Systole-Conditioned Generative Cardiac Motion

2025-07-20

AI Summary

Cardiac CT motion estimation relies on densely annotated 3D optical flow fields, yet ground-truth motion labels are scarce and prohibitively expensive to acquire. To address this, we propose a self-supervised synthetic data generation framework that requires no real motion annotations: a multi-scale feature-conditioned generative model built upon a conditional variational autoencoder (CVAE), capable of synthesizing temporally consistent 3D motion frame pairs and their corresponding high-fidelity 3D optical flow fields from a single input cardiac CT volume. Our method integrates multi-scale feature guidance, explicit 3D deformation field modeling, and differentiable image registration to enable end-to-end, fully supervised synthetic data generation. Experiments demonstrate that models trained on our synthetic data achieve motion estimation accuracy comparable to those trained on real labeled data—significantly alleviating the annotation bottleneck. The generated high-quality training resources advance cardiac functional analysis and surgical planning.

Technology Category

• Computer Vision: Motion & Tracking
• Machine Learning: Deep Generative Models & Autoencoders
• Natural Language Processing: Code Generation / Program Synthesis from Natural Language

Application Category

• Web Mining and Content Analysis: Web data generation and simulation
• User Modeling, Personalization and Recommendation: On-Device user modeling, personalization, and recommendation
• Economics, Online Markets and Human Computation: Data quality aspects of human-annotated datasets

Abstract

Accurate motion estimation in cardiac computed tomography (CT) imaging is critical for assessing cardiac function and surgical planning. Data-driven methods have become the standard approach for dense motion estimation, but they rely on vast amounts of labeled data with dense ground-truth (GT) motion annotations, which are often unfeasible to obtain. To address this limitation, we present a novel approach that synthesizes realistically looking pairs of cardiac CT frames enriched with dense 3D flow field annotations. Our method leverages a conditional Variational Autoencoder (CVAE), which incorporates a novel multi-scale feature conditioning mechanism and is trained to generate 3D flow fields conditioned on a single CT frame. By applying the generated flow field to warp the given frame, we create pairs of frames that simulate realistic myocardium deformations across the cardiac cycle. These pairs serve as fully annotated data samples, providing optical flow GT annotations. Our data generation pipeline could enable the training and validation of more complex and accurate myocardium motion models, allowing for substantially reducing reliance on manual annotations. Our code, along with animated generated samples and additional material, is available on our project page: https://shaharzuler.github.io/GenerativeCardiacMotion_Page.

Problem

• Accurate cardiac motion estimation lacks labeled data
• Generate synthetic cardiac CT frames with flow fields
• Reduce reliance on manual motion annotations

Innovation

• Uses conditional Variational Autoencoder for 3D flow
• Generates synthetic cardiac CT frame pairs
• Reduces need for manual motion annotations