A Multi-Site Study on AI-Driven Pathology Detection and Osteoarthritis Grading from Knee X-Ray
Journal:
arXiv
Published Date:
Mar 28, 2025
Abstract
Introduction: Bone health disorders like osteoarthritis and osteoporosis pose
major global health challenges, often leading to delayed diagnoses due to
limited diagnostic tools. This study presents an AI-powered system that
analyzes knee X-rays to detect key pathologies, including joint space
narrowing, sclerosis, osteophytes, tibial spikes, alignment issues, and soft
tissue anomalies. It also grades osteoarthritis severity, enabling timely,
personalized treatment.
Study Design: The research used 1.3 million knee X-rays from a multi-site
Indian clinical trial across government, private, and SME hospitals. The
dataset ensured diversity in demographics, imaging equipment, and clinical
settings. Rigorous annotation and preprocessing yielded high-quality training
datasets for pathology-specific models like ResNet15 for joint space narrowing
and DenseNet for osteoarthritis grading.
Performance: The AI system achieved strong diagnostic accuracy across diverse
imaging environments. Pathology-specific models excelled in precision, recall,
and NPV, validated using Mean Squared Error (MSE), Intersection over Union
(IoU), and Dice coefficient. Subgroup analyses across age, gender, and
manufacturer variations confirmed generalizability for real-world applications.
Conclusion: This scalable, cost-effective solution for bone health
diagnostics demonstrated robust performance in a multi-site trial. It holds
promise for widespread adoption, especially in resource-limited healthcare
settings, transforming bone health management and enabling proactive patient
care.
