An AI System for Continuous Knee Osteoarthritis Severity Grading Using Self-Supervised Anomaly Detection with Limited Data

TL;DR

This paper introduces a novel self-supervised anomaly detection system for continuous knee osteoarthritis severity grading, requiring minimal labeled data and outperforming existing methods in accuracy and correlation with expert assessments.

Contribution

It presents a three-stage approach combining self-supervised learning, pseudo-labeling, and dual centre representation learning for effective OA severity grading with limited data.

Findings

Outperforms existing techniques by up to 24% in OA detection accuracy.

Achieves disease severity scoring comparable to human experts.

Requires less than 3% of labels compared to traditional methods.

Abstract

The diagnostic accuracy and subjectivity of existing Knee Osteoarthritis (OA) ordinal grading systems has been a subject of on-going debate and concern. Existing automated solutions are trained to emulate these imperfect systems, whilst also being reliant on large annotated databases for fully-supervised training. This work proposes a three stage approach for automated continuous grading of knee OA that is built upon the principles of Anomaly Detection (AD); learning a robust representation of healthy knee X-rays and grading disease severity based on its distance to the centre of normality. In the first stage, SS-FewSOME is proposed, a self-supervised AD technique that learns the 'normal' representation, requiring only examples of healthy subjects and <3% of the labels that existing methods require. In the second stage, this model is used to pseudo label a subset of unlabelled data as 'normal' or 'anomalous', followed by denoising of pseudo labels with CLIP. The final stage involves retraining on labelled and pseudo labelled data using the proposed Dual Centre Representation Learning (DCRL) which learns the centres of two representation spaces; normal and anomalous. Disease severity is then graded based on the distance to the learned centres. The proposed methodology outperforms existing techniques by margins of up to 24% in terms of OA detection and the disease severity scores correlate with the Kellgren-Lawrence grading system at the same level as human expert performance. Code available at https://github.com/niamhbelton/SS-FewSOME_Disease_Severity_Knee_Osteoarthritis.