HeartLens

HeartLens has the potential to detect calcium deposits in the heart earlier, leading to timelier interventions and less invasive and aggressive patient treatment options.

Coronary artery calcification (CAC) scoring helps assess cardiovascular disease severity but relies on radiologists manually reviewing CT scans to identify small, easily overlooked calcium deposits. This process is critical for early detection and intervention but is prone to human error. Through an EXCEL Research Committee effort, HeartLens is a collaborative project involving the UK Divisions of Radiology & Cardiology, the Department of Computer Science, and CAAI. The goal is to develop an AI-based tool to assist radiologists in reviewing CT scans, detecting CAC, and informing cardiologists’ diagnostic and treatment decisions. Early detection of calcification enables more timely, less invasive interventions.

HeartLens uses the DINO Transformer Model, a computer vision AI applied to identify patterns in CT scans without requiring manual labeling. By analyzing UK and Stanford University datasets, the model extracts and highlights calcified areas in coronary arteries, color-coding them by severity to aid clinical review. These visual cues support tasks such as classification and segmentation and can integrate with LLMs to enhance diagnostic accuracy. Beyond CAC scoring, the tool has potential applications for detecting other heart conditions, and the long-term goal is to make it available as a web-based tool within CAAI’s self-service platform, CLASSify. This would streamline clinical decision-making, improve early disease detection, and foster further research.