TPG-INR: Target Prior-Guided Implicit 3D CT Reconstruction for Enhanced Sparse-view Imaging

TL;DR

This paper introduces TPG-INR, a novel 3D CT reconstruction method that uses target priors from projection data to improve implicit learning, significantly boosting efficiency and accuracy in sparse-view imaging.

Contribution

It proposes a target prior-guided framework with a CUDA algorithm for rapid prior estimation, enhancing implicit 3D reconstruction in ultra-sparse view scenarios.

Findings

Outperforms NAF by a factor of ten in learning efficiency.

Achieves PSNR improvements of 3.57, 5.42, and 5.70 dB with 10, 20, and 30 projections.

Demonstrates superior reconstruction quality on complex abdominal datasets.

Abstract

X-ray imaging, based on penetration, enables detailed visualization of internal structures. Building on this capability, existing implicit 3D reconstruction methods have adapted the NeRF model and its variants for internal CT reconstruction. However, these approaches often neglect the significance of objects' anatomical priors for implicit learning, limiting both reconstruction precision and learning efficiency, particularly in ultra-sparse view scenarios. To address these challenges, we propose a novel 3D CT reconstruction framework that employs a 'target prior' derived from the object's projection data to enhance implicit learning. Our approach integrates positional and structural encoding to facilitate voxel-wise implicit reconstruction, utilizing the target prior to guide voxel sampling and enrich structural encoding. This dual strategy significantly boosts both learning efficiency and reconstruction quality. Additionally, we introduce a CUDA-based algorithm for rapid estimation of high-quality 3D target priors from sparse-view projections. Experiments utilizing projection data from a complex abdominal dataset demonstrate that the proposed model substantially enhances learning efficiency, outperforming the current leading model, NAF, by a factor of ten. In terms of reconstruction quality, it also exceeds the most accurate model, NeRP, achieving PSNR improvements of 3.57 dB, 5.42 dB, and 5.70 dB with 10, 20, and 30 projections, respectively. The code is available at https://github.com/qlcao171/TPG-INR.