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
Radiomics and AI Predict Secondary Surgery Risk in TBI Patients
A radiomics-based machine learning model using CT scans predicts the need for secondary decompressive craniectomy after traumatic brain injury.
•EurekAlert
Integrating Biomarkers and AI to Transform Psychiatric Diagnosis
New review charts a roadmap for biologically informed psychiatric diagnosis using biomarkers and AI.
•EurekAlert
Radiologist-AI Workflow Impacts Medical Malpractice Perceptions
Radiologists’ perceived legal liability varies based on how AI is integrated into clinical workflows and how often scans are reviewed.