Deep Filtered Back Projection for CT Reconstruction

Authors

X I Tan
Xuan Liu
Kai Xiang
Jing Wang
Shan Tan

Language

English

Publication Date

1-1-2024

Journal

IEEE Access

DOI

10.1109/access.2024.3357355

PMID

39211346

PMCID

PMC11361368

PubMedCentral® Posted Date

8-29-2024

PubMedCentral® Full Text Version

Author MSS

Abstract

Filtered back projection (FBP) is a classic analytical algorithm for computed tomography (CT) reconstruction, with high computational efficiency. However, images reconstructed by FBP often suffer from excessive noise and artifacts. The original FBP algorithm uses a window function to smooth signals and a linear interpolation to estimate projection values at un-sampled locations. In this study, we propose a novel framework named DeepFBP in which an optimized filter and an optimized nonlinear interpolation operator are learned with neural networks. Specifically, the learned filter can be considered as the product of an optimized window function and the ramp filter, and the learned interpolation can be considered as an optimized way to utilize projection information of nearby locations through nonlinear combination. The proposed method remains the high computational efficiency of the original FBP and achieves much better reconstruction quality at different noise levels. It also outperforms the TV-based statistical iterative algorithm, with computational time being reduced in an order of two, and state-of-the-art post-processing deep learning methods that have deeper and more complicated network structures.

Keywords

Analytical reconstruction, deep learning, FBP, neural network

Published Open-Access

yes

Recommended Citation

Tan, X I; Liu, Xuan; Xiang, Kai; et al., "Deep Filtered Back Projection for CT Reconstruction" (2024). Faculty, Staff and Student Publications. 6632.
https://digitalcommons.library.tmc.edu/uthgsbs_docs/6632