EUVIMEDEUVIMED entdecken
Open Access · CC BY 4.0

GeoTranMesh: a geometry-guided multi-branch mesh transformer for 3d liver segmentation

Jiaming Feng, Xukun Zhang, Shahid Farid, Sharib Ali

International Journal of Computer Assisted Radiology and Surgery · 06.04.2026 · 21 (5) · 929-938

DOI: 10.1007/s11548-026-03600-8 ↗

Kurz gefasst

Fachartikel in der Zeitschrift International Journal of Computer Assisted Radiology and Surgery, online erschienen am 06.04.2026. Verfasst von Jiaming Feng und 3 weiteren Autor:innen. Beteiligte Einrichtung: AI in Medicine and Surgery Group, School of Computer Science, University of Leeds, LS2 9JT, Leeds, UK. Hauptthemen laut MEDLINE: Imaging, Three-Dimensional, Liver, Anatomic Landmarks, Tomography, X-Ray Computed. Die Arbeit nennt 13 Literaturangaben. Der Volltext ist frei zugänglich (Open Access, CC BY 4.0). Gefördert von: Engineering and Physical Sciences Research Council.

AbstractSchlagwörterBibliografische AngabenZitierenVerwandte Studien

Abstract (Originalsprache)

Purpose

Anatomical landmarks on the liver surface, such as the falciform ligament and hepatic ridge, exhibit complex geometry and significant morphological variability. Accurate segmentation of these structures on 3D liver mesh is essential for intraoperative navigation. This paper presents GeoTranMesh, a geometry-guided multi-branch mesh Transformer that employs hierarchical encoding–decoding and global geometric modeling to achieve high-precision liver mesh segmentation.

Methods

A hybrid attention mechanism is proposed to fuse local geometric features with cross-branch contextual information, while a directional multi-branch fusion module refines features along tangent, normal, and bitangent directions to enhance geometric consistency. In addition, geometry-guided multi-task supervision, including boundary, distance, and normal regression, is incorporated to strengthen morphological feature learning.

Results

On liver mesh dataset, GeoTranMesh achieved the highest segmentation accuracy, with Dice scores of 30.9% and 66.4% for the falciform ligament and liver ridge, respectively, an overall Dice of 59.5%, and a Chamfer distance of only 4.4 mm, demonstrating superior geometric consistency and anatomical precision.

Conclusion

GeoTranMesh integrates hybrid attention and directional multi-branch fusion to enhance geometric consistency and morphological feature learning, achieving precise segmentation of complex anatomical landmarks, demonstrating potential for clinical and AR-guided liver surgery applications.

Schlagwörter

MeSH-Schlagwörter (MEDLINE)

Imaging, Three-DimensionalLiverAnatomic LandmarksTomography, X-Ray ComputedSurgery, Computer-AssistedHumansAlgorithms

Stichwörter der Autor:innen

3D landmark segmentationAR-guided surgeryLiver surfaceMesh transformer

Autor:innen und Institutionen

  • AI in Medicine and Surgery Group, School of Computer Science, University of Leeds, LS2 9JT, Leeds, UK.
  • Department of Diagnostic Radiology, Li Ka Shing Faculty of Medicine, The University of Hong Kong, Pok Fu Lam, Hong Kong.
  • Department of HPB and Transplant Surgery, St. James's University Hospital, Leeds, UK.
  • AI in Medicine and Surgery Group, School of Computer Science, University of Leeds, LS2 9JT, Leeds, UK. s.s.ali@leeds.ac.uk.

Förderung

  • Engineering and Physical Sciences Research Council

Zitieren

APA

Feng, J., Zhang, X., Farid, S., & Ali, S. (2026). GeoTranMesh: a geometry-guided multi-branch mesh transformer for 3d liver segmentation. International Journal of Computer Assisted Radiology and Surgery, 21(5), 929-938. https://doi.org/10.1007/s11548-026-03600-8

Vancouver

Feng J, Zhang X, Farid S, Ali S. GeoTranMesh: a geometry-guided multi-branch mesh transformer for 3d liver segmentation. International Journal of Computer Assisted Radiology and Surgery. 2026;21(5):929-938. doi:10.1007/s11548-026-03600-8

BibTeX
@article{Feng2026,
  author = {Feng, Jiaming and Zhang, Xukun and Farid, Shahid and Ali, Sharib},
  title = {GeoTranMesh: a geometry-guided multi-branch mesh transformer for 3d liver segmentation},
  journal = {International Journal of Computer Assisted Radiology and Surgery},
  year = {2026},
  volume = {21},
  number = {5},
  pages = {929--938},
  doi = {10.1007/s11548-026-03600-8}
}
Kostenlos starten →