Fighting MRI Anisotropy: Learning Multiple Cardiac Shapes From a Single Implicit Neural Representation

TL;DR

This paper introduces a neural implicit representation trained on CTA data to accurately model cardiac shapes from MRI despite anisotropy, improving shape analysis with high fidelity reconstructions.

Contribution

It presents a novel method leveraging CTA data to learn a single neural implicit function for reconstructing cardiac shapes from MRI at any resolution.

Findings

Achieved Dice scores of 0.91 for RV and 0.75 for MYO.

Reconstructed shapes are accurate, smooth, and anatomically plausible.

Demonstrated improved cardiac shape analysis capabilities.

Abstract

The anisotropic nature of short-axis (SAX) cardiovascular magnetic resonance imaging (CMRI) limits cardiac shape analysis. To address this, we propose to leverage near-isotropic, higher resolution computed tomography angiography (CTA) data of the heart. We use this data to train a single neural implicit function to jointly represent cardiac shapes from CMRI at any resolution. We evaluate the method for the reconstruction of right ventricle (RV) and myocardium (MYO), where MYO simultaneously models endocardial and epicardial left-ventricle surfaces. Since high-resolution SAX reference segmentations are unavailable, we evaluate performance by extracting a 4-chamber (4CH) slice of RV and MYO from their reconstructed shapes. When compared with the reference 4CH segmentation masks from CMRI, our method achieved a Dice similarity coefficient of 0.91 $\pm$ 0.07 and 0.75 $\pm$ 0.13, and a Hausdorff distance of 6.21 $\pm$ 3.97 mm and 7.53 $\pm$ 5.13 mm for RV and MYO, respectively. Quantitative and qualitative assessment demonstrate the model's ability to reconstruct accurate, smooth and anatomically plausible shapes, supporting improvements in cardiac shape analysis.