A new AI approach enables OCT to automatically detect lipid-rich plaques in coronary arteries, showing strong agreement with histopathology results.
Key Details
- 1Researchers developed an AI method for detecting fatty deposits in coronary arteries using OCT images.
- 2This method combines spectral data from OCT with deep learning to identify lipid-rich plaques.
- 3The AI approach works with existing clinical OCT systems and does not require extra hardware.
- 4Validation against histopathology in a rabbit model showed strong classification performance.
- 5The technique requires only frame-level annotations, reducing expert labeling time and subjectivity.
- 6Plans are underway for further validation in human coronary artery data and workflow integration.
Why It Matters
Automated lipid plaque detection in OCT can help clinicians better assess cardiac risk without increasing workflow burden, offering more objective and robust support for interventional cardiology. This is a significant advance in imaging AI for cardiovascular applications.
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.