Differentiable Forward Projector for X-ray Computed Tomography
This work addresses a specific technical bottleneck in CT reconstruction for medical imaging, providing a tool to improve data consistency in deep learning methods.
The paper tackles the inconsistency between deep learning-predicted CT images and measured projection data by introducing an accurate differentiable forward and back projection software library that supports various geometries and minimizes GPU memory usage, with the software made available as open source.
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.