UCL Discovery
UCL home » Library Services » Electronic resources » UCL Discovery

Training-free temporal object tracking in surgical videos

Koley, Subhadeep; Kadkhodamohammadi, Abdolrahim; Barbarisi, Santiago; Stoyanov, Danail; Luengo, Imanol; (2025) Training-free temporal object tracking in surgical videos. Training-free temporal object tracking in surgical videos 10.1007/s11548-025-03349-6. (In press).

[thumbnail of Stoyanov_training_free_temporal_mask Subhadeep.pdf] Text
Stoyanov_training_free_temporal_mask Subhadeep.pdf
Access restricted to UCL open access staff until 2 April 2026.

Download (42MB)

Abstract

Purpose: In this paper, we present a novel approach for online object tracking in laparoscopic cholecystectomy (LC) surgical videos, targeting localisation and tracking of critical anatomical structures and instruments. Our method addresses the challenges of costly pixel-level annotations and label inconsistencies inherent in existing datasets.// Methods: Leveraging the inherent object localisation capabilities of pre-trained text-to-image diffusion models, we extract representative features from surgical frames without any training or fine-tuning. Our tracking framework uses these features, along with cross-frame interactions via an affinity matrix inspired by query-key-value attention, to ensure temporal continuity in the tracking process.// Results: Through a pilot study, we first demonstrate that diffusion features exhibit superior object localisation and consistent semantics across different decoder levels and temporal frames. Later, we perform extensive experiments to validate the effectiveness of our approach, showcasing its superiority over competitors for the task of temporal object tracking. Specifically, we achieve a per-pixel classification accuracy of , mean Jaccard score of , and mean F-score of on the publicly available CholeSeg8K dataset.// Conclusion: Our work not only introduces a novel application of text-to-image diffusion models but also contributes to advancing the field of surgical video analysis, offering a promising avenue for accurate and cost-effective temporal object tracking in minimally invasive surgery videos.

Type: Article
Title: Training-free temporal object tracking in surgical videos
Location: Germany
DOI: 10.1007/s11548-025-03349-6
Publisher version: https://doi.org/10.1007/s11548-025-03349-6
Language: English
Additional information: This version is the author-accepted manuscript. For information on re-use, please refer to the publisher’s terms and conditions.
Keywords: Medical imaging, Diffusion model, Object tracking, Training free
UCL classification: UCL
UCL > Provost and Vice Provost Offices > UCL BEAMS
UCL > Provost and Vice Provost Offices > UCL BEAMS > Faculty of Engineering Science > Dept of Computer Science
URI: https://discovery.ucl.ac.uk/id/eprint/10207819
Downloads since deposit
1Download
Download activity - last month
Download activity - last 12 months
Downloads by country - last 12 months

Archive Staff Only

View Item View Item