We develop image analysis algorithms for whole-heart cardiac MRI in patients with severe congenital heart disease.

We develop computer vision and machine learning methods for segmentation and interpretation of cardiac MRI in patients with congenital heart disease (CHD), to support simulation and surgical planning. The resulting heart surface models can, for example, be 3D-printed to visualize each patient's individual cardiac anatomy, or be used for dynamic functional analysis of the cardiac cycle (i.e., ejection fraction). Our research focuses on overcoming challenges of dramatic anatomical variability on the heart in CHD patients.

 

Dynamic Heart Surface Model
Dynamic Heart Surface Model