FusionNet: a frame interpolation network for 4D heart models

arXiv cs.CV / 3/12/2026

📰 NewsTools & Practical UsageModels & Research

共有:

Key Points

FusionNet is a neural network designed to interpolate frames and estimate intermediate 3D heart shapes to recover high-temporal-resolution 4D cardiac motion from short-duration CMR scans.
It achieves higher temporal resolution by leveraging information from adjacent shapes to synthesize intermediate frames.
In experiments, FusionNet attains a Dice coefficient above 0.897, indicating improved shape recovery over existing methods.
The code is publicly available on GitHub, enabling replication and reuse.

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