KNOAP Challenge and data management with XNAT


Published March 11, 2024

Join us for an afternoon of presentations from Euro-BioImaging users and image data/image analysis experts at our Nodes that will provide a compelling overview of the state-of-the-art in Image Data. At the Euro-BioImaging User Forum on Image Data, Jukka Hirvasniemi, Erasmus MC, Population Imaging Flagship Node, presents the KNee OsteoArthritis Prediction (KNOAP) challenge and how it made it possible to objectively compare methods for the prediction of incident symptomatic radiographic knee osteoarthritis.

What: Euro-BioImaging User Forum “Image Data”

When: March 26, 2024, from 14:00-17:00 CEST Where: Online

Full program

Register

Abstract

KNOAP Challenge and data management with XNAT

Jukka Hirvasniemi,

Erasmus MC, Population Imaging Flagship Node

Osteoarthritis is the most common joint disease which affects over 250 million people worldwide. Identification of subjects at high risk to develop knee osteoarthritis is important to prevent or slow down the disease process. The KNee OsteoArthritis Prediction (KNOAP) challenge (https://knoap2020.grand-challenge.org/) was organised to objectively compare methods for the prediction of incident symptomatic radiographic knee osteoarthritis within 78 months on a test set with blinded ground truth. The challenge participants were free to use any available data sources to train their models. A test set of 423 knees from the Prevention of Knee Osteoarthritis in Overweight Females (PROOF) study consisting of magnetic resonance imaging (MRI) and X-ray image data along with clinical risk factors at baseline was made available to all challenge participants through XNAT. The ground truth outcomes, i.e., which knees developed incident symptomatic radiographic knee osteoarthritis within 78 months, were not provided to the participants. The model with the highest area under the receiver operating characteristic curve (0.64) used deep learning to extract information from X-ray images combined with clinical variables. The KNOAP challenge established a benchmark for predicting incident symptomatic radiographic knee osteoarthritis. Accurate prediction of incident symptomatic radiographic knee osteoarthritis is a complex and still unsolved problem requiring additional investigation.


More news from Euro-BioImaging

issue concentration of deuterated glucose and/or fructose

June 30, 2025

Deuterium Metabolic Imaging to measure hepatic fructose metabolism

Chronic intake of high amounts of fructose has been linked to the development of metabolic disorders caused by the almost complete clearance of fructose…

June 30, 2025

VISITING THE PRIME NODE

With the occasion of the Board meeting which took place in Amsterdam last May, the Med-Hub section Director Linda Chaabane and the Med-Hub Head…

CANDLE logo

June 24, 2025

EU Project CANDLE starts building National Cancer Data Nodes

The EU-funded project CANDLE – National CAncer data Node DeveLopErs – officially kicked off on 1st of June 2025, launching its three-year mission to…