Researchers developed an AI model that can accurately detect fatty liver disease from routine chest X-rays.
Key Details
- 1The AI model was created by Osaka Metropolitan University researchers.
- 2It was trained and validated with 6,599 chest X-ray images from 4,414 patients.
- 3Model performance was strong, with AUC between 0.82 and 0.83.
- 4Chest X-rays are less costly and more commonly performed than ultrasounds, CTs, or MRIs currently used for liver diagnosis.
- 5Results were published in Radiology Cardiothoracic Imaging on June 20, 2025.
Why It Matters
This approach could enable earlier and more widespread detection of fatty liver disease using existing chest X-rays, reducing the need for more expensive or specialized imaging modalities. It demonstrates the potential for AI to repurpose common imaging studies for new clinical insights in radiology.
Source
EurekAlert
Related News
•EurekAlert
AI-Powered OCT Enables Rapid 'Optical Biopsy' for Early Endometrial Cancer Detection
A team at Washington University has developed a catheter-based 3D OCT system with AI to quickly and noninvasively detect early endometrial cancers.
•EurekAlert
AI Clinical Reasoning in Diagnostics and Digital Fatigue in Healthcare
Recent JMIR features explore large language models in clinical diagnostics and digital fatigue among healthcare professionals.
•EurekAlert
KAIST, MIT, Microsoft Develop Efficient AI Image Upsampling for Robotics
KAIST, MIT, and Microsoft have created 'Upsample Anything,' a training-free AI method to restore high-resolution visual data from compressed images with up to 16x improved GPU memory efficiency.