A computationally efficient reconstruction algorithm for circular cone-beam computed tomography using shallow neural networks

TL;DR

This paper introduces the NN-FDK algorithm, a machine learning-augmented reconstruction method for circular cone-beam CT that enhances accuracy and speed, especially in high-noise or limited-data scenarios, with minimal training data.

Contribution

The paper presents the NN-FDK algorithm, combining neural networks with FDK for faster, more accurate CT reconstructions requiring less training data and computational resources.

Findings

NN-FDK outperforms standard algorithms in accuracy under challenging conditions.

NN-FDK is significantly faster to train than deep neural networks.

Reconstruction quality is comparable to deep learning methods with less training data.

Abstract

Circular cone-beam (CCB) Computed Tomography (CT) has become an integral part of industrial quality control, materials science and medical imaging. The need to acquire and process each scan in a short time naturally leads to trade-offs between speed and reconstruction quality, creating a need for fast reconstruction algorithms capable of creating accurate reconstructions from limited data. In this paper we introduce the Neural Network Feldkamp-Davis-Kress (NN-FDK) algorithm. This algorithm adds a machine learning component to the FDK algorithm to improve its reconstruction accuracy while maintaining its computational efficiency. Moreover, the NN-FDK algorithm is designed such that it has low training data requirements and is fast to train. This ensures that the proposed algorithm can be used to improve image quality in high throughput CT scanning settings, where FDK is currently used to keep pace with the acquisition speed using readily available computational resources. We compare the NN-FDK algorithm to two standard CT reconstruction algorithms and to two popular deep neural networks trained to remove reconstruction artifacts from the 2D slices of an FDK reconstruction. We show that the NN-FDK reconstruction algorithm is substantially faster in computing a reconstruction than all the tested alternative methods except for the standard FDK algorithm and we show it can compute accurate CCB CT reconstructions in cases of high noise, a low number of projection angles or large cone angles. Moreover, we show that the training time of an NN-FDK network is orders of magnitude lower than the considered deep neural networks, with only a slight reduction in reconstruction accuracy.