Deep Learning Computed Tomography based on the Defrise and Clack Algorithm

TL;DR

This paper introduces a deep learning-based filtered backprojection algorithm tailored for specific orbit CBCT reconstruction, improving speed and memory efficiency while accurately reconstructing images.

Contribution

It develops a novel adaptive filtering method integrated into FBP-type algorithms, learned from data for specific orbit geometries, enhancing reconstruction performance.

Findings

Successfully learned orbit-specific filter parameters from data

Achieved high-quality image reconstruction closely matching analytical solutions

Improved reconstruction speed and reduced memory usage

Abstract

This study presents a novel approach for reconstructing cone beam computed tomography (CBCT) for specific orbits using known operator learning. Unlike traditional methods, this technique employs a filtered backprojection type (FBP-type) algorithm, which integrates a unique, adaptive filtering process. This process involves a series of operations, including weightings, differentiations, the 2D Radon transform, and backprojection. The filter is designed for a specific orbit geometry and is obtained using a data-driven approach based on deep learning. The approach efficiently learns and optimizes the orbit-related component of the filter. The method has demonstrated its ability through experimentation by successfully learning parameters from circular orbit projection data. Subsequently, the optimized parameters are used to reconstruct images, resulting in outcomes that closely resemble the analytical solution. This demonstrates the potential of the method to learn appropriate parameters from any specific orbit projection data and achieve reconstruction. The algorithm has demonstrated improvement, particularly in enhancing reconstruction speed and reducing memory usage for handling specific orbit reconstruction.