Net framework, to address this limitation. GH-UNet integrates a hybrid convolution-Transformer encoder for both local detail and global context modeling, a Group-wise Dynamic Gating (GDG) module for adaptive feature weighting, and a cascaded decoder for multi-scale integration. Both the encoder and GDG are modular, enabling compatibility with various CNN or ViT backbones. Extensive experiments on five public and one private dataset show GH-UNet consistently achieves superior performance. On ISIC2016, it surpasses H2Former with 1.37% and 1.94% gains in DICE and IOU, respectively, using only 38% of the parameters and 49.61% of the FLOPs. The code is freely accessible via: https://github.com/xiachashuanghua/GH-UNet .