Fusing magnetic resonance imaging data for studying ventricular fibrillation.
thesisposted on 2021-05-22, 16:36 authored by Karl Magtibay
Ventricular Fibrillation (VF) has been described as seemingly random activations on the ventricles of the mammalian heart and is one of the causes of Sudden Cardiac Deaths (SCD). Medical imaging techniques, such as Magnetic Resonance Imaging (MRI), could potentially provide a better way of collecting data and understanding the true nature of VF than the techniques that are currently being employed. In addition, as there is a wide variety of MR techniques, fusing and jointly analyzing complementary data sets could also prove beneficial in providing parameters that are informative in studying VF and are otherwise unobservable by inspection. In this thesis, the author explores the quantification of the combination of MRI techniques, Current Density Imaging (CDI) and Diffusion Tensor Imaging (DTI), as novel tools for studying VF. This was accomplished by performing two feature-based data fusion techniques, Joint Independent Component Analysis (jICA) and Canonical Correlation Analysis (CCA). Using 12 imaging data sets from 10 live porcine heart experiments, both data fusion techniques provided unique ways from which the variations of CDI and DTI data sets were used to distinguish cardiac states. The results obtained by the jICA approach demonstrated discrimination between VF and non-VF subjects (p = 0:020) using the jICA loadings with evidence of a significant increase in the mutual information post fusion. For the CCA approach, using the pairwise mixing profiles, we observed discrimination between VF and non-VF subjects (p = 0:023) with a 7.25% increase in average correlation between the modalities, post fusion. The results of the study demonstrate that the fusion of CDI and DTI data sets captures and enhances the variations in electrical current pathways in relation to a myocardial structure that are unique to a cardiac state, such as VF. This study serves as a strong precursor for exploring MRI and data fusion techniques in studying VF. Such a study could provide greater insights on VF characteristics inspiring better treatment options for patients vulnerable to VF.