Deep Networks to Automatically Detect Late-activating Regions of the Heart

TL;DR

This paper introduces a deep learning framework that automatically detects late-activating regions of the heart from cine DENSE MRI, significantly reducing manual effort and improving prediction speed and accuracy.

Contribution

We develop a cascade deep learning network for end-to-end segmentation, TOS prediction, and visualization of late-activation regions in cardiac MRI images.

Findings

Fast TOS prediction with improved accuracy

Reduces manual labor and computational time

Effective in analyzing heart failure patient images

Abstract

This paper presents a novel method to automatically identify late-activating regions of the left ventricle from cine Displacement Encoding with Stimulated Echo (DENSE) MR images. We develop a deep learning framework that identifies late mechanical activation in heart failure patients by detecting the Time to the Onset of circumferential Shortening (TOS). In particular, we build a cascade network performing end-to-end (i) segmentation of the left ventricle to analyze cardiac function, (ii) prediction of TOS based on spatiotemporal circumferential strains computed from displacement maps, and (iii) 3D visualization of delayed activation maps. Our approach results in dramatic savings of manual labors and computational time over traditional optimization-based algorithms. To evaluate the effectiveness of our method, we run tests on cardiac images and compare with recent related works. Experimental results show that the proposed approach provides fast prediction of TOS with improved accuracy.