Explainable Contrastive Learning for KL Grading Classification in Knee Osteoarthritis

Kellgren-Lawrence (KL) grading prediction plays an important role in the assessment of knee osteoarthritis (OA), aiding in early diagnosis and monitoring. This study aims to develop and validate an effective and explainable AI framework for automated KL grading using only plain knee radiographs. The proposed AI-powered framework combines a contrastive learning strategy with Grad-CAM++ visualization, thus offering enhanced feature representation along with AI model explainability. Experimental results indicate that the proposed model achieves promising classification accuracy. Furthermore, the explainability analysis, with domain experts involved, confirms that the AI model focuses on clinically relevant regions, aligning with domain-specific knowledge in orthopedics.