Unsupervised whole-heart function assessment

TL;DR

This paper presents an unsupervised method for assessing whole-heart function from unlabeled cardiac MRI data by reconstructing masked image planes to create a meaningful latent space that captures cardiac dynamics.

Contribution

It introduces a novel unsupervised approach using masked image modeling to extract cardiac function features from unlabeled MRI data, enabling scalable cardiac screening.

Findings

Latent space correlates with cardiac phenotypes.

Strong temporal feature extraction demonstrated.

Potential for scalable cardiac screening.

Abstract

Motivation: CMR is the golden standard for cardiac diagnosis, and medical data annotation is time-consuming. Thus, screening techniques from unlabeled data can help streamline the cardiac diagnosis process. Goal: This work aims to enable cardiac function assessment from unlabeled cardiac MR images using an unsupervised approach with masked image modeling. Approach: Our model creates a robust latent space by reconstructing sparse 2D+T planes (SAX, 2CH, 3CH, and 4CH views) with 70\% masking, which can be further disentangled into distinct cardiac temporal states. Results: t-SNE visualization and kNN clustering analysis confirm the association between latent space and cardiac phenotypes, highlighting strong temporal feature extraction. Impact: This method offers a scalable approach for cardiac screening by creating a latent space as well as distinct time-segment embeddings, enabling diverse preliminary analysis of cardiac function and potentially advancing research in cardiovascular disease applications.