MICCAI 2022 Daily – Tuesday

This work aims not to treat but to diagnose the patient. It allows them to see what problems they might have. It is abstract to talk about ejection fraction, but a visual representation of what someone’s heart is doing now and what it could be doing if it was healthier offers something tangible. This work falls under the umbrella of counterfactual analysis . In the field of causality in machine learning, counterfactual questions explore alternative scenarios that might have happened had our actions been different. These scenarios can help inform clinicians by offering possibilities that may be hard for them to visualize. “ We’ve shown it in echocardiograms with the ejection fraction, but our method isn’t only constrained there, ” Thanos points out. “ It could be a question like, for example, had I given the patient a different drug, would they have survived? We chose an echocardiogram with the ejection fraction because we felt it was clear-cut and visually easy for people to understand the power of these kinds of counterfactual questions, which otherwise they wouldn’t be able to answer. ” This is a representation of the neural network we designed. It shows the factual and counterfactual flow of information, as well as the “trick” we used to train the counterfactual branch, ie: the combination of the expert model for the LVEF regression and GAN discriminator for visual quality. Hadrien tells us that the biggest challenge on the technical side came from the fact that the neural network is causal . The network has two branches, the factual and the counterfactual, and to train that network, they 9 DAILY MICCAI Tuesday Thanos and Hadrien