Can Knowledge Transfer Techniques Compensate for the Limited Myocardial Infarction Data by Leveraging Hæmodynamics? An in silico Study

Abstract

The goal of this work is to investigate the ability of transfer learning (TL) and multitask learning (MTL) algorithms to predict tasks related to myocardial infarction (MI) in a small–data regime, leveraging a larger dataset of hæmodynamic targets. The data are generated in silico, by solving steady–state Navier–Stokes equations in a patient–specific bifurcation geometry. Stenoses, whose location, shape, and dimension vary among the datapoints, are artificially incorporated in the geometry to replicate coronary artery disease conditions. The model input consists of a pair of greyscale images, obtained by postprocessing the velocity field resulting from the numerical simulations. The output is a synthetic MI risk index, designed as a function of various geometrical and hæmodynamic parameters, such as the diameter stenosis and the wall shear stress (WSS) at the plaque throat. Moreover, the Fractional Flow Reserve (FFR) at each outlet branch is computed. The ResNet18 model trained on all the available MI labels is taken as reference. We consider two scenarios. In the first one, we assume that only a fraction of MI labels is available. For TL, models pretrained on FFR data — learned on the full dataset — reach accuracies comparable to the reference. In the second scenario, instead, we suppose also the number of known FFR labels to be small. We employ MTL algorithms in order to leverage domain–specific feature sharing, and significant accuracy gains with respect to the baseline single–task learning approach are observed. Ultimately, we conclude that exploiting representations learned from hæmodynamics–related tasks improves the predictive capability of the models.