EUVIMEDEUVIMED entdecken
Open Access · CC BY 4.0

Point‐Guided Latent Diffusion Model for Novel View Synthesis in Laparoscopic Liver Surgery

Wenzhe Tang, Tao Chen, Yamid Espinel, Shahid Farid, Emmanuel Buc, Adrien Bartoli, Sharib Ali iD

Healthcare Technology Letters · 2025-01 · 12 (1)

DOI: 10.1049/htl2.70032 ↗

Kurz gefasst

Fachartikel in der Zeitschrift Healthcare Technology Letters, online erschienen am 18.11.2025. Verfasst von Wenzhe Tang und 6 weiteren Autor:innen. Beteiligte Einrichtung: School of Computer Science, Faculty of Engineering and Physical Sciences University of Leeds Leeds UK. Die Arbeit nennt 53 Literaturangaben. Der Volltext ist frei zugänglich (Open Access, CC BY 4.0). Gefördert von: Leeds Biomedical Research Centre, Engineering and Physical Sciences Research Council, National Institute for Health and Care Research.

AbstractSchlagwörterBibliografische AngabenZitierenVerwandte Studien

Abstract (Originalsprache)

Despite recent progress in diffusion‐based video synthesis, synthesizing accurate novel views from sparse input frames in laparoscopic liver surgery remains challenging due to occlusions, complex shape of anatomical structures and limited field of views. We propose point‐guided latent diffusion model, specifically designed for generating high‐quality intermediate frames in laparoscopic liver surgery from only the first and last video frames. Our method leverages the powerful generative capability of latent diffusion models combined with geometric cues from 3D point clouds reconstructed via dense stereo matching. To robustly handle occlusions and shape deformation, we use an adaptive camera trajectory planning strategy based on next‐best‐view algorithms. Furthermore, we introduce a spatial‐transformer enhanced decoder to effectively preserve detailed anatomical features from reference frames and minimize visual artefacts in generated views. Extensive experiments on the clinically relevant P2ILF challenge dataset validate our method's effectiveness and superior performance in producing visually coherent and structurally accurate novel views, highlighting its ability for enhancing the quality of surgical scene reconstruction.

Schlagwörter

Stichwörter der Autor:innen

computer visionimage reconstructionlivermedical image processing

Autor:innen und Institutionen

  • School of Computer Science, Faculty of Engineering and Physical Sciences University of Leeds Leeds UK.
  • Centre Hospitalier Universitaire de Clermont-Ferrand Clermont-Ferrand France.
  • Department of HPB and Transplant Surgery St. James's University Hospital Leeds UK.
  • Endoscopy and Computer Vision Group Université Clermont Auvergne Clermont-Ferrand France.

ORCID-Profile: Sharib Ali

Förderung

  • Leeds Biomedical Research Centre
  • Engineering and Physical Sciences Research Council
  • National Institute for Health and Care Research

Zitieren

APA

Tang, W., Chen, T., Espinel, Y., Farid, S., Buc, E., Bartoli, A., & Ali, S. (2025). Point‐Guided Latent Diffusion Model for Novel View Synthesis in Laparoscopic Liver Surgery. Healthcare Technology Letters, 12(1). https://doi.org/10.1049/htl2.70032

Vancouver

Tang W, Chen T, Espinel Y, Farid S, Buc E, Bartoli A, et al. Point‐Guided Latent Diffusion Model for Novel View Synthesis in Laparoscopic Liver Surgery. Healthcare Technology Letters. 2025;12(1). doi:10.1049/htl2.70032

BibTeX
@article{Tang2025,
  author = {Tang, Wenzhe and Chen, Tao and Espinel, Yamid and Farid, Shahid and Buc, Emmanuel and Bartoli, Adrien and Ali, Sharib},
  title = {Point‐Guided Latent Diffusion Model for Novel View Synthesis in Laparoscopic Liver Surgery},
  journal = {Healthcare Technology Letters},
  year = {2025},
  volume = {12},
  number = {1},
  doi = {10.1049/htl2.70032}
}
Kostenlos starten →