Implicit Neural Representations for Registration of Left Ventricle Myocardium During a Cardiac Cycle

2025-01-13

AI Summary

To address low modeling accuracy and high memory consumption in dynamic deformation modeling of the left ventricular myocardium (LVmyo) from cardiac CT sequences, this work introduces implicit neural representations (INRs) to temporal registration for the first time. We propose a continuous, differentiable deformation registration method that jointly leverages signed distance field (SDF)-based geometric priors and CT voxel Hounsfield unit (HU) intensities. By integrating multimodal feature embedding with coordinate-mapping networks, our approach achieves synergistic optimization of anatomical fidelity and tissue information preservation. Experimental results demonstrate an LVmyo registration Dice score exceeding 0.92, a target registration error (TRE) below 1.8 mm, and a 67% reduction in memory footprint. Moreover, the method enables arbitrary-time-point interpolation and high-resolution quantification of myocardial motion.

Technology Category

• Computer Vision: 3D Computer Vision
• Knowledge Representation and Reasoning: Geometric, Spatial, and Temporal Reasoning
• Machine Learning: Calibration & Uncertainty Quantification

Application Category

• Graph Algorithms and Modeling for the Web: Efficient manipulation of static and dynamic Web-related graphs
• User Modeling, Personalization and Recommendation: On-Device user modeling, personalization, and recommendation
• Systems and Infrastructure for Web, Mobile and WoT: Virtualization and resource management in Web systems and infrastructures

Abstract

Understanding the movement of the left ventricle myocardium (LVmyo) during the cardiac cycle is essential for assessing cardiac function. One way to model this movement is through a series of deformable image registrations (DIRs) of the LVmyo. Traditional deep learning methods for DIRs, such as those based on convolutional neural networks, often require substantial memory and computational resources. In contrast, implicit neural representations (INRs) offer an efficient approach by operating on any number of continuous points. This study extends the use of INRs for DIR to cardiac computed tomography (CT), focusing on LVmyo registration. To enhance the precision of the registration around the LVmyo, we incorporate the signed distance field of the LVmyo with the Hounsfield Unit values from the CT frames. This guides the registration of the LVmyo, while keeping the tissue information from the CT frames. Our framework demonstrates high registration accuracy and provides a robust method for temporal registration that facilitates further analysis of LVmyo motion.

Problem

• Left Ventricular Myocardium
• Heartbeat Motion
• Cardiac Health Analysis

Innovation

• Implicit Neural Representations
• Left Ventricular Myocardium
• Deformable Image Registration