Page 118 - Artificial Intelligence for Computational Modeling of the Heart

88 Chapter 2 Implementation of a patient-specific cardiac model

Figure 2.34. Flow rates vs time.

Figure 2.35. Cardiac cycle (systole on top, diastole on bottom) computed using the
FSI framework introduced in this chapter. Velocity magnitude in the left ventricle is
visualized using a standard rainbow colormap with constant positive slope
transparency map. Myocardial stress magnitude is also visualized with a
black-body radiation colormap.

dynamic valve system ensures that valve geometry at any time is
also realistic.

2.5 Parameter estimation
The goal of model personalization is to estimate the free pa-
rameters of the model such that it captures the observed, clinically
measured cardiac physiology. A successful strategy is to marginal-
ize each modeling component and personalize them one-by-one,
following a sequence that reflects their interdependency. For in-
stance, one could adopt the following sequence:
1. Compute the patient-specific anatomical model of the heart
from medical images (section 2.1).