Interpretable Representation Learning of Cardiac MRI via Attribute Regularization
This work addresses interpretability issues in medical imaging AI for clinicians, but it is incremental as it builds on existing methods.
The paper tackled the problem of blurry reconstructions in attribute-regularized variational autoencoders for cardiac MRI, proposing a method that combines attribute regularization with adversarial training to improve reconstruction quality while maintaining interpretability, demonstrated on UK Biobank data.
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.