Skip to main content
SpringerLink
Log in

Value of deep learning reconstruction of chest low-dose CT for image quality improvement and lung parenchyma assessment on lung window

  • Chest
  • Published:
European Radiology Aims and scope Submit manuscript

Abstract

Objectives

To explore the performance of low-dose computed tomography (LDCT) with deep learning reconstruction (DLR) for the improvement of image quality and assessment of lung parenchyma.

Methods

Sixty patients underwent chest regular-dose CT (RDCT) followed by LDCT during the same examination. RDCT images were reconstructed with hybrid iterative reconstruction (HIR) and LDCT images were reconstructed with HIR and DLR, both using lung algorithm. Radiation exposure was recorded. Image noise, signal-to-noise ratio, and subjective image quality of normal and abnormal CT features were evaluated and compared using the Kruskal–Wallis test with Bonferroni correction.

Results

The effective radiation dose of LDCT was significantly lower than that of RDCT (0.29 ± 0.03 vs 2.05 ± 0.65 mSv, p < 0.001). The mean image noise ± standard deviation was 33.9 ± 4.7, 39.6 ± 4.3, and 31.1 ± 3.2 HU in RDCT, LDCT HIR-Strong, and LDCT DLR-Strong, respectively (p < 0.001). The overall image quality of LDCT DLR-Strong was significantly better than that of LDCT HIR-Strong (p < 0.001) and comparable to that of RDCT (p > 0.05). LDCT DLR-Strong was comparable to RDCT in evaluating solid nodules, increased attenuation, linear opacity, and airway lesions (all p > 0.05). The visualization of subsolid nodules and decreased attenuation was better with DLR than with HIR in LDCT but inferior to RDCT (all p < 0.05).

Conclusion

LDCT DLR can effectively reduce image noise and improve image quality. LDCT DLR provides good performance for evaluating pulmonary lesions, except for subsolid nodules and decreased lung attenuation, compared to RDCT-HIR.

Clinical relevance statement

The study prospectively evaluated the contribution of DLR applied to chest low-dose CT for image quality improvement and lung parenchyma assessment. DLR can be used to reduce radiation dose and keep image quality for several indications.

Key Points

• DLR enables LDCT maintaining image quality even with very low radiation doses.

• Chest LDCT with DLR can be used to evaluate lung parenchymal lesions except for subsolid nodules and decreased lung attenuation.

• Diagnosis of pulmonary emphysema or subsolid nodules may require higher radiation doses.

This is a preview of subscription content, log in via an institution to check access.

Access this article

Log in via an institution

Price excludes VAT (USA)
Tax calculation will be finalised during checkout.

Instant access to the full article PDF.

Institutional subscriptions

Fig. 1
Fig. 2
Fig. 3
Fig. 4
Fig. 5
Fig. 6

Similar content being viewed by others

Abbreviations

AiCE:

Advanced Intelligent Clear-IQ Engine

AIDR 3D:

Adaptive Iterative Dose Reduction 3-Dimensional

AP:

Anteroposterior

BMI:

Body mass index

CT:

Computed tomography

CTDIvol :

Volume CT dose index

DCNN:

Deep convolutional neural networks

DLP:

Dose-length product

DLR:

Deep learning reconstruction

ED:

Effective dose

FBP:

Filtered back projection

GGN:

Ground-glass nodule

HIR:

Hybrid iterative reconstruction

HU:

Hounsfield Unit

LAT:

Lateral

LDCT:

Low-dose CT

MBIR:

Model-based iterative reconstruction

RDCT:

Regular-dose CT

ROI:

Regions of interest

SD:

Standard deviation

SNR:

Signal-to-noise ratio

SSDE:

Size-specific dose estimates

Std:

Standard

Str:

Strong

References

  1. Smith-Bindman R, Wang Y, Chu P et al (2019) International variation in radiation dose for computed tomography examinations: prospective cohort study. BMJ 364:k4931

    Article  PubMed  PubMed Central  Google Scholar 

  2. Alsharif W, Qurashi A (2021) Effectiveness of COVID-19 diagnosis and management tools: a review. Radiography (Lond) 27(2):682–687

    Article  CAS  Google Scholar 

  3. Kim H, Park CM, Chae HD et al (2015) Impact of radiation dose and iterative reconstruction on pulmonary nodule measurements at chest CT: a phantom study. Diagn Interv Radiol 21(6):459–465

    Article  PubMed  PubMed Central  Google Scholar 

  4. Zhang M, Qi W, Sun Y et al (2018) Screening for lung cancer using sub-millisievert chest CT with iterative reconstruction algorithm: image quality and nodule detectability. Br J Radiol 91(1090):20170658

    Article  PubMed  Google Scholar 

  5. Ye K, Zhu Q, Li M et al (2019) A feasibility study of pulmonary nodule detection by ultralow-dose CT with adaptive statistical iterative reconstruction-V technique. Eur J Radiol 119:108652

    Article  PubMed  Google Scholar 

  6. Willemink MJ, Noël PB (2019) The evolution of image reconstruction for CT-from filtered back projection to artificial intelligence. Eur Radiol 29(5):2185–2195

    Article  PubMed  Google Scholar 

  7. Hata A, Yanagawa M, Yoshida Y et al (2021) The image quality of deep-learning image reconstruction of chest CT images on a mediastinal window setting. Clin Radiol 76(2):155.e15–155.e23

    Article  CAS  PubMed  Google Scholar 

  8. Singh R, Digumarthy SR, Muse VV et al (2020) Image quality and lesion detection on deep learning reconstruction and iterative reconstruction of submillisievert chest and abdominal CT. AJR Am J Roentgenol 214(3):566–573

    Article  PubMed  Google Scholar 

  9. Kim JH, Yoon HJ, Lee E et al (2021) Validation of deep-learning image reconstruction for low-dose chest computed tomography scan: emphasis on image quality and noise. Korean J Radiol 22(1):131–138

    Article  PubMed  Google Scholar 

  10. Franck C, Zhang G, Deak P et al (2021) Preserving image texture while reducing radiation dose with a deep learning image reconstruction algorithm in chest CT: a phantom study. Phys Med 81:86–93

    Article  PubMed  Google Scholar 

  11. Greffier J, Hamard A, Pereira F et al (2020) Image quality and dose reduction opportunity of deep learning image reconstruction algorithm for CT: a phantom study. Eur Radiol 30(7):3951–3959

    Article  PubMed  Google Scholar 

  12. Svalkvist A, Fagman E, Vikgren J et al (2023) Evaluation of deep-learning image reconstruction for chest CT examinations at two different dose levels. J Appl Clin Med Phys 24(3):e13871

    Article  PubMed  Google Scholar 

  13. Tian Q, Li X, Li J et al (2022) Image quality improvement in low-dose chest CT with deep learning image reconstruction. J Appl Clin Med Phys 23(12):e13796

    Article  PubMed  PubMed Central  Google Scholar 

  14. Wang H, Li LL, Shang J et al (2022) Application of deep learning image reconstruction in low-dose chest CT scan. Br J Radiol 95(1133):20210380

    Article  PubMed  Google Scholar 

  15. Aberle DR, Berg CD, Black WC et al (2011) The National Lung Screening Trial: overview and study design. Radiology 258(1):243–253

    Article  Google Scholar 

  16. Kang H (2021) Sample size determination and power analysis using the G*Power software. J Educ Eval Health Prof 18:17

    Article  PubMed  PubMed Central  Google Scholar 

  17. Jiang B, Li N, Shi X et al (2022) Deep learning reconstruction shows better lung nodule detection for ultra-low-dose chest CT. Radiology 303(1):202–212

    Article  Google Scholar 

  18. Pontana F, Billard AS, Duhamel A et al (2016) Effect of iterative reconstruction on the detection of systemic sclerosis-related interstitial lung disease: clinical experience in 55 patients. Radiol 279(1):297–305

    Article  Google Scholar 

  19. Yamada Y, Jinzaki M, Hosokawa T et al (2012) Dose reduction in chest CT: comparison of the adaptive iterative dose reduction 3D, adaptive iterative dose reduction, and filtered back projection reconstruction techniques. Eur J Radiol 81(12):4185–4195

    Article  PubMed  Google Scholar 

  20. Lee SW, Kim Y, Shim SS et al (2014) Image quality assessment of ultra low-dose chest CT using sinogram-affirmed iterative reconstruction. Eur Radiol 24(4):817–826

    Article  PubMed  Google Scholar 

  21. Hansell DM, Bankier AA, MacMahon H et al (2008) Fleischner Society: glossary of terms for thoracic imaging. Radiology 246(3):697–722

    Article  Google Scholar 

  22. Deak PD, Smal Y, Kalender WA (2010) Multisection CT protocols: sex- and age-specific conversion factors used to determine effective dose from dose-length product. Radiology 257(1):158–166

    Article  Google Scholar 

  23. Christner JA, Braun NN, Jacobsen MC et al (2012) Size-specific dose estimates for adult patients at CT of the torso. Radiology 265(3):841–847

    Article  Google Scholar 

  24. AAPM Task Group 204 (2011) Size-specific dose estimates (SSDE) in pediatric and adult body CT examinations. Report of AAPM Task Group 204. https://www.aapm.org/pubs/reports/RPT_204.pdf. Accessed 20 May 2021

  25. Sui X, Meinel FG, Song W et al (2016) Detection and size measurements of pulmonary nodules in ultra-low-dose CT with iterative reconstruction compared to low dose CT. Eur J Radiol 85(3):564–570

    Article  PubMed  Google Scholar 

  26. Christe A, Charimo-Torrente J, Roychoudhury K et al (2013) Accuracy of low-dose computed tomography (CT) for detecting and characterizing the most common CT-patterns of pulmonary disease. Eur J Radiol 82(3):e142–e150

    Article  PubMed  Google Scholar 

  27. Martini K, Barth BK, Nguyen-Kim TD et al (2016) Evaluation of pulmonary nodules and infection on chest CT with radiation dose equivalent to chest radiography: prospective intra-individual comparison study to standard dose CT. Eur J Radiol 85(2):360–365

    Article  CAS  PubMed  Google Scholar 

  28. Neroladaki A, Botsikas D, Boudabbous S et al (2013) Computed tomography of the chest with model-based iterative reconstruction using a radiation exposure similar to chest X-ray examination: preliminary observations. Eur Radiol 23(2):360–366

    Article  PubMed  Google Scholar 

  29. de Margerie-Mellon C, de Bazelaire C, Montlahuc C et al (2016) Reducing radiation dose at chest CT: comparison among model-based type iterative reconstruction, hybrid iterative reconstruction, and filtered back projection. Acad Radiol 23(10):1246–1254

    Article  PubMed  Google Scholar 

  30. Nagatani Y, Takahashi M, Murata K et al (2015) Lung nodule detection performance in five observers on computed tomography (CT) with adaptive iterative dose reduction using three-dimensional processing (AIDR 3D) in a Japanese multicenter study: comparison between ultra-low-dose CT and low-dose CT by receiver-operating characteristic analysis. Eur J Radiol 84(7):1401–1412

    Article  PubMed  Google Scholar 

  31. Rampinelli C, Origgi D, Vecchi V et al (2015) Ultra-low-dose CT with model-based iterative reconstruction (MBIR): detection of ground-glass nodules in an anthropomorphic phantom study. Radiol Med 120(7):611–617

    Article  PubMed  Google Scholar 

  32. Xu X, Sui X, Song L et al (2019) Feasibility of low-dose CT with spectral shaping and third-generation iterative reconstruction in evaluating interstitial lung diseases associated with connective tissue disease: an intra-individual comparison study. Eur Radiol 29(9):4529–4537

    Article  PubMed  Google Scholar 

  33. Meyer E, Labani A, Schaeffer M et al (2019) Wide-volume versus helical acquisition in unenhanced chest CT: prospective intra-patient comparison of diagnostic accuracy and radiation dose in an ultra-low-dose setting. Eur Radiol 29(12):6858–6866

    Article  PubMed  Google Scholar 

  34. Higaki T, Nakamura Y, Zhou J et al (2020) Deep learning reconstruction at CT: phantom study of the image characteristics. Acad Radiol 27(1):82–87

    Article  PubMed  Google Scholar 

  35. Baldwin DR, Duffy SW, Wald NJ et al (2011) UK Lung Screen (UKLS) nodule management protocol: modelling of a single screen randomised controlled trial of low-dose CT screening for lung cancer. Thorax 66(4):308–313

    Article  CAS  PubMed  Google Scholar 

  36. Ababneh ZQ, Almusallam M, Alfajri I et al (2021) Estimation of the organ and effective dose to patients undergoing medical diagnostic X-ray examinations in Saudi Arabia. Radiat Prot Dosim 194(1):1–8

    Article  Google Scholar 

  37. Park C, Choo KS, Jung Y et al (2021) CT iterative vs deep learning reconstruction: comparison of noise and sharpness. Eur Radiol 31(5):3156–3164

    Article  PubMed  Google Scholar 

  38. Azour L, Hu Y, Ko JP et al (2023) Deep learning denoising of low-dose computed tomography chest images: a quantitative and qualitative image analysis. J Comput Assist Tomogr 47(2):212–219

    Article  PubMed  Google Scholar 

Download references

Acknowledgements

We would like to thank Canon Medical Systems for their technical support in this study.

Funding

This study has received funding by the National Natural Science Foundation of China (NSFC No. 82171934); the National Key R&D Program of China (No. 2021ZD0111105); the National High Level Hospital Clinical Research Funding (2022-PUMCH-B-069); the Beijing Municipal Key Clinical Specialty Excellence Program; the Undergraduate Education and Teaching Reform Program of Peking Union Medical College (2021zlgc0112); the CAMS Innovation Fund for Medical Sciences (CIFMS, 2021-I2M-C&T-A-007); and the 2021 SKY Imaging Research Fund of Chinese International Medical Exchange Foundation (No. Z-2014-07-2101).

Author information

Author notes

  1. Lan Song and Wei Song contributed equally to this work.

Authors and Affiliations

  1. Department of Radiology, Peking Union Medical College Hospital, Peking Union Medical College, Chinese Academy of Medical Sciences, Shuaifuyuan No. 1, Wangfujing Street, Dongcheng District, Beijing, 100730, China

    Jinhua Wang, Xin Sui, Ruijie Zhao, Huayang Du, Jiaru Wang, Yun Wang, Ruiyao Qin, Xiaoping Lu, Zhengyu Jin, Lan Song & Wei Song

  2. Canon Medical System (China), No. 10, Jiuxianqiao North Road, Chaoyang District, Beijing, 100024, China

    Zhuangfei Ma & Yinghao Xu

Authors
  1. Jinhua Wang
    View author publications

    You can also search for this author in PubMed Google Scholar

  2. Xin Sui
    View author publications

    You can also search for this author in PubMed Google Scholar

  3. Ruijie Zhao
    View author publications

    You can also search for this author in PubMed Google Scholar

  4. Huayang Du
    View author publications

    You can also search for this author in PubMed Google Scholar

  5. Jiaru Wang
    View author publications

    You can also search for this author in PubMed Google Scholar

  6. Yun Wang
    View author publications

    You can also search for this author in PubMed Google Scholar

  7. Ruiyao Qin
    View author publications

    You can also search for this author in PubMed Google Scholar

  8. Xiaoping Lu
    View author publications

    You can also search for this author in PubMed Google Scholar

  9. Zhuangfei Ma
    View author publications

    You can also search for this author in PubMed Google Scholar

  10. Yinghao Xu
    View author publications

    You can also search for this author in PubMed Google Scholar

  11. Zhengyu Jin
    View author publications

    You can also search for this author in PubMed Google Scholar

  12. Lan Song
    View author publications

    You can also search for this author in PubMed Google Scholar

  13. Wei Song
    View author publications

    You can also search for this author in PubMed Google Scholar

Corresponding authors

Correspondence to Lan Song or Wei Song.

Ethics declarations

Guarantor

The scientific guarantor of this publication is Wei Song.

Conflict of interest

The authors of this manuscript declare relationships with the following companies: Zhuangfei Ma and Yinghao Xu are employees of Canon Medical Systems, China, which provided the deep learning reconstruction algorithm used in the study. All remaining authors have declared no conflicts of interest.

Statistics and biometry

No complex statistical methods were necessary for this paper.

Informed consent

Written informed consent was received from each enrolled patient after study process was fully explained.

Ethical approval

Institutional Review Board approval was obtained.

Study subjects or cohort overlap

No study subject or cohort overlap has been reported.

Methodology

  • prospective

  • observational

  • performed at one institution

Additional information

Publisher’s note

Springer Nature remains neutral with regard to jurisdictional claims in published maps and institutional affiliations.

Supplementary Information

ESM 1

(PDF 202 kb)

Rights and permissions

Springer Nature or its licensor (e.g. a society or other partner) holds exclusive rights to this article under a publishing agreement with the author(s) or other rightsholder(s); author self-archiving of the accepted manuscript version of this article is solely governed by the terms of such publishing agreement and applicable law.

Reprints and permissions

About this article

Check for updates. Verify currency and authenticity via CrossMark

Cite this article

Wang, J., Sui, X., Zhao, R. et al. Value of deep learning reconstruction of chest low-dose CT for image quality improvement and lung parenchyma assessment on lung window. Eur Radiol 34, 1053–1064 (2024). https://doi.org/10.1007/s00330-023-10087-3

Download citation

  • Received:

  • Revised:

  • Accepted:

  • Published:

  • Issue Date:

  • DOI: https://doi.org/10.1007/s00330-023-10087-3

Keywords

Search

Navigation