SEG-LUS: A novel ultrasound segmentation method for liver and its accessory structures based on muti-head self-attention

Although liver ultrasound (US) is quick and convenient, it presents challenges due to patient variations. Previous research has predominantly focused on computer-aided diagnosis (CAD), particularly for disease analysis. However, characterizing liver US images is complex due to structural diversity and a limited number of samples. Normal liver US images are crucial, especially for standard section diagnosis. This study explicitly addresses Liver US standard sections (LUSS) and involves detailed labeling of eight anatomical structures. We propose SEG-LUS, a US image segmentation model for the liver and its accessory structures. In SEG-LUS, we have adopted the shifted windows feature encoder combined with the cross-attention mechanism to adapt to capturing image information at different scales and resolutions and address context mismatch and sample imbalance in the segmentation task. By introducing the UUF module, we achieve the perfect fusion of shallow and deep information, making the information retained by the network in the feature extraction process more comprehensive. We have improved the Focal Loss to tackle the imbalance of pixel-level distribution. The results show that the SEG-LUS model exhibits significant performance improvement, with mPA, mDice, mIOU, and mASD reaching 85.05%, 82.60%, 74.92%, and 0.31, respectively. Compared with seven state-of-the-art semantic segmentation methods, the mPA improves by 5.32%. SEG-LUS is positioned to serve as a crucial reference for research in computer-aided modeling using liver US images, thereby advancing the field of US medicine research. •We propose SEG-LUS, a semantic segmentation model for liver ultrasound diagnostic and therapeutic processes. It is the sole model applicable to LUSS recognition, effectively representing key anatomical structures during clinical scanning.•Introducing a hybrid attention mechanism, Cross Shift-window MSA (CSW-MSA), combined with UUF for liver ultrasound analysis, achieves top performance on an LUSS dataset with eight key anatomical structures.•Compared with seven other leading segmentation methods, we achieve a 4.5% lead over the baseline average. Results include mPA 85.05%, mDice 82.60%, mIOU 74.92%, and mASD 0.31. This provides an effective design reference for automated computer-aided modeling based on liver ultrasound data.