Left ventricle quantification through spatio-temporal CNNs

TL;DR

This paper introduces a deep learning approach using 3D spatio-temporal CNNs to improve left ventricle quantification from cardiac MRI sequences by capturing temporal dynamics, outperforming existing methods.

Contribution

The novel integration of 3D spatio-temporal convolutions into LV quantification models enhances accuracy and surpasses previous state-of-the-art results.

Findings

Improved accuracy over single-slice models

Achieved state-of-the-art results in cardiac phase estimation

Effectively captures temporal dynamics of the heart

Abstract

Cardiovascular diseases are among the leading causes of death globally. Cardiac left ventricle (LV) quantification is known to be one of the most important tasks for the identification and diagnosis of such pathologies. In this paper, we propose a deep learning method that incorporates 3D spatio-temporal convolutions to perform direct left ventricle quantification from cardiac MR sequences. Instead of analysing slices independently, we process stacks of temporally adjacent slices by means of 3D convolutional kernels which fuse the spatio-temporal information, incorporating the temporal dynamics of the heart to the learned model. We show that incorporating such information by means of spatio-temporal convolutions into standard LV quantification architectures improves the accuracy of the predictions when compared with single-slice models, achieving competitive results for all cardiac indices and significantly breaking the state of the art (Xue et al., 2018, MedIA) for cardiac phase estimation.