Dyna3DGR: 4D Cardiac Motion Tracking with Dynamic 3D Gaussian Representation

TL;DR

Dyna3DGR introduces a self-supervised framework for 4D cardiac motion tracking that combines explicit Gaussian representations with neural motion fields, outperforming existing methods without extensive training data.

Contribution

The paper presents a novel dynamic 3D Gaussian representation framework that jointly models cardiac structure and motion in a self-supervised manner, addressing limitations of prior methods.

Findings

Outperforms state-of-the-art deep learning registration methods

Maintains topological and temporal consistency in motion tracking

Eliminates need for extensive training data

Abstract

Accurate analysis of cardiac motion is crucial for evaluating cardiac function. While dynamic cardiac magnetic resonance imaging (CMR) can capture detailed tissue motion throughout the cardiac cycle, the fine-grained 4D cardiac motion tracking remains challenging due to the homogeneous nature of myocardial tissue and the lack of distinctive features. Existing approaches can be broadly categorized into image based and representation-based, each with its limitations. Image-based methods, including both raditional and deep learning-based registration approaches, either struggle with topological consistency or rely heavily on extensive training data. Representation-based methods, while promising, often suffer from loss of image-level details. To address these limitations, we propose Dynamic 3D Gaussian Representation (Dyna3DGR), a novel framework that combines explicit 3D Gaussian representation with implicit neural motion field modeling. Our method simultaneously optimizes cardiac structure and motion in a self-supervised manner, eliminating the need for extensive training data or point-to-point correspondences. Through differentiable volumetric rendering, Dyna3DGR efficiently bridges continuous motion representation with image-space alignment while preserving both topological and temporal consistency. Comprehensive evaluations on the ACDC dataset demonstrate that our approach surpasses state-of-the-art deep learning-based diffeomorphic registration methods in tracking accuracy. The code will be available in https://github.com/windrise/Dyna3DGR.