Researchers have developed new Artificial Intelligence (AI) capable of detecting early knee osteoarthritis from x-ray images.
The new technology has been developed by the University of Jyväskylä and the Central Finland Health Care District and is able to match a doctors’ diagnosis in 87% of knee osteoarthritis cases.
X-rays are the primary diagnostic method for early knee osteoarthritis. If the condition is diagnosed early, patients can avoid unnecessary examinations, treatments and even knee joint replacement surgery.
Knee osteoarthritis is highly common
Osteoarthritis is the most common joint-related illness in the world. It causes as many as 600,000 medical visits each year in Finland alone. The estimated to cost the national economy is close to €1 billion per year.
The new AI based method can detect a radiological feature predictive of osteoarthritis from x-rays. This feature is not currently included in diagnostic criteria; however, orthopaedic specialists do consider it as an early sign of osteoarthritis. The new technology utilises neural network technologies that are already widely used across the world.
“The aim of the project was to train the AI to recognise an early feature of osteoarthritis from an x-ray. Something that experienced doctors can visually distinguish from the image, but cannot be done automatically”, explained Anri Patron, a researcher on the project.
The AI aims to detect any spiking on the tibial tubercles in the knee joint. Tibial spiking can be a sign of knee osteoarthritis. Specialists from the Central Finland Healthcare District worked with the researchers to assess the reliability of this method.
“Around 700 x-ray images were used in developing the AI model, after which the model was validated with around 200 x-ray images. The model managed to make an estimate of the spiking that was congruent with a doctors’ estimate in 87% of the cases, which is a promising result,” said Patron.
AI can ease the burden of osteoarthritis
“Several AI models have previously been developed to detect knee osteoarthritis. These models can detect severe cases that would be easily detected by any specialists. However, the previously developed methods are not accurate enough to detect the early-stage manifestations. The method now being developed aims for, in particular, early detection from x-rays, for which there is a great need,” explained Docent Sami Äyrämö, head of the Digital Health Intelligence Laboratory at the University of Jyväskylä.
The researchers hope that in future, the AI would be able to detect early signs of knee osteoarthritis from x-ray images. This would make it possible for an initial diagnosis to be made more often by general practitioners. This would be a major breakthrough in the treatment of osteoarthritis.
“If we can make the diagnosis in the early stages, we can avoid uncertainty and expensive examinations such as MRI scanning. In addition, the patient can be motivated to take the measures to slow down or even stop the progression of the symptomatic osteoarthritis. In the best possible scenario, the patient might even avoid joint replacement surgery,” concluded CEO for Central Finland Health Care district and professor of surgery, Juha Paloneva.
