Research
Our main focus areas:
We integrate multimodal data, including imaging and electronic health records, to identify biomarkers, develop predictive models, and track cardiovascular disease progression. Leveraging advanced machine learning and deep learning techniques, we uncover hidden disease patterns, improve prediction accuracy, and advance personalized, precision-guided patient care.
Our team designs and optimizes cardiac MRI protocols to acquire more information in less time while ensuring patient comfort. We develop methods to resolve, compensate, and encode motion, enabling real-time imaging with high signal-to-noise ratio (SNR).
We develop in-silico models of cardiovascular hemodynamics based on patient-specific imaging. These models allow us to predict altered hemodynamic conditions under various disease scenarios. Furthermore, the simulations can be incorporated as priors into broader models of cardiovascular disease.
We develop computational models that integrate imaging and clinical data to identify main biomarkers to different cardiac pathologies and clinical outcomes. By incorporating artificial intelligence with physics-based modeling approaches, we aim to improve the accuracy and clinical relevance of these findings.
We examine imaging and blood biomarkers alongside patients’ clinical profiles and outcomes. Through this approach, we aim to advance diagnostic accuracy, improve patient care, and guide clinical decision-making across a wide range of cardiovascular conditions.
Help Our Research
If you are interested in participating as a research subject or collaborating on our studies, please:
- Email CVImaginglab@mednet.ucla.edu
- Include the title of the study
- Provide your contact information