Confidence-Driven Deep Learning Framework for Early Detection of Knee Osteoarthritis

TL;DR

This paper introduces a confidence-driven deep learning framework that improves early detection of Knee Osteoarthritis by accurately distinguishing between KL-0 and KL-2 stages, matching expert radiologist performance.

Contribution

It presents a novel Siamese-based architecture with multi-level feature extraction and a hybrid loss strategy to handle annotation uncertainty and improve diagnostic accuracy.

Findings

Achieves accuracy comparable to expert radiologists

Substantial agreement with Cohen's kappa > 0.85

No significant difference in diagnostic performance (p > 0.05)

Abstract

Knee Osteoarthritis (KOA) is a prevalent musculoskeletal disorder that severely impacts mobility and quality of life, particularly among older adults. Its diagnosis often relies on subjective assessments using the Kellgren-Lawrence (KL) grading system, leading to variability in clinical evaluations. To address these challenges, we propose a confidence-driven deep learning framework for early KOA detection, focusing on distinguishing KL-0 and KL-2 stages. The Siamese-based framework integrates a novel multi-level feature extraction architecture with a hybrid loss strategy. Specifically, multi-level Global Average Pooling (GAP) layers are employed to extract features from varying network depths, ensuring comprehensive feature representation, while the hybrid loss strategy partitions training samples into high-, medium-, and low-confidence subsets. Tailored loss functions are applied to improve model robustness and effectively handle uncertainty in annotations. Experimental results on the Osteoarthritis Initiative (OAI) dataset demonstrate that the proposed framework achieves competitive accuracy, sensitivity, and specificity, comparable to those of expert radiologists. Cohen's kappa values (k > 0.85)) confirm substantial agreement, while McNemar's test (p > 0.05) indicates no statistically significant differences between the model and radiologists. Additionally, Confidence distribution analysis reveals that the model emulates radiologists' decision-making patterns. These findings highlight the potential of the proposed approach to serve as an auxiliary diagnostic tool, enhancing early KOA detection and reducing clinical workload.