AI-enabled cardiac shape reconstruction from routine magnetic resonance imaging

TL;DR

This paper introduces a neural field-based framework for reconstructing 3D cardiac geometries from sparse MRI data, improving accuracy over traditional methods and supporting AI-driven cardiac modeling.

Contribution

The study presents a novel neural field approach that enhances 3D cardiac shape reconstruction from limited planar contours, outperforming local interpolation techniques.

Findings

Reconstructed meshes closely matched reference geometries across datasets.

The framework showed improved fidelity in challenging regions like the left ventricular apex.

It demonstrated robustness and efficiency in data-limited cardiac imaging scenarios.

Abstract

Computational models of cardiac structure and function are increasingly central to the development of subject-specific cardiac digital twins, enabling improved characterization of contractile dysfunction, pathological remodeling, and electrical abnormalities. A critical prerequisite for these models is the accurate reconstruction of three-dimensional (3D) cardiac anatomy from medical imaging. Multi-planar magnetic resonance imaging, particularly when combined with artificial intelligence, offers a clinically feasible alternative to conventional reconstruction techniques. In this study, we present a neural field-based reconstruction framework that recovers 3D cardiac geometries from sparse planar contour data by learning continuous shape representations. Reconstruction performance was evaluated using complementary in-silico and in vivo datasets spanning variations in sampling density and geometric complexity. Across both datasets, reconstructed meshes closely matched reference geometries, demonstrating that the neural field approach faithfully captures cardiac planar contours. Compared with traditional local interpolation methods, the proposed framework exhibited improved geometric fidelity in anatomically challenging regions, including the left ventricular apex and basal segments, particularly under sparse sampling conditions. Collectively, these findings demonstrate that neural field-based reconstruction provides a robust and efficient pathway for multi-planar cardiac shape recovery, with particular relevance for AI-driven modeling pipelines and data-limited settings such as small-animal and time-resolved cardiac imaging.