Attention-enhanced TransUNet for ultrasound liver parenchyma segmentation toward assessment of schistosomiasis-associated liver disease
Technology and Health Care · 18.11.2026
DOI: 10.1177/09287329261506929 ↗Kurz gefasst
Fachartikel in der Zeitschrift Technology and Health Care, online erschienen am 18.11.2026. Verfasst von Lifeng Gao und 4 weiteren Autor:innen. Beteiligte Einrichtung: Hubei Key Laboratory of Cognitive and Affective Disorders, Institute of Biomedical Sciences, School of Medicine, Jianghan University, Wuhan, China. Die Arbeit nennt 40 Literaturangaben. Gefördert von: Hubei Provincial Laboratory Animal Science and Technology Program, National Natural Science Foundation of China.
Abstract (Originalsprache)
Background
Schistosomiasis-associated liver disease is the most common clinical form of chronic schistosomiasis. Chronic hepatic schistosomiasis is mainly manifested as liver fibrosis, cirrhosis and other liver dysfunction, and even induces liver cancer in the late stage. Ultrasound is widely used for the diagnosis of schistosomiasis-associated liver disease, grading of liver fibrosis, and assessment of of therapeutic effects.
Objective
The study aims to detect and segment the ultrasound liver parenchyma with high accuracy.
Methods
We propose an attention-enhanced TransUNet that improves skip-connection feature transfer by integrating axial attention with residual connections, while retaining the Vision Transformer module for global context modeling. Axial attention re-weights features along spatial axes to emphasize direction-sensitive structures such as liver boundaries, and residual refinement mitigates information degradation during multi-scale fusion. We compared the proposed method against UNet and the original TransUNet using Dice, IoU, and Sensitivity. Ablation studies further demonstrated that combining axial attention with residual connection outperformed axial attention alone.
Results
The proposed model achieved a satisfactory performance in the delineation of the ultrasound liver parenchyma region, with a Dice coefficient of 0.965, an IoU of 0.931 and a Sensitivity value of 0.970.
Conclusion
The results support the feasibility of the attention-enhanced TransUNet model as an upstream module for accurate ultrasound image analysis in schistosomiasis-associated liver disease such as fibrosis staging and cirrhosis.
Schlagwörter
Stichwörter der Autor:innen
Autor:innen und Institutionen
- Hubei Key Laboratory of Cognitive and Affective Disorders, Institute of Biomedical Sciences, School of Medicine, Jianghan University, Wuhan, China.
- School of Artificial Intelligence, Jianghan University, Wuhan, China.
- Department of Ultrasonic Imaging, Wuhan Daishan Hospital, Wuhan, China.
- State Key Laboratory of Magnetic Resonance Spectroscopy and Imaging, National Center for Magnetic Resonance in Wuhan, Innovation Academy for Precision Measurement Science and Technology, Chinese Academy of Sciences, Wuh…
ORCID-Profile: Lifeng Gao
Förderung
- Hubei Provincial Laboratory Animal Science and Technology Program
- National Natural Science Foundation of China
Zitieren
APA
Gao, L., Li, Y., Sun, P., Wang, X., & Ye, F. (2026). Attention-enhanced TransUNet for ultrasound liver parenchyma segmentation toward assessment of schistosomiasis-associated liver disease. Technology and Health Care. https://doi.org/10.1177/09287329261506929
Vancouver
Gao L, Li Y, Sun P, Wang X, Ye F. Attention-enhanced TransUNet for ultrasound liver parenchyma segmentation toward assessment of schistosomiasis-associated liver disease. Technology and Health Care. 2026. doi:10.1177/09287329261506929
BibTeX
@article{Gao2026,
author = {Gao, Lifeng and Li, Yaojuan and Sun, Ping and Wang, Xuxia and Ye, Feng},
title = {Attention-enhanced TransUNet for ultrasound liver parenchyma segmentation toward assessment of schistosomiasis-associated liver disease},
journal = {Technology and Health Care},
year = {2026},
doi = {10.1177/09287329261506929}
}
EUVIMED