IIT Guwahati Researchers Develop A Model To Predict Knee Osteoarthritis From X-Ray Images

Researchers from the Indian Institute of Technology (IIT) Guwahati created the 'OsteoHRNet' learning-based framework to assess the severity of knee osteoarthritis (OA) using X-ray images.

The AI-based model was created by Rohit Kumar Jain, an MTech (data science) graduate, and was co-supervised by Arijit Sur and Palash Ghosh of the institute's computer science and engineering and mathematics departments, respectively. Prasen Kumar Sharma and Sibaji Gaj, both previous PhD students of Sur, are also members of the study team. Medical practitioners can utilise the model remotely to make a more accurate diagnosis of the problem.

According to an IIT Guwahati statement, knee osteoarthritis is the most common musculoskeletal illness in the globe, with a prevalence of 28% in the country. There is no cure for knee OA save total joint replacement at an advanced stage. Therefore, early diagnosis is critical for pain management and behavioural changes, according to the study. Although MRI and CT scans provide a 3D image of the knee joints for effective diagnosis of knee OA, their availability is restricted and expensive. According to the statement, X-ray imaging is very effective and more economically practical for routine diagnosis.

The AI-based model uses an efficient deep convolutional neural network (CNN) i.e an algorithm from image recognition. This model predicts knee OA severity as per the World Health Organisation-approved Kellgren and Lawrence (KL) grading scale. It is built upon one of the most recent deep models, called the high-resolution network (HRNet), to capture the multiscale features of knee X-rays.