Comparison of a Deep Learning-Based Reconstruction Algorithm with Filtered Back Projection and Iterative Reconstruction Algorithms for Pediatric Abdominopelvic CT

Wookon Son; MinWoo Kim; Jae-Yeon Hwang; Yong-Woo Kim; Chankue Park; Ki Seok Choo; Tae Un Kim; Joo Yeon Jang

doi:10.3348/kjr.2021.0466

Comparison of a Deep Learning-Based Reconstruction Algorithm with Filtered Back Projection and Iterative Reconstruction Algorithms for Pediatric Abdominopelvic CT

Korean J Radiol. 2022 Jul;23(7):752-762. doi: 10.3348/kjr.2021.0466. Epub 2022 May 27.

Authors

Wookon Son^#¹, MinWoo Kim^#², Jae-Yeon Hwang^{1

3}, Yong-Woo Kim¹, Chankue Park¹, Ki Seok Choo¹, Tae Un Kim¹, Joo Yeon Jang¹

Affiliations

¹ Department of Radiology, Pusan National University Yangsan Hospital, Yangsan, Korea.
² School of Biomedical Convergence Engineering, Pusan National University, Busan, Korea.
³ Research Institute for Convergence of Biomedical Science and Technology, Pusan National University Yangsan Hospital, College of Medicine, Pusan National University, Yangsan, Korea. jyhwang79@gmail.com.

^# Contributed equally.

Abstract

Objective: To compare a deep learning-based reconstruction (DLR) algorithm for pediatric abdominopelvic computed tomography (CT) with filtered back projection (FBP) and iterative reconstruction (IR) algorithms.

Materials and methods: Post-contrast abdominopelvic CT scans obtained from 120 pediatric patients (mean age ± standard deviation, 8.7 ± 5.2 years; 60 males) between May 2020 and October 2020 were evaluated in this retrospective study. Images were reconstructed using FBP, a hybrid IR algorithm (ASiR-V) with blending factors of 50% and 100% (AV50 and AV100, respectively), and a DLR algorithm (TrueFidelity) with three strength levels (low, medium, and high). Noise power spectrum (NPS) and edge rise distance (ERD) were used to evaluate noise characteristics and spatial resolution, respectively. Image noise, edge definition, overall image quality, lesion detectability and conspicuity, and artifacts were qualitatively scored by two pediatric radiologists, and the scores of the two reviewers were averaged. A repeated-measures analysis of variance followed by the Bonferroni post-hoc test was used to compare NPS and ERD among the six reconstruction methods. The Friedman rank sum test followed by the Nemenyi-Wilcoxon-Wilcox all-pairs test was used to compare the results of the qualitative visual analysis among the six reconstruction methods.

Results: The NPS noise magnitude of AV100 was significantly lower than that of the DLR, whereas the NPS peak of AV100 was significantly higher than that of the high- and medium-strength DLR (p < 0.001). The NPS average spatial frequencies were higher for DLR than for ASiR-V (p < 0.001). ERD was shorter with DLR than with ASiR-V and FBP (p < 0.001). Qualitative visual analysis revealed better overall image quality with high-strength DLR than with ASiR-V (p < 0.001).

Conclusion: For pediatric abdominopelvic CT, the DLR algorithm may provide improved noise characteristics and better spatial resolution than the hybrid IR algorithm.

Keywords: Abdomen; Deep learning; Image reconstruction; Pediatrics; Tomography.

MeSH terms

Adolescent
Algorithms
Child
Child, Preschool
Deep Learning*
Humans
Image Processing, Computer-Assisted
Male
Radiation Dosage
Radiographic Image Interpretation, Computer-Assisted* / methods
Retrospective Studies
Tomography, X-Ray Computed / methods