AI technologies outperform or complement radiologist scoring in CT, MRI, and ultrasound imaging for rheumatology disorders, as shown in key EULAR 2025 studies.
Key Details
- 1AI-assisted HRCT outperformed expert radiologists in detecting progression of SSc-associated interstitial lung disease (ILD).
- 2A deep learning model integrating MRI findings achieved high accuracy for diagnosing axial spondyloarthritis and identified cases beyond standard criteria.
- 3Ultrasound AI models improved classification of giant cell arteritis lesions but showed limitations in smaller arteries.
- 4Machine learning approaches identified personalized cancer risk factors in systemic sclerosis using clinical and imaging data.
- 5Large language models show promise but mixed performance in osteoporosis risk stratification tasks based on imaging and clinical data.
Why It Matters
These EULAR 2025 findings validate the growing impact of AI in augmenting radiologic assessment and predictive analytics in rheumatology. Enhanced imaging AI can increase diagnostic accuracy, detect subtle disease changes, and underpin precision medicine strategies for complex rheumatic diseases.
Source
EurekAlert
Related News
•EurekAlert
Major Study Reveals Barriers to Implementing AI Chest Diagnostics in NHS Hospitals
A UCL-led study identifies significant challenges in deploying AI tools for chest diagnostics across NHS hospitals in England.
•EurekAlert
Sybil AI Model Accurately Predicts Lung Cancer Risk in Diverse Urban Populations
A new study validates the Sybil AI model for predicting lung cancer risk using low-dose CT in a predominantly Black cohort at an urban safety-net hospital.
•EurekAlert
DreamConnect AI Translates and Edits fMRI Brain Activity into Images
Researchers unveil DreamConnect, an AI system that reconstructs and edits visual imagery from fMRI brain data with language prompts.