CineMesh4D: Personalized 4D Whole Heart Reconstruction from Sparse Cine MRI

2026-05-13

AI Summary

This work addresses the challenge of reconstructing patient-specific four-dimensional (3D+t) whole-heart meshes from sparsely sampled 2D cine MRI, which is hindered by limited anatomical sampling and the strong coupling between cardiac anatomy and motion. The authors propose CineMesh4D, an end-to-end framework that, for the first time, enables full cardiac cycle reconstruction of personalized 4D whole-heart meshes, overcoming the limitations of existing methods that are restricted to partial chambers or single time frames. By establishing a cross-domain image-to-mesh mapping, incorporating differentiable rendering losses for cross-modal supervision, and introducing a dual-context temporal module to integrate local and global temporal dynamics, the method achieves superior reconstruction accuracy and motion consistency. Experimental results demonstrate its significant advantages over current approaches, offering a promising technical pathway for personalized, real-time cardiac functional assessment.

Abstract

Accurate 3D+t whole-heart mesh reconstruction from cine MRI is a clinically crucial yet technically challenging task. The difficulty of this task arises from two coupled factors: inherently sparse sampling of 3D cardiac anatomy by 2D image slices and the tight coupling between cardiac shape and motion. Current cardiac image-to-mesh approaches typically reconstruct only a subset of cardiac chambers or a single phase of the cardiac cycle. In this work, we propose CineMesh4D, a novel end-to-end 4D (3D+t) pipeline that directly reconstructs patient-specific whole-heart mesh from multi-view 2D cine MRI via cross-domain mapping. Specifically, we introduce a differentiable rendering loss that enables supervision of 3D+t whole-heart mesh from multi-view sparse contours of cine MRI. Furthermore, we develop a dual-context temporal block that fuses global and local cardiac temporal information to capture high-dimensional sequential patterns. In quantitative and qualitative evaluations, CineMesh4D outperforms existing approaches in terms of reconstruction quality and motion consistency, providing a practical pathway for personalized real-time cardiac assessment. The code will be publicly released once the manuscript is accepted.

Problem

• 4D whole-heart reconstruction
• cine MRI
• sparse sampling
• cardiac motion
• personalized mesh

Innovation

• 4D cardiac reconstruction
• differentiable rendering loss
• dual-context temporal block
• whole-heart mesh
• cine MRI