ECU researchers developed an AI algorithm that improves early detection and disease staging using medical imaging.
Key Details
- 1Supervised Contrastive Ordinal Learning algorithm was developed at Edith Cowan University.
- 2It uses imaging modalities such as bone density scans and ultrasounds for detection and staging.
- 3Achieved 85% accuracy and 79% sensitivity for Abdominal Aortic Calcification (early CVD indicator).
- 4Attained 87% accuracy/84% sensitivity in diagnosing Diabetic Retinopathy and 91% accuracy for breast cancer staging.
- 5Can differentiate between healthy and diseased individuals by learning disease-specific traits.
- 6Results will be presented at MICCAI Conference in Korea later this year.
Why It Matters
This AI system demonstrates significant improvements in accuracy for diagnosing and staging major diseases, potentially reducing subjectivity and the workload for clinicians. Early, precise detection using widely available imaging could enhance patient outcomes and expand access to advanced diagnostics.
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.