Murine Atherosclerosis Detection Using Machine Learning Under Magnetic Resonance Imaging

Over the past few decades, the diagnosis of heart disease, namely atherosclerosis, has been of interest for many researchers. The use of electrocardiogram (ECG) triggered Magnetic Resonance Imaging (MRI) sequences, enables exploration of aortic arches with high-resolution images. Lately, implementation of numerous Machine Learning (ML) techniques improved the accuracy of diagnosing diseases especially cardiovascular ones. In this paper, we proposed a model to diagnose atherosclerosis in mice using features extracted from the electrocardiogram (ECG) and respiratory signals. We defined new variables, after adaptation to the altered nature of electrophysiological signals with superimposed MRI noise. Using the 5-fold cross validation test, we introduced the features into the Random Forest (RF) classifier and obtained an accuracy of 96.96%. Feature selection then took place using the Info Gain (IG) attribute evaluator, which increased our model's accuracy to 97.57%. This presents a first step towards a real-time MRI synchronous cardiovascular finding system.