Interpretable Representation Learning of Cardiac MRI via Attribute Regularization

TL;DR

This paper introduces a novel adversarial variational autoencoder with attribute regularization for interpretable cardiac MRI analysis, effectively reducing reconstruction blurriness while maintaining interpretability.

Contribution

It proposes an attributed-regularized soft introspective variational autoencoder that combines attribute regularization with adversarial training for improved interpretability and image quality.

Findings

Addresses blurry reconstruction in VAE models

Preserves interpretability of latent space

Effective on cardiac MRI data

Abstract

Interpretability is essential in medical imaging to ensure that clinicians can comprehend and trust artificial intelligence models. Several approaches have been recently considered to encode attributes in the latent space to enhance its interpretability. Notably, attribute regularization aims to encode a set of attributes along the dimensions of a latent representation. However, this approach is based on Variational AutoEncoder and suffers from blurry reconstruction. In this paper, we propose an Attributed-regularized Soft Introspective Variational Autoencoder that combines attribute regularization of the latent space within the framework of an adversarially trained variational autoencoder. We demonstrate on short-axis cardiac Magnetic Resonance images of the UK Biobank the ability of the proposed method to address blurry reconstruction issues of variational autoencoder methods while preserving the latent space interpretability.