Related Experiment Video
Updated: Sep 8, 2025
Automated Midline Shift and Intracranial Pressure Estimation based on Brain CT Images
Published on: April 13, 2013
Comparison of a Deep Learning-Based Reconstruction Algorithm with Filtered Back Projection and Iterative
Wookon Son1, MinWoo Kim2, Jae-Yeon Hwang1,3
1Department of Radiology, Pusan National University Yangsan Hospital, Yangsan, Korea.
Insights
Deep learning-based reconstruction (DLR) offers improved image quality and spatial resolution in pediatric abdominopelvic CT scans compared to traditional iterative reconstruction (IR) methods. This advanced algorithm shows promise for clearer diagnostic imaging in young patients.
Area of Science:
- Radiology
- Medical Imaging
- Artificial Intelligence in Medicine
Background:
- Pediatric abdominopelvic computed tomography (CT) imaging requires high-quality reconstructions for accurate diagnosis.
- Traditional reconstruction algorithms like filtered back projection (FBP) and iterative reconstruction (IR) have limitations in noise reduction and spatial resolution.
- Deep learning-based reconstruction (DLR) algorithms are emerging as a potential advancement in medical image processing.
Purpose of the Study:
- To compare the performance of a deep learning-based reconstruction (DLR) algorithm against filtered back projection (FBP) and hybrid iterative reconstruction (IR) algorithms for pediatric abdominopelvic CT.
- To evaluate image noise, spatial resolution, and overall image quality using objective and subjective measures.
Main Methods:
- Retrospective analysis of 120 pediatric abdominopelvic CT scans.
- Reconstruction of images using FBP, hybrid IR (ASiR-V at 50% and 100% blending), and DLR (TrueFidelity at low, medium, and high strengths).
- Objective assessment using noise power spectrum (NPS) and edge-spread function (ERD); subjective assessment by two pediatric radiologists for image quality, lesion detectability, and artifacts.
Main Results:
- DLR demonstrated shorter edge-rise distance (ERD), indicating better spatial resolution, compared to ASiR-V and FBP (p < 0.001).
- High-strength DLR yielded superior overall image quality compared to ASiR-V (p < 0.001).
- While AV100 had lower noise magnitude, DLR showed higher NPS average spatial frequencies, suggesting a different noise profile.
Conclusions:
- Deep learning-based reconstruction (DLR) may offer enhanced noise characteristics and superior spatial resolution for pediatric abdominopelvic CT.
- DLR shows potential for improving diagnostic accuracy in pediatric CT imaging.
- Further research may validate DLR as a preferred reconstruction method in pediatric radiology.
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.
