Image Courtesy : www.facebook.com/iitgwt/

A team of researchers from the Indian Institute of Technology Guwahati has developed a deep learning framework called OsteoHRNet. This AI-based model automatically assesses the severity of Knee Osteoarthritis (OA) from X-ray images. The framework aims to aid medical practitioners in remote locations by providing a more accurate diagnosis of the disease.

Knee Osteoarthritis is a prevalent musculoskeletal disorder, affecting approximately 28 percent of the population in India. While total joint replacement is the only cure at advanced stages, early diagnosis is crucial for pain management and corrective measures. While MRI and CT scans offer detailed 3D images for effective diagnosis, their availability and cost pose limitations. X-ray imaging, on the other hand, is readily available and economically feasible for routine diagnosis.

In the pursuit of enhancing automatic knee osteoarthritis detection from X-ray images, the IIT Guwahati team has developed an AI-based model to assess the severity of Knee OA. The model uses a deep convolutional neural network, specifically the High-Resolution Network (HRNet), to capture multi-scale features of knee X-rays. It predicts the severity of Knee OA based on the Kellgren and Lawrence (KL) grading scale approved by the World Health Organization, ranging from grade 0 (low severity) to grade 4 (high severity).

Dr. Palash Ghosh, Assistant Professor in the Department of Mathematics at IIT Guwahati, explained that their model is capable of identifying the most medically significant area to determine the severity level of knee osteoarthritis. This capability assists medical practitioners in accurately detecting the disease at an early stage.

The research team is currently working on adapting these models to be deployed on resource-constrained devices, aiming to provide medical professionals with an initial but accurate guess for diagnosis. This advancement has the potential to alleviate the shortage of skilled personnel in this field, particularly in rural areas of India.