Liver mask-guided SAM-enhanced dual-decoder network for landmark segmentation in AR-guided surgery
International Journal of Computer Assisted Radiology and Surgery · 2025
DOI: 10.1007/s11548-025-03516-9 ↗Kurz gefasst
Fachartikel in der Zeitschrift International Journal of Computer Assisted Radiology and Surgery, 2025. Verfasst von Xukun Zhang und 7 weiteren Autor:innen. Beteiligte Einrichtung: Academy for Engineering and Technology, Fudan University, Shanghai, 200082, China. Hauptthemen laut MEDLINE: Surgery, Computer-Assisted, Liver, Laparoscopy, Augmented Reality. Die Arbeit wurde bisher 1-mal zitiert (Crossref) und nennt 17 Literaturangaben. Gefördert von: School of Medicine, Stanford University.
Abstract (Originalsprache)
PURPOSE: In augmented reality (AR)-guided laparoscopic liver surgery, accurate segmentation of liver landmarks is crucial for precise 3D-2D registration. However, existing methods struggle with complex structures, limited data, and class imbalance. In this study, we propose a novel approach to improve landmark segmentation performance by leveraging liver mask prediction. METHODS: We propose a dual-decoder model enhanced by a pre-trained segment anything model (SAM) encoder, where one decoder segments the liver and the other focuses on liver landmarks. The SAM encoder provides robust features for liver mask prediction, improving generalizability. A liver-guided consistency constraint establishes fine-grained spatial consistency between liver regions and landmarks, enhancing segmentation accuracy through detailed spatial modeling. RESULTS: The proposed method achieved state-of-the-art performance in liver landmark segmentation on two public laparoscopic datasets. By addressing feature entanglement, the dual-decoder framework with SAM and consistency constraints significantly improved segmentation in complex surgical scenarios. CONCLUSION: The SAM-enhanced dual-decoder network, incorporating liver-guided consistency constraints, offers a promising solution for 2D landmark segmentation in AR-guided laparoscopic surgery. By mutually reinforcing liver mask and landmark segmentation, the method achieves improved accuracy and robustness for intraoperative applications.
Schlagwörter
MeSH-Schlagwörter (MEDLINE)
Stichwörter der Autor:innen
Autor:innen und Institutionen
- Academy for Engineering and Technology, Fudan University, Shanghai, 200082, China.
- School of Computer Science, University of Leeds, Leeds, LS2 9JT, UK.
- Liver Cancer Institute, Zhongshan Hospital, Fudan University, Shanghai, 200082, China. xiaoyingwang@fudan.edu.cn.
- Academy for Engineering and Technology, Fudan University, Shanghai, 200082, China. lihuazhang@fudan.edu.cn.
- Meta-Medical Center, Institute of Intelligent Medicine, Fudan University, Shanghai, 200032, China. lihuazhang@fudan.edu.cn.
Förderung
- School of Medicine, Stanford University
Zitieren
APA
Zhang, X., Ali, S., Kang, Y., Zhu, J., Han, M., Wang, L., Wang, X., & Zhang, L. (2025). Liver mask-guided SAM-enhanced dual-decoder network for landmark segmentation in AR-guided surgery. International Journal of Computer Assisted Radiology and Surgery. https://doi.org/10.1007/s11548-025-03516-9
Vancouver
Zhang X, Ali S, Kang Y, Zhu J, Han M, Wang L, et al. Liver mask-guided SAM-enhanced dual-decoder network for landmark segmentation in AR-guided surgery. International Journal of Computer Assisted Radiology and Surgery. 2025. doi:10.1007/s11548-025-03516-9
BibTeX
@article{Zhang2025,
author = {Zhang, Xukun and Ali, Sharib and Kang, Yanlan and Zhu, Jingyi and Han, Minghao and Wang, Le and Wang, Xiaoying and Zhang, Lihua},
title = {Liver mask-guided SAM-enhanced dual-decoder network for landmark segmentation in AR-guided surgery},
journal = {International Journal of Computer Assisted Radiology and Surgery},
year = {2025},
doi = {10.1007/s11548-025-03516-9}
}
EUVIMED