Robust multi-label surgical tool classification in noisy endoscopic videos

Qayyum, Adnan; Ali, Hassan; Caputo, Massimo; Vohra, Hunaid; Akinosho, Taofeek; Abioye, Sofiat; Berrou, Ilhem; Capik, Paweł; Qadir, Junaid; Bilal, Muhammad

Abstract

Over the past few years, surgical data science has attracted substantial interest from the machine learning (ML) community. Various studies have demonstrated the efficacy of emerging ML techniques in analysing surgical data, particularly recordings of procedures, for digitising clinical and non-clinical functions like preoperative planning, context-aware decision-making, and operating skill assessment. However, this field is still in its infancy and lacks representative, well-annotated datasets for training robust models in intermediate ML tasks. Also, existing datasets suffer from inaccurate labels, hindering the development of reliable models. In this paper, we propose a systematic methodology for developing robust models for surgical tool classification using noisy endoscopic videos. Our methodology introduces two key innovations: (1) an intelligent active learning strategy for minimal dataset identification and label correction by human experts through collective intelligence; and (2) an assembling strategy for a student-teacher model-based self-training framework to achieve the robust classification of 14 surgical tools in a semi-supervised fashion. Furthermore, we employ strategies such as weighted data loaders and label smoothing to enable the models to learn difficult samples and address class imbalance issues. The proposed methodology achieves an average F1-score of 85.88% for the ensemble model-based self-training with class weights, and 80.88% without class weights for noisy tool labels. Also, our proposed method significantly outperforms existing approaches, which effectively demonstrates its effectiveness.

• Journal Article Type: Article
• Acceptance Date: Dec 4, 2024
• Online Publication Date: Feb 14, 2025
• Publication Date: Feb 14, 2025
• Deposit Date: Mar 26, 2025
• Publicly Available Date: Mar 26, 2025
• Journal: Scientific Reports
• Electronic ISSN: 2045-2322
• Publisher: Nature Research (part of Springer Nature)
• Peer Reviewed: Peer Reviewed
• Volume: 15
• Issue: 1
• Article Number: 5520
• DOI: https://doi.org/10.1038/s41598-024-82351-5
• Public URL: https://uwe-repository.worktribe.com/output/13784986