An update to PYRO-NN: A Python Library for Differentiable CT Operators

TL;DR

This paper presents an updated Python library, PYRO-NN, for differentiable CT reconstruction that now supports PyTorch, CUDA, and various geometries, enabling efficient, flexible, and trainable imaging pipelines.

Contribution

The update introduces PyTorch compatibility, native CUDA support, and new tools for artifact simulation and trajectory modeling in the PYRO-NN library.

Findings

Enhanced computational efficiency with CUDA kernels.

Broader applicability across different CT geometries.

Facilitates end-to-end trainable CT reconstruction pipelines.

Abstract

Deep learning has brought significant advancements to X-ray Computed Tomography (CT) reconstruction, offering solutions to challenges arising from modern imaging technologies. These developments benefit from methods that combine classical reconstruction techniques with data-driven approaches. Differentiable operators play a key role in this integration by enabling end-to-end optimization and the incorporation of physical modeling within neural networks. In this work, we present an updated version of PYRO-NN, a Python-based library for differentiable CT reconstruction. The updated framework extends compatibility to PyTorch and introduces native CUDA kernel support for efficient projection and back-projection operations across parallel, fan, and cone-beam geometries. Additionally, it includes tools for simulating imaging artifacts, modeling arbitrary acquisition trajectories, and creating flexible, end-to-end trainable pipelines through a high-level Python API. Code is available at: https://github.com/csyben/PYRO-NN