Latent Interpolation Learning Using Diffusion Models for Cardiac Volume Reconstruction

2025-08-19

AI Summary

Sparse 2D cardiac magnetic resonance (CMR) short-axis slices yield incomplete 3D volumetric reconstructions; existing methods rely on handcrafted interpolation, suffer from computational inefficiency, and require segmentation labels or motion priors. Method: We propose CaLID—the first diffusion-based, latent-space data-driven interpolation framework for end-to-end, semantics-agnostic, high-fidelity whole-heart 3D reconstruction from sparse 2D CMR images alone. It employs a variational autoencoder for dimensionality reduction and jointly models spatial and temporal dependencies in the latent space. Contribution/Results: CaLID is the first to formulate diffusion interpolation in the latent space, ensuring spatiotemporal consistency without semantic supervision. Experiments demonstrate that CaLID achieves state-of-the-art performance in volumetric accuracy and downstream segmentation tasks, while accelerating reconstruction by 24× over prior methods—significantly enhancing both clinical utility and computational efficiency.

Technology Category

• Computer Vision: Diffusion Models for Vision
• Machine Learning: Multimodal Learning
• Knowledge Representation and Reasoning: Geometric, Spatial, and Temporal Reasoning

Application Category

• User Modeling, Personalization and Recommendation: Explainable and interpretable methods for personalization
• Graph Algorithms and Modeling for the Web: Representation, reconstruction, and subgraph or motif discovery in Web-related graphs
• Semantics and Knowledge: Methods to enhance, augment, integrate or synergize semantic models such as knowledge graphs and LLMs

Abstract

Cardiac Magnetic Resonance (CMR) imaging is a critical tool for diagnosing and managing cardiovascular disease, yet its utility is often limited by the sparse acquisition of 2D short-axis slices, resulting in incomplete volumetric information. Accurate 3D reconstruction from these sparse slices is essential for comprehensive cardiac assessment, but existing methods face challenges, including reliance on predefined interpolation schemes (e.g., linear or spherical), computational inefficiency, and dependence on additional semantic inputs such as segmentation labels or motion data. To address these limitations, we propose a novel extbf{Ca}rdiac extbf{L}atent extbf{I}nterpolation extbf{D}iffusion (CaLID) framework that introduces three key innovations. First, we present a data-driven interpolation scheme based on diffusion models, which can capture complex, non-linear relationships between sparse slices and improves reconstruction accuracy. Second, we design a computationally efficient method that operates in the latent space and speeds up 3D whole-heart upsampling time by a factor of 24, reducing computational overhead compared to previous methods. Third, with only sparse 2D CMR images as input, our method achieves SOTA performance against baseline methods, eliminating the need for auxiliary input such as morphological guidance, thus simplifying workflows. We further extend our method to 2D+T data, enabling the effective modeling of spatiotemporal dynamics and ensuring temporal coherence. Extensive volumetric evaluations and downstream segmentation tasks demonstrate that CaLID achieves superior reconstruction quality and efficiency. By addressing the fundamental limitations of existing approaches, our framework advances the state of the art for spatio and spatiotemporal whole-heart reconstruction, offering a robust and clinically practical solution for cardiovascular imaging.

Problem

• Reconstructing 3D cardiac volumes from sparse 2D MRI slices
• Overcoming reliance on predefined interpolation schemes and auxiliary inputs
• Improving computational efficiency for whole-heart reconstruction

Innovation

• Data-driven interpolation using diffusion models
• Latent space operation for computational efficiency
• Eliminates need for auxiliary input data