Rethinking Knee Osteoarthritis Severity Grading: A Few Shot Self-Supervised Contrastive Learning Approach

TL;DR

This paper introduces SS-FewSOME, a self-supervised contrastive learning approach for continuous knee osteoarthritis severity grading that requires only a few labeled examples, aiming to improve objectivity and clinical applicability.

Contribution

The work presents a novel few-shot, self-supervised method for OA severity assessment that reduces reliance on large labeled datasets and moves beyond traditional ordinal grading.

Findings

Achieved a Spearman Rank Correlation of 0.43 with only 30 labels.

Demonstrated the feasibility of continuous OA grading using self-supervised learning.

Reduced data annotation requirements compared to existing methods.

Abstract

Knee Osteoarthritis (OA) is a debilitating disease affecting over 250 million people worldwide. Currently, radiologists grade the severity of OA on an ordinal scale from zero to four using the Kellgren-Lawrence (KL) system. Recent studies have raised concern in relation to the subjectivity of the KL grading system, highlighting the requirement for an automated system, while also indicating that five ordinal classes may not be the most appropriate approach for assessing OA severity. This work presents preliminary results of an automated system with a continuous grading scale. This system, namely SS-FewSOME, uses self-supervised pre-training to learn robust representations of the features of healthy knee X-rays. It then assesses the OA severity by the X-rays' distance to the normal representation space. SS-FewSOME initially trains on only 'few' examples of healthy knee X-rays, thus reducing the barriers to clinical implementation by eliminating the need for large training sets and costly expert annotations that existing automated systems require. The work reports promising initial results, obtaining a positive Spearman Rank Correlation Coefficient of 0.43, having had access to only 30 ground truth labels at training time.