Optimizing latent graph representations of surgical scenes for unseen domain generalization
International Journal of Computer Assisted Radiology and Surgery · 2024
DOI: 10.1007/s11548-024-03121-2 ↗Kurz gefasst
Multizentrische Studie in der Zeitschrift International Journal of Computer Assisted Radiology and Surgery, 2024. Verfasst von Siddhant Satyanaik und 5 weiteren Autor:innen. Beteiligte Einrichtung: ICube, University of Strasbourg, CNRS, Strasbourg, France. Hauptthemen laut MEDLINE: Cholecystectomy, Laparoscopic. Die Arbeit wurde bisher 6-mal zitiert (Crossref) und nennt 22 Literaturangaben. Gefördert von: Agence Nationale de la Recherche.
Abstract (Originalsprache)
PURPOSE: Advances in deep learning have resulted in effective models for surgical video analysis; however, these models often fail to generalize across medical centers due to domain shift caused by variations in surgical workflow, camera setups, and patient demographics. Recently, object-centric learning has emerged as a promising approach for improved surgical scene understanding, capturing and disentangling visual and semantic properties of surgical tools and anatomy to improve downstream task performance. In this work, we conduct a multicentric performance benchmark of object-centric approaches, focusing on critical view of safety assessment in laparoscopic cholecystectomy, then propose an improved approach for unseen domain generalization. METHODS: We evaluate four object-centric approaches for domain generalization, establishing baseline performance. Next, leveraging the disentangled nature of object-centric representations, we dissect one of these methods through a series of ablations (e.g., ignoring either visual or semantic features for downstream classification). Finally, based on the results of these ablations, we develop an optimized method specifically tailored for domain generalization, LG-DG, that includes a novel disentanglement loss function. RESULTS: Our optimized approach, LG-DG, achieves an improvement of 9.28% over the best baseline approach. More broadly, we show that object-centric approaches are highly effective for domain generalization thanks to their modular approach to representation learning. CONCLUSION: We investigate the use of object-centric methods for unseen domain generalization, identify method-agnostic factors critical for performance, and present an optimized approach that substantially outperforms existing methods.
Schlagwörter
MeSH-Schlagwörter (MEDLINE)
Stichwörter der Autor:innen
Autor:innen und Institutionen
- ICube, University of Strasbourg, CNRS, Strasbourg, France.
- ICube, University of Strasbourg, CNRS, Strasbourg, France. murali@unistra.fr.
- West China Hospital of Sichuan University, Chengdu, China.
- IHU, Strasbourg, France.
- Fondazione Policlinico Universitario A. Gemelli IRCCS, Rome, Italy.
Förderung
- Agence Nationale de la Recherche
Zitieren
APA
Satyanaik, S., Murali, A., Alapatt, D., Wang, X., Mascagni, P., & Padoy, N. (2024). Optimizing latent graph representations of surgical scenes for unseen domain generalization. International Journal of Computer Assisted Radiology and Surgery. https://doi.org/10.1007/s11548-024-03121-2
Vancouver
Satyanaik S, Murali A, Alapatt D, Wang X, Mascagni P, Padoy N. Optimizing latent graph representations of surgical scenes for unseen domain generalization. International Journal of Computer Assisted Radiology and Surgery. 2024. doi:10.1007/s11548-024-03121-2
BibTeX
@article{Satyanaik2024,
author = {Satyanaik, Siddhant and Murali, Aditya and Alapatt, Deepak and Wang, Xin and Mascagni, Pietro and Padoy, Nicolas},
title = {Optimizing latent graph representations of surgical scenes for unseen domain generalization},
journal = {International Journal of Computer Assisted Radiology and Surgery},
year = {2024},
doi = {10.1007/s11548-024-03121-2}
}
EUVIMED