Researchers from the University of Jyväskylä and Central Finland Health Care District have developed an AI-based neural network to detect early knee osteoarthritis from X-ray images. The AI was able to match a doctor’s diagnosis in 87% of cases. The result is important because X-rays are the main method of diagnosing early osteoarthritis of the knee. Early diagnosis can save the patient from unnecessary examinations, treatments and even knee replacement surgery.
Osteoarthritis is the most common joint disease in the world. In Finland alone, it causes up to 600,000 medical visits each year. It is estimated to cost the national economy up to 1 billion euros per year.
The new AI-based method was trained to detect a predictive radiological feature of osteoarthritis from X-rays. The finding is not yet included in the diagnostic criteria, but orthopedic specialists consider it as an early sign of osteoarthritis. The method was developed in the Digital Health Intelligence Lab at the University of Jyväskylä as part of the AI Hub Central Finland project. It uses neural network technologies that are widely used around the world.
“The aim of the project was to train the AI to recognize an early characteristic of osteoarthritis from an x-ray. Something that experienced doctors can distinguish visually from the image, but cannot be done automatically,” explains Anri Patron, the researcher responsible for developing the method.
In practice, the AI tries to detect whether or not there is a spike on the tibial tuberosities of the knee joint. The tibial peak can be a sign of osteoarthritis.
The reliability of the method was evaluated with specialists from the Central Finland Healthcare District.
“Around 700 x-ray images were used to develop the AI model, after which the model was validated with around 200 x-ray images. The model succeeded in making an estimate of the peak that agreed with the doctors’ estimate in 87% of the cases. cases, which is a promising result,” describes Patron.
AI can support early diagnosis of osteoarthritis in primary healthcare
Docent Sami Äyrämö, head of the Digital Health Intelligence Laboratory at the University of Jyväskylä, explains that the development of AI models to diagnose early osteoarthritis is active globally.
“Several AI models have already been developed to detect knee osteoarthritis. These models can detect serious cases that would be easily detected by any specialist. However, the previously developed methods are not precise enough to detect manifestations at an early stage. The method currently being developed aims in particular at early detection using X-rays, which is greatly needed.
The aim is that in the future, an AI can detect early signs of knee osteoarthritis from x-rays, allowing the initial diagnosis to be made more often by general practitioners.
The project was carried out in collaboration with the Central Finland Health Care District. Juha Paloneva, CEO of the Central Finland Health Care District and professor of surgery, says early-stage osteoarthritis can be treated effectively.
“If we can make the diagnosis at an early stage, we can avoid uncertainty and costly tests such as MRI. In addition, the patient may be motivated to take steps to slow or even stop the progression of symptomatic osteoarthritis. In the best case, the patient could even avoid arthroplasty, ”summarizes Paloneva.
We would like to give thanks to the author of this write-up for this incredible material
Artificial intelligence searches for early sign of osteoarthritis from x-ray image – CNET
Our social media profiles here and other pages related to them here.https://www.ai-magazine.com/related-pages/