Impact of Deep Learning-based Image Reconstruction on Image Quality and Lesion Visibility in Renal Computed Tomography at Different Doses

Overview

Journal Quant Imaging Med Surg

Specialty Radiology

Date 2023 Apr 17

PMID 37064389

Authors

Yifan Bie

Shuo Yang

Xingchao Li

Kun Zhao

Changlei Zhang

Hai Zhong

Affiliations

Soon will be listed here.

Abstract

Background: Numerous computed tomography (CT) image reconstruction algorithms have been developed to improve image quality, and high-quality renal CT images are crucial to clinical diagnosis. This study evaluated the image quality and lesion visibility of deep learning-based image reconstruction (DLIR) compared with adaptive statistical iterative reconstruction-Veo (ASiR-V) in contrast-enhanced renal CT at different reconstruction strengths and doses.

Methods: From January 2020 to May 2021, we prospectively included 101 patients who underwent renal contrast-enhanced CT scanning (69 at 120 kV; 32 at 80 kV). All image data were reconstructed with ASiR-V (30% and 70%) and DLIR at low, medium, and high reconstruction strengths (DLIR-L, DLIR-M, and DLIR-H, respectively). The CT number, noise, noise reduction rate (NRR), signal-to-noise ratio (SNR), contrast-to-noise ratio (CNR), overall image quality, and the proportion of acceptable images were compared. Lesions of DLIR groups were evaluated, and the conspicuity-to-noise ratio (C/N) was calculated.

Results: Quantitative values (noise, SNR, CNR, and NRR) significantly differed between all reconstructions at 120 and 80 kV (P<0.001) and between each reconstruction, except ASiR-V 70% DLIR-M. At 120 kV, the overall image quality and the proportion of acceptable images significantly differed between all reconstructions (P<0.001) and between each reconstruction, except ASiR-V 30% DLIR-L and ASiR-V 70% DLIR-M. At 80 kV, the overall image quality significantly differed between all reconstructions (P<0.001) and between each reconstruction, except between ASiR-V 30%, ASiR-V 70%, and DLIR-L. Quantitative and qualitative values were highest in DLIR-H, while the values were close in DLIR-H (80 kV) ASiR-V 70% (120 kV) and DLIR-M (80 kV) ASiR-V 30% (120 kV). The lesion conspicuity and noise significantly differed in DLIR at 120 kV and 80 kV (P<0.001). C/N significantly differed in DLIR at 120 kV (P<0.001) but not at 80 kV. DLIR-L and DLIR-M exhibited much-improved lesion display (C/N >1), and DLIR-H exhibited much-improved noise (C/N <1) at 120 kV.

Conclusions: DLIR significantly improved the image quality and lesion visibility of renal CT compared with ASiR-V, even at a low dose.

Citing Articles

Dynamic controllable residual generative adversarial network for low-dose computed tomography imaging.

Xia Z, Liu J, Kang Y, Wang Y, Hu D, Zhang Y Quant Imaging Med Surg. 2023; 13(8):5271-5293.

PMID: 37581059 PMC: 10423351. DOI: 10.21037/qims-22-1384.

References

Geyer L, Schoepf U, Meinel F, Nance Jr J, Bastarrika G, Leipsic J . State of the Art: Iterative CT Reconstruction Techniques. Radiology. 2015; 276(2):339-57. DOI: 10.1148/radiol.2015132766. View

Thitaikumar A, Krouskop T, Ophir J . Signal-to-noise ratio, contrast-to-noise ratio and their trade-offs with resolution in axial-shear strain elastography. Phys Med Biol. 2006; 52(1):13-28. DOI: 10.1088/0031-9155/52/1/002. View

Sun J, Li H, Wang B, Li J, Li M, Zhou Z . Application of a deep learning image reconstruction (DLIR) algorithm in head CT imaging for children to improve image quality and lesion detection. BMC Med Imaging. 2021; 21(1):108. PMC: 8268450. DOI: 10.1186/s12880-021-00637-w. View

Chen L, Jin C, Li J, Wang G, Jia Y, Duan H . Image quality comparison of two adaptive statistical iterative reconstruction (ASiR, ASiR-V) algorithms and filtered back projection in routine liver CT. Br J Radiol. 2018; 91(1088):20170655. PMC: 6209461. DOI: 10.1259/bjr.20170655. View

Shuman W, Green D, Busey J, Kolokythas O, Mitsumori L, Koprowicz K . Model-based iterative reconstruction versus adaptive statistical iterative reconstruction and filtered back projection in liver 64-MDCT: focal lesion detection, lesion conspicuity, and image noise. AJR Am J Roentgenol. 2013; 200(5):1071-6. PMC: 5278542. DOI: 10.2214/AJR.12.8986. View

Hardie A, Nelson R, Egbert R, Rieter W, Tipnis S . What is the preferred strength setting of the sinogram-affirmed iterative reconstruction algorithm in abdominal CT imaging?. Radiol Phys Technol. 2014; 8(1):60-3. DOI: 10.1007/s12194-014-0288-8. View

Krishna S, Murray C, McInnes M, Chatelain R, Siddaiah M, Al-Dandan O . CT imaging of solid renal masses: pitfalls and solutions. Clin Radiol. 2017; 72(9):708-721. DOI: 10.1016/j.crad.2017.05.003. View

Telesmanich M, Jensen C, Enriquez J, Wagner-Bartak N, Liu X, Le O . Third version of vendor-specific model-based iterativereconstruction (Veo 3.0): evaluation of CT image quality in the abdomen using new noise reduction presets and varied slice optimization. Br J Radiol. 2017; 90(1077):20170188. PMC: 5858796. DOI: 10.1259/bjr.20170188. View

Bailey D . Effects of lines of progress and semilogarithmic charts on ratings of charted data. J Appl Behav Anal. 1984; 17(3):359-65. PMC: 1307952. DOI: 10.1901/jaba.1984.17-359. View

10.

Chartrand G, Cheng P, Vorontsov E, Drozdzal M, Turcotte S, Pal C . Deep Learning: A Primer for Radiologists. Radiographics. 2017; 37(7):2113-2131. DOI: 10.1148/rg.2017170077. View

11.

Jensen C, Telesmanich M, Wagner-Bartak N, Liu X, Rong J, Szklaruk J . Evaluation of Abdominal Computed Tomography Image Quality Using a New Version of Vendor-Specific Model-Based Iterative Reconstruction. J Comput Assist Tomogr. 2016; 41(1):67-74. PMC: 5233568. DOI: 10.1097/RCT.0000000000000472. View

12.

Birnbaum B, Hindman N, Lee J, Babb J . Multi-detector row CT attenuation measurements: assessment of intra- and interscanner variability with an anthropomorphic body CT phantom. Radiology. 2006; 242(1):109-19. DOI: 10.1148/radiol.2421052066. View

13.

Zhou B . Predictive values of body mass index and waist circumference for risk factors of certain related diseases in Chinese adults--study on optimal cut-off points of body mass index and waist circumference in Chinese adults. Biomed Environ Sci. 2002; 15(1):83-96. View

14.

Xiao H, Teng X, Liu C, Li T, Ren G, Yang R . A review of deep learning-based three-dimensional medical image registration methods. Quant Imaging Med Surg. 2021; 11(12):4895-4916. PMC: 8611468. DOI: 10.21037/qims-21-175. View

15.

. The 2007 Recommendations of the International Commission on Radiological Protection. ICRP publication 103. Ann ICRP. 2007; 37(2-4):1-332. DOI: 10.1016/j.icrp.2007.10.003. View

16.

Alagic Z, Diaz Cardenas J, Halldorsson K, Grozman V, Wallgren S, Suzuki C . Deep learning versus iterative image reconstruction algorithm for head CT in trauma. Emerg Radiol. 2022; 29(2):339-352. PMC: 8917108. DOI: 10.1007/s10140-021-02012-2. View

17.

Ye K, Zhu Q, Li M, Lu Y, Yuan H . A feasibility study of pulmonary nodule detection by ultralow-dose CT with adaptive statistical iterative reconstruction-V technique. Eur J Radiol. 2019; 119:108652. DOI: 10.1016/j.ejrad.2019.108652. View

18.

Bernard A, Comby P, Lemogne B, Haioun K, Ricolfi F, Chevallier O . Deep learning reconstruction versus iterative reconstruction for cardiac CT angiography in a stroke imaging protocol: reduced radiation dose and improved image quality. Quant Imaging Med Surg. 2021; 11(1):392-401. PMC: 7719916. DOI: 10.21037/qims-20-626. View

19.

Manolov R . Linear Trend in Single-Case Visual and Quantitative Analyses. Behav Modif. 2017; 42(5):684-706. DOI: 10.1177/0145445517726301. View

20.

McCollough C, Leng S . Use of artificial intelligence in computed tomography dose optimisation. Ann ICRP. 2020; 49(1_suppl):113-125. DOI: 10.1177/0146645320940827. View