Differentiable Forward Projector for X-ray Computed Tomography

Hyojin Kim, Kyle Champley
7/11/2023
cs.LGcs.CVcs.MS

Official code: llnl/LEAP (237 stars, MIT, last commit 2026-04-28).

Abstract

Data-driven deep learning has been successfully applied to various computed tomographic reconstruction problems. The deep inference models may outperform existing analytical and iterative algorithms, especially in ill-posed CT reconstruction. However, those methods often predict images that do not agree with the measured projection data. This paper presents an accurate differentiable forward and back projection software library to ensure the consistency between the predicted images and the original measurements. The software library efficiently supports various projection geometry types while minimizing the GPU memory footprint requirement, which facilitates seamless integration with existing deep learning training and inference pipelines. The proposed software is available as open source: https://github.com/LLNL/LEAP.

View on arXivView PDF

Code Implementations(1)

llnl/LEAPOfficial100%
MIT

comprehensive library of 3D transmission Computed Tomography (CT) algorithms with Python and C++ APIs, a PyQt GUI, and fully integrated with PyTorch

23730C, C++May 23, 20235 months agoMIT
abel-transformartificial-intelligencebeamhardeningbhccomputed-tomography+15 more

Similar Papers

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

83% match1 repo1222025

Task-based Generation of Optimized Projection Sets using Differentiable Ranking

80% match2023

Compressibility Analysis for the differentiable shift-variant Filtered Backprojection Model

80% match2025

Benchmarking learned algorithms for computed tomography image reconstruction tasks

77% match2024

Glimpse: Generalized Locality for Scalable and Robust CT

77% match1 repo82024

Differentiable Visual Computing for Inverse Problems and Machine Learning

77% match2023

Cite this paper

@article{kim2023differentiable,
  title  = {Differentiable Forward Projector for X-ray Computed Tomography},
  author = {Hyojin Kim and Kyle Champley},
  year   = {2023},
  eprint = {2307.05801},
  archivePrefix = {arXiv},
  url    = {http://arxiv.org/abs/2307.05801v1}
}

Add a badge to your README

Shows whether official code is linked for this paper.

Code of Paper badge
[![Code of Paper](https://codeofpaper.com/badge/2307.05801.svg)](https://codeofpaper.com/paper/2307.05801)

Discussion