Skip to main content
SpringerLink
Log in

Image quality in liver CT: low-dose deep learning vs standard-dose model-based iterative reconstructions

  • Computed Tomography
  • Published:
European Radiology Aims and scope Submit manuscript

Abstract

Objectives

To compare the overall image quality and detectability of significant (malignant and pre-malignant) liver lesions of low-dose liver CT (LDCT, 33.3% dose) using deep learning denoising (DLD) to standard-dose CT (SDCT, 100% dose) using model-based iterative reconstruction (MBIR).

Methods

In this retrospective study, CT images of 80 patients with hepatic focal lesions were included. For noninferiority analysis of overall image quality, a margin of − 0.5 points (scored in a 5-point scale) for the difference between scan protocols was pre-defined. Other quantitative or qualitative image quality assessments were performed. Additionally, detectability of significant liver lesions was compared, with 64 pairs of CT, using the jackknife alternative free-response ROC analysis, with noninferior margin defined by the lower limit of 95% confidence interval (CI) of the difference of figure-of-merit less than − 0.1.

Results

The mean overall image quality scores with LDCT and SDCT were 3.77 ± 0.38 and 3.94 ± 0.34, respectively, demonstrating a difference of − 0.17 (95% CI: − 0.21 to − 0.12), which did not cross the predefined noninferiority margin of − 0.5. Furthermore, LDCT showed significantly superior quantitative results of liver lesion contrast to noise ratio (p < 0.05). However, although LDCT scored higher than the average score in qualitative image quality assessments, they were significantly lower than those of SDCT (p < 0.05). Figure-of-merit for lesion detection was 0.859 for LDCT and 0.878 for SDCT, showing noninferiority (difference: − 0.019, 95% CI: − 0.058 to 0.021).

Conclusion

LDCT using DLD with 67% radiation dose reduction showed non-inferior overall image quality and lesion detectability, compared to SDCT.

Key Points

• Low-dose liver CT using deep learning denoising (DLD), at 67% dose reduction, provided non-inferior overall image quality compared to standard-dose CT using model-based iterative reconstruction (MBIR).

• Low-dose CT using DLD showed significantly less noise and higher CNR lesion to liver than standard-dose CT using MBIR and demonstrated at least average image quality score among all readers, albeit with lower scores than standard-dose CT using MBIR.

• Low-dose liver CT showed noninferior detectability for malignant and pre-malignant liver lesions, compared to standard-dose CT.

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

Similar content being viewed by others

Abbreviations

CNR:

Contrast‐to‐noise ratio

CT:

Computed tomography

CTDIvol :

Volume computed tomography dose index

DLD:

Deep learning denoising

DLP:

Dose-length product

FBP:

Filtered back projection

IR:

Iterative reconstruction

LDCT:

Low-dose CT

MBIR:

Model-based iterative reconstruction

NPS:

Noise power spectrum

ROI:

Region of interest

SDCT:

Standard-dose CT

SNR:

Signal-to-noise ratio

References

  1. Brenner DJ (2010) Should we be concerned about the rapid increase in CT usage? Rev Environ Health 25:63–68

    Article  Google Scholar 

  2. Pearce MS, Salotti JA, Little MP et al (2012) Radiation exposure from CT scans in childhood and subsequent risk of leukaemia and brain tumours: a retrospective cohort study. Lancet 380:499–505

    Article  Google Scholar 

  3. Mathews JD, Forsythe AV, Brady Z et al (2013) Cancer risk in 680,000 people exposed to computed tomography scans in childhood or adolescence: data linkage study of 11 million Australians. BMJ 346:f2360

    Article  Google Scholar 

  4. Brenner DJ, Hall EJ (2007) Computed tomography–an increasing source of radiation exposure. N Engl J Med 357:2277–2284

    Article  CAS  Google Scholar 

  5. Mahesh M (2010) Medical radiation exposure with focus on CT. Rev Environ Health 25:69–74

    Article  Google Scholar 

  6. Chityala R, Hoffmann KR, Bednarek DR, Rudin S (2004) Region of interest (ROI) computed tomography. Proc SPIE Int Soc Opt Eng 5368:534–541

    CAS  PubMed  PubMed Central  Google Scholar 

  7. Bubba T, Labate D, Zanghirati G, Bonettini S, Goossens B (2015) Shearlet-based regularized ROI reconstruction in fan beam computed tomography. Proc SPIE 9597. https://doi.org/10.1117/12.2187387

  8. Azencott R, Bodmann BG, Chowdhury T, Labate D, Sen A, Vera D (2015) Region-of-interest reconstruction from truncated cone-beam projections. arXiv preprint arXiv:150201114

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

    Article  Google Scholar 

  10. Kataria B, Althén JN, Smedby Ö, Persson A, Sökjer H, Sandborg M (2018) Assessment of image quality in abdominal CT: potential dose reduction with model-based iterative reconstruction. Eur Radiol 28:2464–2473

    Article  Google Scholar 

  11. Brady SL, Yee BS, Kaufman RA (2012) Characterization of adaptive statistical iterative reconstruction algorithm for dose reduction in CT: a pediatric oncology perspective. Med Phys 39:5520–5531

    Article  CAS  Google Scholar 

  12. Smith EA, Dillman JR, Goodsitt MM, Christodoulou EG, Keshavarzi N, Strouse PJ (2014) Model-based iterative reconstruction: effect on patient radiation dose and image quality in pediatric body CT. Radiology 270:526–534

    Article  Google Scholar 

  13. Gramer BM, Muenzel D, Leber V et al (2012) Impact of iterative reconstruction on CNR and SNR in dynamic myocardial perfusion imaging in an animal model. Eur Radiol 22:2654–2661

    Article  CAS  Google Scholar 

  14. Noël PB, Engels S, Köhler T et al (2018) Evaluation of an iterative model-based CT reconstruction algorithm by intra-patient comparison of standard and ultra-low-dose examinations. Acta Radiol 59:1225–1231

    Article  Google Scholar 

  15. Jensen CT, Liu X, Tamm EP et al (2020) Image quality assessment of abdominal CT by use of new deep learning image reconstruction: initial experience. AJR Am J Roentgenol 215:50–57

    Article  Google Scholar 

  16. 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 214:566–573

    Article  Google Scholar 

  17. Wolterink JM, Leiner T, Viergever MA, Isgum I (2017) Generative adversarial networks for noise reduction in low-dose CT. IEEE Trans Med Imaging 36:2536–2545

    Article  Google Scholar 

  18. Chen H, Zhang Y, Kalra MK et al (2017) Low-dose CT with a residual encoder-decoder convolutional neural network. IEEE Trans Med Imaging 36:2524–2535

    Article  Google Scholar 

  19. Akagi M, Nakamura Y, Higaki T et al (2019) Deep learning reconstruction improves image quality of abdominal ultra-high-resolution CT. Eur Radiol 29:6163–6171

    Article  Google Scholar 

  20. 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 30:3951–3959

    Article  Google Scholar 

  21. Ahn C, Heo C, Kim JH (2019) Combined low-dose simulation and deep learning for CT denoising: application in ultra-low-dose chest CT. Proc SPIE 11050. https://doi.org/10.1117/12.2521539

  22. Wu D, Kim K, El Fakhri G, Li Q (2017) Iterative low-dose CT reconstruction with priors trained by artificial neural network. IEEE Trans Med Imaging 36:2479–2486

    Article  Google Scholar 

  23. Yi X, Babyn P (2018) Sharpness-aware low-dose CT denoising using conditional generative adversarial network. J Digit Imaging 31:655–669

    Article  Google Scholar 

  24. Kang E, Min J, Ye JC (2017) A deep convolutional neural network using directional wavelets for low-dose X-ray CT reconstruction. Med Phys 44:e360–e375

    Article  CAS  Google Scholar 

  25. Brady SL, Trout AT, Somasundaram E, Anton CG, Li Y, Dillman JR (2020) Improving image quality and reducing radiation dose for pediatric CT by using deep learning reconstruction. Radiology. https://doi.org/10.1148/radiol.2020202317:202317

    Article  PubMed  PubMed Central  Google Scholar 

  26. Shin YJ, Chang W, Ye JC et al (2020) 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 21:356–364

    Article  Google Scholar 

  27. Solomon J, Lyu P, Marin D, Samei E (2020) Noise and spatial resolution properties of a commercially available deep learning-based CT reconstruction algorithm. Med Phys. https://doi.org/10.1002/mp.14319

    Article  PubMed  Google Scholar 

  28. Schindera ST, Odedra D, Raza SA et al (2013) Iterative reconstruction algorithm for CT: can radiation dose be decreased while low-contrast detectability is preserved? Radiology 269:511–518

    Article  Google Scholar 

  29. Ellmann S, Kammerer F, Allmendinger T et al (2018) Advanced Modeled Iterative Reconstruction (ADMIRE) facilitates radiation dose reduction in abdominal CT. Acad Radiol 25:1277–1284

    Article  Google Scholar 

  30. Hausleiter J, Martinoff S, Hadamitzky M et al (2010) Image quality and radiation exposure with a low tube voltage protocol for coronary CT angiography results of the PROTECTION II Trial. JACC Cardiovasc Imaging 3:1113–1123

    Article  Google Scholar 

  31. Ahn S, Park SH, Lee KH (2013) How to demonstrate similarity by using noninferiority and equivalence statistical testing in radiology research. Radiology 267:328–338

    Article  Google Scholar 

  32. American Association of Physicists in Medicine (2008) The measurement, reporting, and management of radiation dose in CT. AAPM report. Available via https://www.aapm.org/pubs/reports/RPT_96.pdf

  33. Ahn CK, Jin H, Heo C, Kim JH (2019) Combined low-dose simulation and deep learning for CT denoising: application of ultra-low-dose cardiac CTA. Proc SPIE 10948. https://doi.org/10.1117/12.2513144

  34. Chang W, Lee JM, Lee K et al (2013) Assessment of a model-based, iterative reconstruction algorithm (MBIR) regarding image quality and dose reduction in liver computed tomography. Invest Radiol 48:598–606

    Article  CAS  Google Scholar 

  35. Nam JG, Lee JM, Lee SM et al (2019) High Acceleration three-dimensional T1-weighted dual echo dixon hepatobiliary phase imaging using compressed sensing-sensitivity encoding: comparison of image quality and solid lesion detectability with the standard T1-weighted sequence. Korean J Radiol 20:438–448

    Article  Google Scholar 

  36. Fletcher JG, Yu L, Li Z et al (2015) Observer performance in the detection and classification of malignant hepatic nodules and masses with CT image-space denoising and iterative reconstruction. Radiology 276:465–478

    Article  Google Scholar 

  37. Fletcher JG, Fidler JL, Venkatesh SK et al (2018) Observer performance with varying radiation dose and reconstruction methods for detection of hepatic metastases. Radiology 289:455–464

    Article  Google Scholar 

  38. Choi SJ, Park SH, Shim YS et al (2020) Comparison of image quality and focal lesion detection in abdominopelvic CT: potential dose reduction using advanced modelled iterative reconstruction. Clin Imaging 62:41–48

    Article  Google Scholar 

  39. Hong JH, Park EA, Lee W, Ahn C, Kim JH (2020) Incremental image noise reduction in coronary CT angiography using a deep learning-based technique with iterative reconstruction. Korean J Radiol 21:1165–1177

    Article  Google Scholar 

  40. Solomon J, Marin D, Roy Choudhury K, Patel B, Samei E (2017) Effect of radiation dose reduction and reconstruction algorithm on image noise, contrast, resolution, and detectability of subtle hypoattenuating liver lesions at multidetector CT: filtered back projection versus a commercial model-based iterative reconstruction algorithm. Radiology 284:777–787

    Article  Google Scholar 

  41. Jensen CT, Wagner-Bartak NA, Vu LN et al (2019) Detection of colorectal hepatic metastases is superior at standard radiation dose CT versus reduced dose CT. Radiology 290:400–409

    Article  Google Scholar 

  42. Pooler BD, Lubner MG, Kim DH et al (2017) Prospective evaluation of reduced dose computed tomography for the detection of low-contrast liver lesions: direct comparison with concurrent standard dose imaging. Eur Radiol 27:2055–2066

    Article  Google Scholar 

Download references

Funding

The authors state that this work has not received any funding.

Author information

Authors and Affiliations

  1. Department of Radiology, Seoul National University Hospital, 101 Daehak-ro, Jongno-gu, Seoul, 03080, Republic of Korea

    Sungeun Park, Jeong Hee Yoon, Ijin Joo, Jae Hyun Kim, Junghoan Park, Se Woo Kim, Seungchul Han & Jeong Min Lee

  2. Department of Radiology, Konkuk University Medical Center, Seoul, Republic of Korea

    Sungeun Park

  3. Department of Radiology, Seoul National University College of Medicine, 103 Daehak-ro, Jongnogu, Seoul, 03080, Republic of Korea

    Jeong Hee Yoon, Ijin Joo, Jae Hyun Kim, Seungchul Han, Jong Hyo Kim & Jeong Min Lee

  4. Institute of Radiation Medicine, Seoul National University Medical Research Center, 103 Daehak-ro, Jongno-gu, Seoul, 03087, Republic of Korea

    Jeong Hee Yoon & Jeong Min Lee

  5. Department of Radiology, Konkuk University Medical Center, Konkuk University School of Medicine, Seoul, Republic of Korea

    Mi Hye Yu

  6. Department of Transdisciplinary Studies, Program in Biomedical Radiation Sciences, Graduate School of Convergence Science and Technology, Seoul National University, Seoul, 08826, Republic of Korea

    Chulkyun Ahn & Jong Hyo Kim

  7. Research Institute, ClariPi, Seoul, 03086, Republic of Korea

    Chulkyun Ahn & Jong Hyo Kim

  8. Center for Medical-IT Convergence Technology Research, Advanced Institutes of Convergence Technology, Suwon, 16229, Republic of Korea

    Jong Hyo Kim

Authors
  1. Sungeun Park
    View author publications

    You can also search for this author in PubMed Google Scholar

  2. Jeong Hee Yoon
    View author publications

    You can also search for this author in PubMed Google Scholar

  3. Ijin Joo
    View author publications

    You can also search for this author in PubMed Google Scholar

  4. Mi Hye Yu
    View author publications

    You can also search for this author in PubMed Google Scholar

  5. Jae Hyun Kim
    View author publications

    You can also search for this author in PubMed Google Scholar

  6. Junghoan Park
    View author publications

    You can also search for this author in PubMed Google Scholar

  7. Se Woo Kim
    View author publications

    You can also search for this author in PubMed Google Scholar

  8. Seungchul Han
    View author publications

    You can also search for this author in PubMed Google Scholar

  9. Chulkyun Ahn
    View author publications

    You can also search for this author in PubMed Google Scholar

  10. Jong Hyo Kim
    View author publications

    You can also search for this author in PubMed Google Scholar

  11. Jeong Min Lee
    View author publications

    You can also search for this author in PubMed Google Scholar

Corresponding author

Correspondence to Jeong Min Lee.

Ethics declarations

Guarantor

The scientific guarantor of this publication is Jeong Min Lee (J.M.L.).

Conflict of interest

J.M.L. is a consultant to Samsung Medison; institution received grants from Samsung Medison, GE Healthcare, Philips Healthcare, Bayer, Guerbet, Bracco, Central Medical Service, and Canon Healthcare; institution was compensated for lectures by Bayer, Samsung Medison, and Bracco. However, J.M.L. performs no activities related to the present article and disclosed no relevant relationships.

One author (J.H.K.) was a stockholder of ClariPI, but did not have control over any of the data or information submitted for publication.

One author (C.A.) was an employee of ClariPi and performed imaging data processing, but did not have control over any of statistical analysis for publication.

Other authors of this manuscript declare no relationships with any companies, whose products or services may be related to the subject matter of the article.

Statistics and biometry

This study was revised, under the advice of the Konkuk University Medical Center Research Coordinating Center.

Informed consent

Written informed consent was waived by the Institutional Review Board.

Ethical approval

Institutional Review Board approval was obtained.

Methodology

• retrospective

• observational study 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

Below is the link to the electronic supplementary material.

Supplementary file1 (DOCX 2.21 mb)

Rights and permissions

Reprints and permissions

About this article

Check for updates. Verify currency and authenticity via CrossMark

Cite this article

Park, S., Yoon, J.H., Joo, I. et al. Image quality in liver CT: low-dose deep learning vs standard-dose model-based iterative reconstructions. Eur Radiol 32, 2865–2874 (2022). https://doi.org/10.1007/s00330-021-08380-0

Download citation

  • Received:

  • Revised:

  • Accepted:

  • Published:

  • Issue Date:

  • DOI: https://doi.org/10.1007/s00330-021-08380-0

Keywords

Search

Navigation