Heart disease remains a leading cause of death worldwide. Previous research has indicated that the dynamics of the cardiac left ventricle (LV) during diastolic filling may play a critical role in dictating overall cardiac health. Hence, numerous studies have aimed to predict and evaluate global cardiac health based on quantitative parameters describing LV function. However, the inherent complexity of LV diastole, in its electrical, muscular, and hemodynamic processes, has prevented the development of tools to accurately predict and diagnose heart failure at early stages, when corrective measures are most effective. In this work, it is demonstrated that major aspects of cardiac function are reflected uniquely and sensitively in the optimization of vortex formation in the blood flow during early diastole, as measured by a dimensionless numerical index. This index of optimal vortex formation correlates well with existing measures of cardiac health such as the LV ejection fraction. However, unlike existing measures, this previously undescribed index does not require patient-specific information to determine numerical index values corresponding to normal function. A study of normal and pathological cardiac health in human subjects demonstrates the ability of this global index to distinguish disease states by a straightforward analysis of noninvasive LV measurements.

Purpose: This study aims to accurately segment the right ventricle (RV) from cardiac MRI using a fully automatic learning‐based method.Methods: The proposed method uses deep learning algorithms, i.e., convolutional neural networks and stacked autoencoders, for automatic detection and initial segmentation of the RV chamber. The initial segmentation is then combined with the deformable models to improve the accuracy and robustness of the process. We trained our algorithm using 16 cardiac MRI datasets of the MICCAI 2012 RV Segmentation Challenge database and validated our technique using the rest of the dataset (32 subjects).Results: An average Dice metric of 82.5% along with an average Hausdorff distance of 7.85 mm were achieved for all the studied subjects. Furthermore, a high correlation and level of agreement with the ground truth contours for end‐diastolic volume (0.98), end‐systolic volume (0.99), and ejection fraction (0.93) were observed.Conclusion: Our results show that deep learning algorithms can be effectively used for automatic segmentation of the RV. Computed quantitative metrics of our method outperformed that of the existing techniques participated in the MICCAI 2012 challenge, as reported by the challenge organizers. Magn Reson Med 78:2439–2448, 2017. © 2017 International Society for Magnetic Resonance in Medicine.