Cycle-Consistent Generative Adversarial Network: Effect on Radiation Dose Reduction and Image Quality Improvement in Ultralow-Dose CT for Evaluation of Pulmonary Tuberculosis

Overview

Journal Korean J Radiol

Specialty Radiology

Date 2021 Mar 19

PMID 33739634

Citations 8

Authors

Chenggong Yan

Jie Lin

Haixia Li

Jun Xu

Tianjing Zhang

Hao Chen

Henry C Woodruff

Guangyao Wu

Siqi Zhang

Yikai Xu

Philippe Lambin

Affiliations

Soon will be listed here.

Abstract

Objective: To investigate the image quality of ultralow-dose CT (ULDCT) of the chest reconstructed using a cycle-consistent generative adversarial network (CycleGAN)-based deep learning method in the evaluation of pulmonary tuberculosis.

Materials And Methods: Between June 2019 and November 2019, 103 patients (mean age, 40.8 ± 13.6 years; 61 men and 42 women) with pulmonary tuberculosis were prospectively enrolled to undergo standard-dose CT (120 kVp with automated exposure control), followed immediately by ULDCT (80 kVp and 10 mAs). The images of the two successive scans were used to train the CycleGAN framework for image-to-image translation. The denoising efficacy of the CycleGAN algorithm was compared with that of hybrid and model-based iterative reconstruction. Repeated-measures analysis of variance and Wilcoxon signed-rank test were performed to compare the objective measurements and the subjective image quality scores, respectively.

Results: With the optimized CycleGAN denoising model, using the ULDCT images as input, the peak signal-to-noise ratio and structural similarity index improved by 2.0 dB and 0.21, respectively. The CycleGAN-generated denoised ULDCT images typically provided satisfactory image quality for optimal visibility of anatomic structures and pathological findings, with a lower level of image noise (mean ± standard deviation [SD], 19.5 ± 3.0 Hounsfield unit [HU]) than that of the hybrid (66.3 ± 10.5 HU, < 0.001) and a similar noise level to model-based iterative reconstruction (19.6 ± 2.6 HU, > 0.908). The CycleGAN-generated images showed the highest contrast-to-noise ratios for the pulmonary lesions, followed by the model-based and hybrid iterative reconstruction. The mean effective radiation dose of ULDCT was 0.12 mSv with a mean 93.9% reduction compared to standard-dose CT.

Conclusion: The optimized CycleGAN technique may allow the synthesis of diagnostically acceptable images from ULDCT of the chest for the evaluation of pulmonary tuberculosis.

Citing Articles

Enhancement of abdominal Low-Dose CT image quality utilizing Clear View reconstruction technique at Mzuzu Central Hospital, Malawi.

Li J, Kondowe B, Wang R, Zhang H, Wang G, Xiao Y Malawi Med J. 2025; 36(5):308-312.

PMID: 40018018 PMC: 11862844. DOI: 10.4314/mmj.v36i5.3.

Improved lung nodule segmentation with a squeeze excitation dilated attention based residual UNet.

Alhajim D, Ansari-Asl K, Akbarizadeh G, Soorki M Sci Rep. 2025; 15(1):3770.

PMID: 39885263 PMC: 11782676. DOI: 10.1038/s41598-025-85199-5.

Revolutionizing diagnosis of pulmonary based on CT: a systematic review of imaging analysis through deep learning.

Zhang F, Han H, Li M, Tian T, Zhang G, Yang Z Front Microbiol. 2025; 15():1510026.

PMID: 39845042 PMC: 11750854. DOI: 10.3389/fmicb.2024.1510026.

Synthesizing High b-Value Diffusion-Weighted Imaging of Gastric Cancer Using an Improved Vision Transformer CycleGAN.

Hu C, Bian C, Cao N, Zhou H, Guo B Bioengineering (Basel). 2024; 11(8).

PMID: 39199763 PMC: 11351349. DOI: 10.3390/bioengineering11080805.

Updated Primer on Generative Artificial Intelligence and Large Language Models in Medical Imaging for Medical Professionals.

Kim K, Cho K, Jang R, Kyung S, Lee S, Ham S Korean J Radiol. 2024; 25(3):224-242.

PMID: 38413108 PMC: 10912493. DOI: 10.3348/kjr.2023.0818.

References

Yamada Y, Jinzaki M, Tanami Y, Shiomi E, Sugiura H, Abe T . Model-based iterative reconstruction technique for ultralow-dose computed tomography of the lung: a pilot study. Invest Radiol. 2012; 47(8):482-9. DOI: 10.1097/RLI.0b013e3182562a89. View

Yan C, Liang C, Xu J, Wu Y, Xiong W, Zheng H . Ultralow-dose CT with knowledge-based iterative model reconstruction (IMR) in evaluation of pulmonary tuberculosis: comparison of radiation dose and image quality. Eur Radiol. 2019; 29(10):5358-5366. DOI: 10.1007/s00330-019-06129-4. View

Finck T, Li H, Grundl L, Eichinger P, Bussas M, Muhlau M . Deep-Learning Generated Synthetic Double Inversion Recovery Images Improve Multiple Sclerosis Lesion Detection. Invest Radiol. 2020; 55(5):318-323. DOI: 10.1097/RLI.0000000000000640. View

Zumla A, George A, Sharma V, Herbert R, Oxley A, Oliver M . The WHO 2014 global tuberculosis report--further to go. Lancet Glob Health. 2014; 3(1):e10-2. DOI: 10.1016/S2214-109X(14)70361-4. View

Tang H, Liu Z, Hu Z, He T, Li D, Yu N . Clinical value of a new generation adaptive statistical iterative reconstruction (ASIR-V) in the diagnosis of pulmonary nodule in low-dose chest CT. Br J Radiol. 2019; 92(1103):20180909. PMC: 6849666. DOI: 10.1259/bjr.20180909. View

Yan C, Xu J, Liang C, Wei Q, Wu Y, Xiong W . Radiation Dose Reduction by Using CT with Iterative Model Reconstruction in Patients with Pulmonary Invasive Fungal Infection. Radiology. 2018; 288(1):285-292. DOI: 10.1148/radiol.2018172107. View

Tie X, Lam S, Zhang Y, Lee K, Au K, Cai J . Pseudo-CT generation from multi-parametric MRI using a novel multi-channel multi-path conditional generative adversarial network for nasopharyngeal carcinoma patients. Med Phys. 2020; 47(4):1750-1762. DOI: 10.1002/mp.14062. View

Zhao T, McNitt-Gray M, Ruan D . A convolutional neural network for ultra-low-dose CT denoising and emphysema screening. Med Phys. 2019; 46(9):3941-3950. DOI: 10.1002/mp.13666. View

Wolterink J, Leiner T, Viergever M, Isgum I . Generative Adversarial Networks for Noise Reduction in Low-Dose CT. IEEE Trans Med Imaging. 2017; 36(12):2536-2545. DOI: 10.1109/TMI.2017.2708987. View

10.

Kaplan S, Zhu Y . Full-Dose PET Image Estimation from Low-Dose PET Image Using Deep Learning: a Pilot Study. J Digit Imaging. 2018; 32(5):773-778. PMC: 6737135. DOI: 10.1007/s10278-018-0150-3. View

11.

Pontana F, Billard A, Duhamel A, Schmidt B, Faivre J, Hachulla E . Effect of Iterative Reconstruction on the Detection of Systemic Sclerosis-related Interstitial Lung Disease: Clinical Experience in 55 Patients. Radiology. 2015; 279(1):297-305. DOI: 10.1148/radiol.2015150849. View

12.

Jeong Y, Lee K . Pulmonary tuberculosis: up-to-date imaging and management. AJR Am J Roentgenol. 2008; 191(3):834-44. DOI: 10.2214/AJR.07.3896. View

13.

Moloney F, James K, Twomey M, Ryan D, Grey T, Downes A . Low-dose CT imaging of the acute abdomen using model-based iterative reconstruction: a prospective study. Emerg Radiol. 2018; 26(2):169-177. DOI: 10.1007/s10140-018-1658-z. View

14.

Shin Y, Chang W, Ye J, Kang E, Oh D, Lee Y . Low-Dose Abdominal CT Using a Deep Learning-Based Denoising Algorithm: A Comparison with CT Reconstructed with Filtered Back Projection or Iterative Reconstruction Algorithm. Korean J Radiol. 2020; 21(3):356-364. PMC: 7039719. DOI: 10.3348/kjr.2019.0413. View

15.

Chen K, Gong E, Carvalho Macruz F, Xu J, Boumis A, Khalighi M . Ultra-Low-Dose F-Florbetaben Amyloid PET Imaging Using Deep Learning with Multi-Contrast MRI Inputs. Radiology. 2018; 290(3):649-656. PMC: 6394782. DOI: 10.1148/radiol.2018180940. View

16.

Kalra M, Sodickson A, Mayo-Smith W . CT Radiation: Key Concepts for Gentle and Wise Use. Radiographics. 2015; 35(6):1706-21. DOI: 10.1148/rg.2015150118. View

17.

Stiller W . Basics of iterative reconstruction methods in computed tomography: A vendor-independent overview. Eur J Radiol. 2018; 109:147-154. DOI: 10.1016/j.ejrad.2018.10.025. View

18.

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

19.

Yang Q, Yan P, Zhang Y, Yu H, Shi Y, Mou X . Low-Dose CT Image Denoising Using a Generative Adversarial Network With Wasserstein Distance and Perceptual Loss. IEEE Trans Med Imaging. 2018; 37(6):1348-1357. PMC: 6021013. DOI: 10.1109/TMI.2018.2827462. View

20.

Yin X, Zhao Q, Liu J, Yang W, Yang J, Quan G . Domain Progressive 3D Residual Convolution Network to Improve Low-Dose CT Imaging. IEEE Trans Med Imaging. 2019; 38(12):2903-2913. DOI: 10.1109/TMI.2019.2917258. View