PRO: Projection Domain Synthesis for CT Imaging

TL;DR

PRO introduces a novel projection domain synthesis model for CT imaging that improves data generation fidelity by simulating physical processes, enabling better downstream task performance and controllable synthesis.

Contribution

This is the first study to perform CT synthesis directly in the projection domain, leveraging physical simulation and anatomical prompts for versatile data generation.

Findings

Synthesized data enhances low-dose and sparse-view reconstruction.

Projection domain synthesis improves fidelity over image domain methods.

PRO generalizes across multiple CT imaging tasks.

Abstract

Synthetic CT projection data is crucial for advancing imaging research, yet its generation remains challenging. Current image domain methods are limited as they cannot simulate the physical acquisition process or utilize the complete statistical information present in projection data, restricting their utility and fidelity. In this work, we present PRO, a projection domain synthesis foundation model for CT imaging. To the best of our knowledge, this is the first study that performs CT synthesis in the projection domain. Unlike previous approaches that operate in the image domain, PRO learns rich structural representations from projection data and leverages anatomical text prompts for controllable synthesis. Projection data generation models can utilize complete measurement signals and simulate the physical processes of scanning, including material attenuation characteristics, beam hardening, scattering, and projection geometry, and support research on downstream imaging tasks. Moreover, PRO functions as a foundation model, capable of generalizing across diverse downstream tasks by adjusting its generative behavior via prompt inputs. Experimental results demonstrated that incorporating our synthesized data significantly improves performance across multiple downstream tasks, including low-dose and sparse-view reconstruction. These findings underscore the versatility and scalability of PRO in data generation for various CT applications. These results highlight the potential of projection domain synthesis as a powerful tool for data augmentation and robust CT imaging. Our source code is publicly available at: https://github.com/yqx7150/PRO.