KneeXNeT: An Ensemble-Based Approach for Knee Radiographic Evaluation

TL;DR

KneeXNeT is an ensemble deep learning approach that automates knee osteoarthritis severity classification from X-ray images, achieving improved accuracy and explainability over individual models.

Contribution

The paper introduces KneeXNeT, a novel ensemble model that combines multiple deep learning classifiers for more accurate and explainable knee OA severity assessment.

Findings

Ensemble model outperformed individual models with 0.72 accuracy.

Weighted sampling improved model accuracy from 0.69 to 0.70.

Smooth-GradCAM++ enhanced model explainability.

Abstract

Knee osteoarthritis (OA) is the most common joint disorder and a leading cause of disability. Diagnosing OA severity typically requires expert assessment of X-ray images and is commonly based on the Kellgren-Lawrence grading system, a time-intensive process. This study aimed to develop an automated deep learning model to classify knee OA severity, reducing the need for expert evaluation. First, we evaluated ten state-of-the-art deep learning models, achieving a top accuracy of 0.69 with individual models. To address class imbalance, we employed weighted sampling, improving accuracy to 0.70. We further applied Smooth-GradCAM++ to visualize decision-influencing regions, enhancing the explainability of the best-performing model. Finally, we developed ensemble models using majority voting and a shallow neural network. Our ensemble model, KneeXNet, achieved the highest accuracy of 0.72, demonstrating its potential as an automated tool for knee OA assessment.