*********************************
There is now a CONTENT FREEZE for Mercury while we switch to a new platform. It began on Friday, March 10 at 6pm and will end on Wednesday, March 15 at noon. No new content can be created during this time, but all material in the system as of the beginning of the freeze will be migrated to the new platform, including users and groups. Functionally the new site is identical to the old one. webteam@gatech.edu
*********************************
Title: Development of a Multimodal Framework for Cardiac Computed Tomography Gating
Committee:
Dr. Bhatti, Advisor
Dr. Tridandapani, Co-Advisor
Dr. McClellan, Chair
Dr. Tang
Abstract:
The objective of the proposed research is to improve the diagnostic quality and reduce radiation exposure of computed tomography angiography (CTA). Cardiac quiescence predicted from electrocardiography (ECG), an indication of the electrical activity, is suboptimal. As an alternative, seismocardiography (SCG) that directly measures the mechanical motion of the heart has demonstrated its effectiveness in detecting cardiac quiescence. An SCG-based cardiac quiescence prediction method is designed by identifying and detecting the heart sound associated waveform in SCG. A personalized multimodal framework that exploits both ECG and SCG is developed, relying upon a three-layer artificial neural network (ANN) that adaptively fuses ECG- and SCG-based cardiac quiescence predictions on a beat-by-beat basis. While comparing the performance of different modalities, the echocardiography is used as a gold standard. In addition, radiological assessment of the diagnostic quality of CTA images reconstructed at phases predicted from different cardiac modalities are made. Finally, to implement this prospective, real-time ECG-SCG-based framework for CTA data acquisition, hardware and software platforms will be integrated and pre-testing of this proposed framework will be carried out. Results from the preliminary research suggest that a more reliable approach to quiescence prediction than ECG-based prediction exclusively is possible for prospective CTA.
