Two knee radiographs rated for spiking of tibial tubercles are compared. The...
Two knee radiographs rated for spiking of tibial tubercles are compared. The tubercles rated as spiking are indicated by arrowheads.

Image source: Patron et al., Diagnostics 2022 (CC BY 4.0)

News • Prevention of unnecessary treatments and examination

AI detects early signs of osteoarthritis from x-ray images

Researchers from the University of Jyväskylä and the Central Finland Health Care District have developed an AI based neural network to detect an early knee osteoarthritis from x-ray images.

AI was able to match a doctors’ diagnosis in 87% of cases. The result is important because x-rays are the primary diagnostic method for early knee osteoarthritis. An early diagnosis can save the patient from unnecessary examinations, treatments and even knee joint replacement surgery. 

The researchers published their findings in the journal Diagnostics.

Osteoarthritis is the most common joint-related ailment globally. In Finland, it causes as many as 600 000 medical visits every year. It has been estimated to cost the national economy up to €1 billion every year. 

The new AI based method was trained to detect a radiological feature predictive of osteoarthritis from x-rays. The finding is not at the moment included in the diagnostic criteria, but orthopaedic specialists consider it as an early sign of osteoarthritis. The method was developed in Digital Health Intelligence Lab at the University of Jyväskylä as a part of the AI Hub Central Finland project. It utilises neural network technologies that are widely used globally. “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”, explains Anri Patron, the researcher responsible for the development of the method. 

In practice, the AI tries to detect whether there is spiking on the tibial tubercles in the knee joint or not. Tibial spiking can be a sign of osteoarthritis. The reliability of the method was evaluated together with specialists from the Central Finland Healthcare District. “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”, Patron describes.

Grad-CAM visualizations for incorrect predictions. In the left-side images, the...
Grad-CAM visualizations for incorrect predictions. In the left-side images, the model rates the knee spiking based on the narrow appearance of the medial joint space, which indicates that the model has learned the association between tibial spiking and medial joint space narrowing (JSN). In the right-side images, the model makes a spiking assessment based on the medial tubercle.

Image source: Patron et al., Diagnostics 2022 (CC BY 4.0)

If we can make the diagnosis in the early stages, we can avoid uncertainty and expensive examinations such as MRI scanning

Juha Paloneva

Docent Sami Äyrämö, Head of the Digital Health Intelligence Laboratory at the University of Jyväskylä, explains that the development of AI models diagnosing early osteoarthritis is active globally. “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.” 

The goal is that in the future, an AI would be able to detect early signs of knee osteoarthritis from x-rays, making it possible for 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. H CEO for Central Finland Health Care disctrict and professor of surgery Juha Paloneva says that early stage osteoarthritis can be effectively treated. “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”, Paloneva sums up. 

Source: University of Jyväskylä


Read all latest stories

Related articles


News • Fracture diagnosis support

AI software to help identify bone trauma at the point of care

Fujifilm partners with Gleamer to integrate an AI software called BoneView into its X-ray imaging systems to assist radiologists and emergency clinicians in the diagnosis of skeletal fractures.


News • Is it broken?

AI accurately detects fractures on x-rays, alerts doctors

A new study has found that AI can help physicians in interpreting x-rays after an injury and suspected fracture. This has the potential to improve diagnostic performance and efficiency.


News • Opportunistic screening using chest X-rays

AI identifies non-smokers at high risk for lung cancer

Incidence of lung cancer among people who never smoked is rising. A new AI tool opens the door for opportunistic screening for this group, using existing chest X-rays in the electronic medical record.

Related products

AI-Rad Companion

Artificial Intelligence

Siemens Healthineers · AI-Rad Companion

Siemens Healthcare GmbH
BoneView & ChestView

Artificial Intelligence

Gleamer · BoneView & ChestView

Cortex Protection Software

Utilities / Add-ons

Swissray · Cortex Protection Software

Swissray Technologies AG
CXDI Elite series

DR Detectors

Canon · CXDI Elite series

Canon Medical Components Europe B.V.
Subscribe to Newsletter