{"ID":2872158,"CreatedAt":"2026-06-01T04:54:23.091178241Z","UpdatedAt":"2026-06-01T04:54:23.091178241Z","DeletedAt":null,"paper_url":"https://arxiv.org/abs/2509.09327","arxiv_id":"2509.09327","title":"Exploring Pre-training Across Domains for Few-Shot Surgical Skill Assessment","abstract":"Automated surgical skill assessment (SSA) is a central task in surgical computer vision. Developing robust SSA models is challenging due to the scarcity of skill annotations, which are time-consuming to produce and require expert consensus. Few-shot learning (FSL) offers a scalable alternative enabling model development with minimal supervision, though its success critically depends on effective pre-training. While widely studied for several surgical downstream tasks, pre-training has remained largely unexplored in SSA. In this work, we formulate SSA as a few-shot task and investigate how self-supervised pre-training strategies affect downstream few-shot SSA performance. We annotate a publicly available robotic surgery dataset with Objective Structured Assessment of Technical Skill (OSATS) scores, and evaluate various pre-training sources across three few-shot settings. We quantify domain similarity and analyze how domain gap and the inclusion of procedure-specific data into pre-training influence transferability. Our results show that small but domain-relevant datasets can outperform large scale, less aligned ones, achieving accuracies of 60.16%, 66.03%, and 73.65% in the 1-, 2-, and 5-shot settings, respectively. Moreover, incorporating procedure-specific data into pre-training with a domain-relevant external dataset significantly boosts downstream performance, with an average gain of +1.22% in accuracy and +2.28% in F1-score; however, applying the same strategy with less similar but large-scale sources can instead lead to performance degradation. Code and models are available at https://github.com/anastadimi/ssa-fsl.","short_abstract":"Automated surgical skill assessment (SSA) is a central task in surgical computer vision. Developing robust SSA models is challenging due to the scarcity of skill annotations, which are time-consuming to produce and require expert consensus. Few-shot learning (FSL) offers a scalable alternative enabling model developmen...","url_abs":"https://arxiv.org/abs/2509.09327","url_pdf":"https://arxiv.org/pdf/2509.09327v1","authors":"[\"Dimitrios Anastasiou\",\"Razvan Caramalau\",\"Nazir Sirajudeen\",\"Matthew Boal\",\"Philip Edwards\",\"Justin Collins\",\"John Kelly\",\"Ashwin Sridhar\",\"Maxine Tran\",\"Faiz Mumtaz\",\"Nevil Pavithran\",\"Nader Francis\",\"Danail Stoyanov\",\"Evangelos B. Mazomenos\"]","published":"2025-09-11T10:23:19Z","proceeding":"cs.CV","tasks":"[\"cs.CV\",\"cs.LG\"]","methods":"[]","has_code":false,"code_links":[{"ID":609948,"CreatedAt":"2026-06-01T04:54:23.091178241Z","UpdatedAt":"2026-06-01T04:54:23.091178241Z","DeletedAt":null,"paper_id":2872158,"paper_url":"https://arxiv.org/abs/2509.09327","paper_title":"Exploring Pre-training Across Domains for Few-Shot Surgical Skill Assessment","repo_url":"https://github.com/anastadimi/ssa-fsl","is_official":false,"mentioned_in_paper":false,"mentioned_in_github":true,"github_stars":0}]}