Network-Based Approach for Modeling and Analyzing Coronary Angiography

Babak Ravandi 1 and Arash Ravandi 21 PhD Candidate in Department of Computer and Information Technology, Purdue University, West Lafayette, Indiana 47906, USA2 MD, Devision of Orthopeadic Rheumatology, Friedrich–Alexander University Erlangen-Nürnberg, Waldkrankengaus Erlangen, 91054 Erlangen, Germany[In Preparation]

There is a significant intra-observer and inter-observer variability in the interpretation of coronary angiograms. This variability is in part due to the common practices that rely on performing visual inspections by specialists (e.g., the thickness of coronaries). Quantitative Coronary Angiography (QCA) approaches are emerging to minimize observer's error and furthermore perform predictions and analysis based on angiography images. However, QCA approaches suffer from the same problem as they mainly rely on performing visual inspections by utilizing image processing techniques.

In this work, we propose a new approach to model and analyze the entire cardiovascular tree as a complex network derived from the coronary angiography images. This method allows to assess the dynamics of cardiovascular network as well as its visual properties by using the whole arsenal of network science tools. We discuss and provide a showcase for the assessments of network integration, degree distribution, and controllability on the structure of a healthy and un-healthy cardiovascular networks. These assessments present examples of connecting the functional characteristics of the coronary system to their network structure. Through our discussion and assessments, we propose that modeling the heart's cardiovascular system as an integrated complex network is an essential phase to fully automate the interpretation of angiographic based imaging techniques such as Invasive Coronary Angiography, Computed Tomography Angiography (CTA), and Magnetic Resonance Angiography (MRA). The proposed modeling approach can significantly enhance the existing computerized approaches for interpreting coronary angiograms.

Percentage of Driver Nodes