Article Dans Une Revue International Journal of Computer Assisted Radiology and Surgery Année : 2025

Text-driven Adaptation of Foundation Models for Few-shot Surgical Workflow Analysis

Résumé

Purpose: Surgical workflow analysis is crucial for improving surgical efficiency and safety. However, previous studies rely heavily on large-scale annotated datasets, posing challenges in cost, scalability, and reliance on expert annotations. To address this, we propose Surg-FTDA (Few-shot Text-driven Adaptation), designed to handle various surgical workflow analysis tasks with minimal paired image–label data.Methods: Our approach has two key components. First, few-shot selection-based modality alignment selects a small subset of images and aligns their embeddings with text embeddings from the downstream task, bridging the modality gap. Second, text-driven adaptation leverages only text data to train a decoder, eliminating the need for paired image–text data. This decoder is then applied to aligned image embeddings, enabling image-related tasks without explicit image–text pairs.Results:We evaluate our approach on generative tasks (image captioning) and discriminative tasks (triplet recognition and phase recognition). Results show that Surg-FTDA outperforms baselines and generalizes well across downstream tasks.Conclusion: We propose a text-driven adaptation approach that mitigates the modality gap and handles multiple downstream tasks in surgical workflow analysis, with minimal reliance on large annotated datasets. The code and dataset will be released in https://github.com/CAMMApublic/Surg-FTDA.

Fichier principal
Vignette du fichier
s11548-025-03341-0.pdf (1.04 Mo) Télécharger le fichier
Origine Publication financée par une institution
Licence

Dates et versions

hal-04981199 , version 1 (15-07-2025)

Licence

Identifiants

Citer

Tingxuan Chen, Kun Yuan, Vinkle Srivastav, Nassir Navab, Nicolas Padoy. Text-driven Adaptation of Foundation Models for Few-shot Surgical Workflow Analysis. International Journal of Computer Assisted Radiology and Surgery, 2025, 20, pp.1175-1183. ⟨10.1007/s11548-025-03341-0⟩. ⟨hal-04981199⟩
312 Consultations
74 Téléchargements

Altmetric

Partager

  • More