Neural Implicit Heart Coordinates: 3D cardiac shape reconstruction from sparse segmentations

2025-12-22

AI Summary

To address the challenge of reconstructing patient-specific 3D cardiac anatomy with high fidelity from sparse, clinically acquired 2D segmentation images, this paper introduces Normalized Neural Implicit Heart Coordinates (NIHCs)—the first neural implicit modeling framework grounded in universal ventricular coordinates. NIHCs learn, in an end-to-end manner, a mapping from sparse 2D segmentations to continuous implicit coordinate fields, enabling anatomically faithful 3D reconstruction even under extreme slice sparsity (e.g., only 3–5 slices) and segmentation noise—particularly preserving critical structures such as valve planes. Trained on a large-scale cardiac mesh dataset comprising 10,107 cases, NIHCs achieves mean 3D surface errors of 2.51±0.33 mm (disease cohort, n=4549) and 2.30±0.36 mm (healthy cohort, n=5576). Inference time is reduced to 5–15 seconds, and the framework supports arbitrary-resolution mesh generation and cross-subject anatomical alignment.

Technology Category

• Computer Vision: 3D Computer Vision
• Cognitive Modeling & Cognitive Systems: Neural Spike Coding
• Machine Learning: Deep Generative Models & Autoencoders

Application Category

• Economics, Online Markets and Human Computation: Data quality aspects of human-annotated datasets
• Graph Algorithms and Modeling for the Web: Graph embeddings and representation learning for Web-related graphs
• User Modeling, Personalization and Recommendation: On-Device user modeling, personalization, and recommendation

Abstract

Accurate reconstruction of cardiac anatomy from sparse clinical images remains a major challenge in patient-specific modeling. While neural implicit functions have previously been applied to this task, their application to mapping anatomical consistency across subjects has been limited. In this work, we introduce Neural Implicit Heart Coordinates (NIHCs), a standardized implicit coordinate system, based on universal ventricular coordinates, that provides a common anatomical reference frame for the human heart. Our method predicts NIHCs directly from a limited number of 2D segmentations (sparse acquisition) and subsequently decodes them into dense 3D segmentations and high-resolution meshes at arbitrary output resolution. Trained on a large dataset of 5,000 cardiac meshes, the model achieves high reconstruction accuracy on clinical contours, with mean Euclidean surface errors of 2.51$pm$0.33 mm in a diseased cohort (n=4549) and 2.3$pm$0.36 mm in a healthy cohort (n=5576). The NIHC representation enables anatomically coherent reconstruction even under severe slice sparsity and segmentation noise, faithfully recovering complex structures such as the valve planes. Compared with traditional pipelines, inference time is reduced from over 60 s to 5-15 s. These results demonstrate that NIHCs constitute a robust and efficient anatomical representation for patient-specific 3D cardiac reconstruction from minimal input data.

Problem

• Reconstructs 3D cardiac anatomy from sparse 2D segmentations.
• Establishes a standardized implicit coordinate system for anatomical consistency.
• Enables fast, accurate reconstruction under severe data sparsity and noise.

Innovation

• Neural Implicit Heart Coordinates standardize anatomical reference frame
• Predicts coordinates from sparse 2D segmentations for dense 3D reconstruction
• Enables fast, robust reconstruction from minimal input data