The objective of the proposed research is to improve the diagnostic quality of cardiac computed tomography angiography (CTA) imaging by developing novel gating strategies for detecting and predicting cardiac quiescence. Cardiovascular disease is the leading cause of death in the world. When evaluated using CTA, patients with arrhythmias have an increased rate of non-diagnostic scans due to motion artifacts. This can be overcome by imaging during cardiac quiescence, i.e., the time point of minimum motion in the cardiac cycle. To achieve this, two multimodal gating frameworks are proposed, one of which will be tested on data acquired from a programmable dynamic heart phantom and the other on patient-derived data. The first proposed algorithm is a deep learning-based ultrasound (US)-electrocardiography (ECG) gating framework that combines B-mode US and ECG data to predict cardiac quiescence, modeled on initial data acquired from a dynamic heart motion phantom. The second proposed framework involves a modification to an existing seismocardiography-ECG prediction framework, tested on patient data. Additionally, the diagnostic quality of reconstructed CTA images at the time periods predicted by various frameworks was interpreted and compared by radiologists. Furthermore, the gating frameworks will be implemented through a real-time hardware prototype, involving the integration of existing hardware and software.