Exploring Pre-training Across Domains for Few-Shot Surgical Skill Assessment
Fuente:
arXiv
Saved in:
| Main Authors: | , , , , , , , , , , , , , |
|---|---|
| Format: | Preprint |
| Published: |
2025
|
| Subjects: | |
| Online Access: | |
| Tags: |
Add Tag
No Tags, Be the first to tag this record!
|
| _version_ | 1866918139352055808 |
|---|---|
| author | Anastasiou, Dimitrios Caramalau, Razvan Sirajudeen, Nazir Boal, Matthew Edwards, Philip Collins, Justin Kelly, John Sridhar, Ashwin Tran, Maxine Mumtaz, Faiz Pavithran, Nevil Francis, Nader Stoyanov, Danail Mazomenos, Evangelos B. |
| author_facet | Anastasiou, Dimitrios Caramalau, Razvan Sirajudeen, Nazir Boal, Matthew Edwards, Philip Collins, Justin Kelly, John Sridhar, Ashwin Tran, Maxine Mumtaz, Faiz Pavithran, Nevil Francis, Nader Stoyanov, Danail Mazomenos, Evangelos B. |
| contents | 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. |
| format | Preprint |
| id |
arxiv_https___arxiv_org_abs_2509_09327 |
| institution | arXiv |
| publishDate | 2025 |
| record_format | arxiv |
| spellingShingle | Exploring Pre-training Across Domains for Few-Shot Surgical Skill Assessment Anastasiou, Dimitrios Caramalau, Razvan Sirajudeen, Nazir Boal, Matthew Edwards, Philip Collins, Justin Kelly, John Sridhar, Ashwin Tran, Maxine Mumtaz, Faiz Pavithran, Nevil Francis, Nader Stoyanov, Danail Mazomenos, Evangelos B. Computer Vision and Pattern Recognition Machine Learning 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. |
| title | Exploring Pre-training Across Domains for Few-Shot Surgical Skill Assessment |
| topic | Computer Vision and Pattern Recognition Machine Learning |
| url | https://arxiv.org/abs/2509.09327 |