New publication: Innovative Diagnostic Approaches for Predicting Knee Cartilage Degeneration in Osteoarthritis Patients: A Radiomics-Based Study

The team of SINPAIN partner Reykjavik University (RU) recently published a scientific paper on “Innovative Diagnostic Approaches for Predicting Knee Cartilage Degeneration in Osteoarthritis Patients: A Radiomics-Based Study”in Information Systems Frontiers.

The study investigates the use of radiomics – quantitative image analysis combined with machine learning – to improve the diagnosis of knee osteoarthritis (OA). A multimodal dataset including MRI and CT scans of 138 knees was used to extract radiomic features from cartilage segments. Machine learning models were applied to differentiate between degenerated and healthy knees based on these features. Through feature selection, guided by correlation and significance analyses, texture- and shape-related features emerged as key predictors. A robustness analysis, which assessed the stability of features across segmentation variations, further optimized feature selection. The results indicate that radiomics can achieve high accuracy in the classification of knee OA, highlighting its potential for early diagnosis and personalized treatment strategies.

The full publication is available here.