Automated detection of electrocardiographic diagnostic features through an interplay between Spatial Aggregation and Computational Geometry
Report a problem or upload filesIf you have found a problem with this lecture or would like to send us extra material, articles, exercises, etc., please use our ticket system to describe your request and upload the data.
Enter your e-mail into the 'Cc' field, and we will keep you updated with your request's status.
Within the medical domain, Functional Imaging provides methods for effectual visualization of diagnostically relevant numeric fields, i.e. of spatially referenced measurements of variables related to organ functions. Unveiling the salient physical events that underly a functional image is most appropriately addressed by feature extraction methods that exploit the domain-specific knowledge combined with spatial relations at multiple abstraction levels and scales. The identification of specific patterns that are known to characterize classes of pathologies provides an important support to the diagnosis of disturbances, and the assessment of organ functions. In this work we focus on Electrocardiographic diagnosis based on epicardial activation fields. This kind of data, which can now be obtained non invasively from body surface data through mathematical model-based reconstruction methods, can hit electrical conduction pathologies that routine surface ECGs may miss. However, their analysis/interpretation still requires highly specialized skills that belong to few experts. Given an epicardial activation field, the automated detection of salient patterns in it, grounded on the existing interpretation rationale, would represent a major contribution towards the clinical use of such valuable tools whose diagnostic potential is still largely unexplored. We focus on epicardial activation isochronal maps, which convey information about the heart electric function in terms of the depolarization wavefront kinematics. An approach grounded on the integration of a Spatial Aggregation (SA) method with concepts borrowed from Computational Geometry provides a computational framework to extract, from the given activation data, a few basic features that characterize the wavefront propagation, as well as a more specific set of diagnostic features that identify an important class of heart rhythm pathologies, namely reentry arrhythmias due to block of conduction. Keywords: Biomedical imaging; functional imaging; image based diagnosis; spatial aggregation; computational geometry; electrocardiography; cardiac electrical function.
Link this pageWould you like to put a link to this lecture on your homepage?
Go ahead! Copy the HTML snippet !