EUVIMEDEUVIMED entdecken
Open Access · CC BY 4.0

Surgical-DINO: adapter learning of foundation models for depth estimation in endoscopic surgery

Beilei Cui, Mobarakol Islam, Long Bai, Hongliang Ren

International Journal of Computer Assisted Radiology and Surgery · 08.03.2024 · 19 (6) · 1013-1020

DOI: 10.1007/s11548-024-03083-5 ↗

Kurz gefasst

Fachartikel in der Zeitschrift International Journal of Computer Assisted Radiology and Surgery, online erschienen am 08.03.2024. Verfasst von Beilei Cui und 3 weiteren Autor:innen. Beteiligte Einrichtung: The Chinese University of Hong Kong, Hong Kong, China. Hauptthemen laut MEDLINE: Imaging, Three-Dimensional. Die Arbeit wurde bisher 65-mal zitiert (Crossref) und nennt 25 Literaturangaben. Der Volltext ist frei zugänglich (Open Access, CC BY 4.0). Gefördert von: Hong Kong Research Grants Council (RGC) Collaborative Research Fund and General Research Fund, Shenzhen-Hong Kong-Macau Technology Research Programme (Type C) STIC Grant SGDX20210823103535014.

AbstractSchlagwörterBibliografische AngabenZitierenVerwandte Studien

Abstract (Originalsprache)

Purpose

Depth estimation in robotic surgery is vital in 3D reconstruction, surgical navigation and augmented reality visualization. Although the foundation model exhibits outstanding performance in many vision tasks, including depth estimation (e.g., DINOv2), recent works observed its limitations in medical and surgical domain-specific applications. This work presents a low-ranked adaptation (LoRA) of the foundation model for surgical depth estimation.

Methods

We design a foundation model-based depth estimation method, referred to as Surgical-DINO, a low-rank adaptation of the DINOv2 for depth estimation in endoscopic surgery. We build LoRA layers and integrate them into DINO to adapt with surgery-specific domain knowledge instead of conventional fine-tuning. During training, we freeze the DINO image encoder, which shows excellent visual representation capacity, and only optimize the LoRA layers and depth decoder to integrate features from the surgical scene.

Results

Our model is extensively validated on a MICCAI challenge dataset of SCARED, which is collected from da Vinci Xi endoscope surgery. We empirically show that Surgical-DINO significantly outperforms all the state-of-the-art models in endoscopic depth estimation tasks. The analysis with ablation studies has shown evidence of the remarkable effect of our LoRA layers and adaptation.

Conclusion

Surgical-DINO shed some light on the successful adaptation of the foundation models into the surgical domain for depth estimation. There is clear evidence in the results that zero-shot prediction on pre-trained weights in computer vision datasets or naive fine-tuning is not sufficient to use the foundation model in the surgical domain directly.

Schlagwörter

MeSH-Schlagwörter (MEDLINE)

Imaging, Three-DimensionalHumansRobotic Surgical ProceduresEndoscopySurgery, Computer-AssistedDepth Perception

Stichwörter der Autor:innen

Adapter learningDepth estimationFoundation modelsSurgical scene understanding

Autor:innen und Institutionen

  • The Chinese University of Hong Kong, Hong Kong, China.
  • Wellcome/EPSRC Centre for Interventional and Surgical Sciences (WEISS), University College London, London, UK.
  • The Chinese University of Hong Kong, Hong Kong, China. hlren@ee.cuhk.edu.hk.
  • Department of BME, National University of Singapore, Singapore, Singapore. hlren@ee.cuhk.edu.hk.

Förderung

  • Hong Kong Research Grants Council (RGC) Collaborative Research Fund and General Research Fund
  • Shenzhen-Hong Kong-Macau Technology Research Programme (Type C) STIC Grant SGDX20210823103535014

Zitieren

APA

Cui, B., Islam, M., Bai, L., & Ren, H. (2024). Surgical-DINO: adapter learning of foundation models for depth estimation in endoscopic surgery. International Journal of Computer Assisted Radiology and Surgery, 19(6), 1013-1020. https://doi.org/10.1007/s11548-024-03083-5

Vancouver

Cui B, Islam M, Bai L, Ren H. Surgical-DINO: adapter learning of foundation models for depth estimation in endoscopic surgery. International Journal of Computer Assisted Radiology and Surgery. 2024;19(6):1013-1020. doi:10.1007/s11548-024-03083-5

BibTeX
@article{Cui2024,
  author = {Cui, Beilei and Islam, Mobarakol and Bai, Long and Ren, Hongliang},
  title = {Surgical-DINO: adapter learning of foundation models for depth estimation in endoscopic surgery},
  journal = {International Journal of Computer Assisted Radiology and Surgery},
  year = {2024},
  volume = {19},
  number = {6},
  pages = {1013--1020},
  doi = {10.1007/s11548-024-03083-5}
}
Kostenlos starten →