FusionNet: a frame interpolation network for 4D heart models

TL;DR

FusionNet is a neural network designed to reconstruct high-temporal-resolution 4D cardiac motion from short-duration CMR images, improving shape accuracy over existing methods.

Contribution

It introduces FusionNet, a novel neural network that estimates intermediate 3D heart shapes to enhance temporal resolution in cardiac imaging.

Findings

Achieved Dice coefficient over 0.897, indicating high shape recovery accuracy.

Outperformed existing methods in reconstructing cardiac shapes.

Validated effectiveness on experimental data.

Abstract

Cardiac magnetic resonance (CMR) imaging is widely used to visualise cardiac motion and diagnose heart disease. However, standard CMR imaging requires patients to lie still in a confined space inside a loud machine for 40-60 min, which increases patient discomfort. In addition, shorter scan times decrease either or both the temporal and spatial resolutions of cardiac motion, and thus, the diagnostic accuracy of the procedure. Of these, we focus on reduced temporal resolution and propose a neural network called FusionNet to obtain four-dimensional (4D) cardiac motion with high temporal resolution from CMR images captured in a short period of time. The model estimates intermediate 3D heart shapes based on adjacent shapes. The results of an experimental evaluation of the proposed FusionNet model showed that it achieved a performance of over 0.897 in terms of the Dice coefficient, confirming that it can recover shapes more precisely than existing methods. This code is available at: https://github.com/smiyauchi199/FusionNet.git