Frame-based 4D interactive modeling of heart motion

Temporal abnormalities in heart wall motion are important diagnostic indicators of cardiac disease. Limitations in cardiac image quality and resolution necessitate the guidance of an experienced user or clinician to define the inside and outside boundaries of the heart. The authors describe methods for reconstructing the spatio-temporal behavior of the heart from magnetic resonance cine images in an interactive setting. A finite element model of the time-varying geometry, incorporating both spatial and temporal coherence constraints, was fitted to image-derived data by minimising an objective function. Interaction was facilitated by a small number of user controlled "guide points" included in the objective function. A frame-based solution procedure was developed allowing the user to interact with the solution via the position of the guide points. The method was applied to patients imaged shortly after a heart attack (myocardial infarction). The inclusion of temporal coherence in the model allowed the influence of spatial smoothing constraints to be reduced, enabling more accurate description of time-dependent regional variations.