TiAVox: Time-aware Attenuation Voxels for Sparse-view 4D DSA Reconstruction

TL;DR

TiAVox introduces a physical, neural network-free method for high-quality sparse-view 4D DSA reconstruction, significantly reducing radiation dose while maintaining detailed imaging of vascular structures.

Contribution

The paper proposes TiAVox, a novel time-aware attenuation voxel approach that enables sparse-view 4D DSA reconstruction without neural networks, improving efficiency and interpretability.

Findings

Achieved 31.23 PSNR with 30 views on clinical data.

Achieved 34.32 PSNR with 10 views on synthetic data.

Outperformed traditional methods requiring more views.

Abstract

Four-dimensional Digital Subtraction Angiography (4D DSA) plays a critical role in the diagnosis of many medical diseases, such as Arteriovenous Malformations (AVM) and Arteriovenous Fistulas (AVF). Despite its significant application value, the reconstruction of 4D DSA demands numerous views to effectively model the intricate vessels and radiocontrast flow, thereby implying a significant radiation dose. To address this high radiation issue, we propose a Time-aware Attenuation Voxel (TiAVox) approach for sparse-view 4D DSA reconstruction, which paves the way for high-quality 4D imaging. Additionally, 2D and 3D DSA imaging results can be generated from the reconstructed 4D DSA images. TiAVox introduces 4D attenuation voxel grids, which reflect attenuation properties from both spatial and temporal dimensions. It is optimized by minimizing discrepancies between the rendered images and sparse 2D DSA images. Without any neural network involved, TiAVox enjoys specific physical interpretability. The parameters of each learnable voxel represent the attenuation coefficients. We validated the TiAVox approach on both clinical and simulated datasets, achieving a 31.23 Peak Signal-to-Noise Ratio (PSNR) for novel view synthesis using only 30 views on the clinically sourced dataset, whereas traditional Feldkamp-Davis-Kress methods required 133 views. Similarly, with merely 10 views from the synthetic dataset, TiAVox yielded a PSNR of 34.32 for novel view synthesis and 41.40 for 3D reconstruction. We also executed ablation studies to corroborate the essential components of TiAVox. The code will be publically available.