4DRGS: 4D Radiative Gaussian Splatting for Efficient 3D Vessel Reconstruction from Sparse-View Dynamic DSA Images

TL;DR

This paper introduces 4DRGS, a novel method for efficient 3D vessel reconstruction from sparse-view DSA images using 4D radiative Gaussian kernels, achieving high quality and fast training times suitable for clinical use.

Contribution

The paper presents a new 4D radiative Gaussian splatting technique that models static vessel geometry and dynamic contrast flow, significantly improving reconstruction speed and quality.

Findings

Achieves 32x faster training than previous methods.

Produces high-quality 3D vessel reconstructions from sparse-view data.

Demonstrates effectiveness on real patient data within 5 minutes.

Abstract

Reconstructing 3D vessel structures from sparse-view dynamic digital subtraction angiography (DSA) images enables accurate medical assessment while reducing radiation exposure. Existing methods often produce suboptimal results or require excessive computation time. In this work, we propose 4D radiative Gaussian splatting (4DRGS) to achieve high-quality reconstruction efficiently. In detail, we represent the vessels with 4D radiative Gaussian kernels. Each kernel has time-invariant geometry parameters, including position, rotation, and scale, to model static vessel structures. The time-dependent central attenuation of each kernel is predicted from a compact neural network to capture the temporal varying response of contrast agent flow. We splat these Gaussian kernels to synthesize DSA images via X-ray rasterization and optimize the model with real captured ones. The final 3D vessel volume is voxelized from the well-trained kernels. Moreover, we introduce accumulated attenuation pruning and bounded scaling activation to improve reconstruction quality. Extensive experiments on real-world patient data demonstrate that 4DRGS achieves impressive results in 5 minutes training, which is 32x faster than the state-of-the-art method. This underscores the potential of 4DRGS for real-world clinics.