Patient-Specific Model of Left Heart Anatomy, Dynamics and Hemodynamics from 4D TEE: A First Validation Study

Patient-specific models of the heart physiology have become powerful instruments able to improve the diagnosis and treatment of cardiac disease. A systemic representation of the whole organ is required to capture the complex functional and hemodynamical interdependencies among the anatomical structures. We propose a novel framework for personalized modeling of the left-side heart that integrates comprehensive data of the morphology, function and hemodynamics. Patient-specific fluid dynamics are computed over the entire cardiac cycle using embedded boundary and ghost fluid methods, constrained by the dynamics of highly detailed anatomical models. Personalized boundary conditions are determined by estimating cardiac shape and motion from 4D TEE images through robust discriminative learning methods. Qualitative and quantitative validation of the computed blood dynamics is performed against Doppler echocardiography measurements, following an original methodology. Results showed a high agreement between simulation and ground truth and a correlation of r = 0.85 (p < 0.0002675). To the best of our knowledge, this is the first time that computational fluid dynamics are simulated on a systemic and comprehensive patient-specific model of the heart and validated against routinely acquired clinical ground truth.