Key result
Deep-HyROMnet speeds computation by orders of magnitude versus classical models while returning accurate pressure-volume loops.
Why the study?
Reducing the high computational time of full-order models for cardiac mechanics is necessary to enable the translation of patient-specific simulations into clinical practice.
Population
Patient-specific left ventricle geometry model
Comparison
Deep-HyROMnet technique vs classical projection-based ROMs and full-order models
Design
Computational modeling and simulation study
Authors
Loading...
May speed patient-specific cardiac modeling in research; leaves open clinical translation without prospective validation.
A novel deep learning-based reduced-order modeling technique significantly accelerates patient-specific cardiac mechanics simulations while maintaining accuracy, potentially enabling clinical translation.
Cicci et al. (2023) studied Cardiac mechanics modeling. Deep-HyROMnet technique vs. Classical projection-based ROMs was evaluated on Computational speed-up and accuracy of pressure-volume loops. The Deep-HyROMnet technique outperformed classical projection-based reduced-order models by orders of magnitude in computational speed-up while returning accurate pressure-volume loops.
Synapse has enriched 4 closely related papers on similar clinical questions. Consider them for comparative context: