Skip to main content

Advertisement

SpringerLink
Log in

Deep learning-based iodine contrast-augmenting algorithm for low-contrast-dose liver CT to assess hypovascular hepatic metastasis

  • Hepatobiliary
  • Published:
Abdominal Radiology Aims and scope Submit manuscript

Abstract

Purpose

To investigate the image quality and diagnostic performance of low-contrast-dose liver CT using a deep learning-based iodine contrast-augmenting algorithm (DLICA) for hypovascular hepatic metastases.

Methods

This retrospective study included 128 patients who underwent contrast-enhanced dual-energy CT for hepatic metastasis surveillance between July 2019 and June 2022 using a 30% reduced iodine contrast dose in the portal phase. Three image types were reconstructed: 50-keV virtual monoenergetic images (50-keV VMI); linearly blended images simulating 120-kVp images (120-kVp); and post-processed 120-kVp images using DLICA (DLICA 120-kVp). Three reviewers evaluated lesion conspicuity, image contrast, and subjective image noise. We also measured image noise, contrast-to-noise ratios (CNRs), and signal-to-noise ratios (SNRs). The diagnostic performance for hepatic metastases was evaluated using a jackknife alternative free-response receiver operating characteristic method with the consensus of two independent radiologists as the reference standard.

Results

DLICA 120-kVp demonstrated significantly higher CNR of lesions to liver (5.7 ± 3.1 vs. 3.8 ± 2.1 vs. 3.8 ± 2.1) and higher SNR compared with 50-keV VMI and 120-kVp (p < 0.001 for all). DLICA 120-kVp had significantly lower image noise than 50-kVp VMI for all regions (p < 0.001 for all). DLICA 120-kVp also exhibited superior lesion conspicuity (4.0 [3.3–4.3] vs. 3.7 [3.0–4.0] vs. 3.7 [3.0–4.0]), higher image contrast, and lower subjective image noise compared with 50-keV VMI and 120-kVp (p < 0.001 for all). Although there was no significant difference in the figure of merit for lesion diagnosis among the three methods (p = 0.11), DLICA 120-kVp had a significantly higher figure of merit for lesions with a diameter < 20 mm than 50-keV VMI (0.677 vs. 0.648, p = 0.007). On a per-lesion basis, DLICA 120-kVp also demonstrated higher sensitivity than the 50-keV VMI (81.2% vs. 72.9%, p < 0.001). The specificities per lesion were not significantly different among the three algorithms (p = 0.15).

Conclusion

DLICA at 120-kVp provided superior lesion conspicuity and image quality and similar diagnostic performance for hypovascular hepatic metastases compared with 50-keV VMI.

Graphical abstract

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

References

  1. Schima W, Kulinna C, Langenberger H, Ba-Ssalamah A (2005) Liver metastases of colorectal cancer: US, CT or MR? Cancer Imaging 5 Spec No A:S149–S156. https://doi.org/10.1102/1470-7330.2005.0035

  2. Haubold J, Hosch R, Umutlu L et al (2021) Contrast agent dose reduction in computed tomography with deep learning using a conditional generative adversarial network. Eur Radiol 31:6087–6095. https://doi.org/10.1007/s00330-021-07714-2

    Article  CAS  PubMed  PubMed Central  Google Scholar 

  3. Hanson GJ, Michalak GJ, Childs R et al (2018) Low kV versus dual-energy virtual monoenergetic CT imaging for proven liver lesions: what are the advantages and trade-offs in conspicuity and image quality? A pilot study. Abdom Radiol (NY) 43:1404–1412. https://doi.org/10.1007/s00261-017-1327-9

    Article  PubMed  Google Scholar 

  4. De Cecco CN, Darnell A, Rengo M et al (2012) Dual-energy CT: oncologic applications. AJR Am J Roentgenol 199:S98–S105. https://doi.org/10.2214/ajr.12.9207

    Article  PubMed  Google Scholar 

  5. Albrecht MH, Vogl TJ, Martin SS et al (2019) Review of clinical applications for virtual monoenergetic dual-energy CT. Radiology 293:260–271. https://doi.org/10.1148/radiol.2019182297

    Article  PubMed  Google Scholar 

  6. Nagayama Y, Nakaura T, Oda S et al (2018) Dual-layer DECT for multiphasic hepatic CT with 50 percent iodine load: a matched-pair comparison with a 120 kVp protocol. Eur Radiol 28:1719–1730. https://doi.org/10.1007/s00330-017-5114-3

    Article  PubMed  Google Scholar 

  7. Lenga L, Czwikla R, Wichmann JL et al (2018) Dual-energy CT in patients with colorectal cancer: improved assessment of hypoattenuating liver metastases using noise-optimized virtual monoenergetic imaging. Eur J Radiol 106:184-191. https://doi.org/10.1016/j.ejrad.2018.07.027

    Article  PubMed  Google Scholar 

  8. Lenga L, Lange M, Arendt CT et al (2021) Can dual-energy CT-based virtual monoenergetic imaging improve the assessment of hypodense liver metastases in patients with hepatic steatosis? Acad Radiol 28:769–777. https://doi.org/10.1016/j.acra.2020.03.044

    Article  PubMed  Google Scholar 

  9. Martin SS, Pfeifer S, Wichmann JL et al (2017) Noise-optimized virtual monoenergetic dual-energy computed tomography: optimization of kiloelectron volt settings in patients with gastrointestinal stromal tumors. Abdom Radiol (NY) 42:718–726. https://doi.org/10.1007/s00261-016-1011-5

    Article  PubMed  Google Scholar 

  10. Fink MA, Seibold C, Kauczor HU, Stiefelhagen R, Kleesiek J (2022) Jointly optimized deep neural networks to synthesize monoenergetic images from single-energy CT angiography for improving classification of pulmonary embolism. Diagnostics (Basel) 12. https://doi.org/10.3390/diagnostics12051224

    Article  PubMed  Google Scholar 

  11. Gong H, Marsh JF, D'Souza KN et al (2021) Deep-learning-based direct synthesis of low-energy virtual monoenergetic images with multi-energy CT. J Med Imaging (Bellingham) 8:052104. https://doi.org/10.1117/1.jmi.8.5.052104

  12. Kang HJ, Lee JM, Ahn C et al (2023) Low dose of contrast agent and low radiation liver computed tomography with deep-learning-based contrast boosting model in participants at high-risk for hepatocellular carcinoma: prospective, randomized, double-blind study. Eur Radiol 33:3660–3670. https://doi.org/10.1007/s00330-023-09520-4

    Article  PubMed  Google Scholar 

  13. Sica GT (2006) Bias in research studies. Radiology 238:780–789. https://doi.org/10.1148/radiol.2383041109

    Article  PubMed  Google Scholar 

  14. Caruso D, De Cecco CN, Schoepf UJ et al (2017) Can dual-energy computed tomography improve visualization of hypoenhancing liver lesions in portal venous phase? Assessment of advanced image-based virtual monoenergetic images. Clin Imaging 41:118–124. https://doi.org/10.1016/j.clinimag.2016.10.015

    Article  PubMed  Google Scholar 

  15. Tao S, Rajendran K, Zhou W, Fletcher JG, McCollough CH, Leng S (2019) Improving iodine contrast to noise ratio using virtual monoenergetic imaging and prior-knowledge-aware iterative denoising (mono-PKAID). Phys Med Biol 64:105014. https://doi.org/10.1088/1361-6560/ab17fa

  16. Krauss B, Grant KL, Schmidt BT, Flohr TG (2015) The importance of spectral separation: an assessment of dual-energy spectral separation for quantitative ability and dose efficiency. Invest Radiol 50:114–118. https://doi.org/10.1097/rli.0000000000000109

    Article  PubMed  Google Scholar 

  17. Lee T, Lee JM, Yoon JH et al (2022) Deep learning-based image reconstruction of 40-keV virtual monoenergetic images of dual-energy CT for the assessment of hypoenhancing hepatic metastasis. Eur Radiol 32:6407–6417. https://doi.org/10.1007/s00330-022-08728-0

    Article  CAS  PubMed  Google Scholar 

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

    Article  CAS  PubMed  Google Scholar 

  19. Borjesson S, Hakansson M, Bath M et al (2005) A software tool for increased efficiency in observer performance studies in radiology. Radiat Prot Dosimetry 114:45–52. https://doi.org/10.1093/rpd/nch550

    Article  PubMed  Google Scholar 

  20. Jensen CT, Gupta S, Saleh MM et al (2022) Reduced-dose deep learning reconstruction for abdominal CT of liver metastases. Radiology 303:90–98. https://doi.org/10.1148/radiol.211838

    Article  PubMed  Google Scholar 

  21. Robinson E, Babb J, Chandarana H, Macari M (2010) Dual source dual energy MDCT: comparison of 80 kVp and weighted average 120 kVp data for conspicuity of hypo-vascular liver metastases. Invest Radiol 45:413–418. https://doi.org/10.1097/rli.0b013e3181dfda78

    Article  PubMed  Google Scholar 

  22. Yamada Y, Jinzaki M, Tanami Y, Abe T, Kuribayashi S (2012) Virtual monochromatic spectral imaging for the evaluation of hypovascular hepatic metastases: the optimal monochromatic level with fast kilovoltage switching dual-energy computed tomography. Invest Radiol 47:292–298. https://doi.org/10.1097/rli.0b013e318240a874

    Article  PubMed  Google Scholar 

  23. Park J, Shin J, Min IK et al (2022) Image quality and lesion detectability of lower-dose abdominopelvic CT obtained using deep learning image reconstruction. Korean J Radiol 23(4):402–412. https://doi.org/10.3348/kjr.2021.0683

  24. Chen FM, Ni JM, Zhang ZY, Zhang L, Li B, Jiang CJ (2016) Presurgical evaluation of pancreatic cancer: a comprehensive imaging comparison of CT versus MRI. AJR Am J Roentgenol 206:526–535. https://doi.org/10.2214/ajr.15.15236

    Article  PubMed  Google Scholar 

Download references

Funding

This study was supported by a research grant from ClariPi (No. 06-2022-4530).

Author information

Authors and Affiliations

  1. Department of Radiology, Seoul National University Hospital, Seoul, Republic of Korea

    Taehee Lee, Jeong Hee Yoon, Jihyuk Lee & Jeong Min Lee

  2. Department of Radiology, Seoul National University College of Medicine, 101, Daehak-ro, Jongno-gu, Seoul, 03080, Republic of Korea

    Jeong Hee Yoon, Jae Won Choi & Jeong Min Lee

  3. Institute of Radiation Medicine, Seoul National University Medical Research Center, Seoul, Republic of Korea

    Jeong Hee Yoon & Jeong Min Lee

  4. Department of Radiology, Busan Paik Hospital, Inje University College of Medicine, Busan, Republic of Korea

    Jin Young Park

  5. Department of Radiology, Armed Forces Yangju Hospital, Yangju, Republic of Korea

    Jae Won Choi

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

    Chulkyun Ahn

  7. ClariPi Research, Seoul, Republic of Korea

    Chulkyun Ahn

Authors
  1. Taehee Lee
    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. Jin Young Park
    View author publications

    You can also search for this author in PubMed Google Scholar

  4. Jihyuk Lee
    View author publications

    You can also search for this author in PubMed Google Scholar

  5. Jae Won Choi
    View author publications

    You can also search for this author in PubMed Google Scholar

  6. Chulkyun Ahn
    View author publications

    You can also search for this author in PubMed Google Scholar

  7. 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

Conflict of interest

Chulkyun Ahn is an employee of ClariPi. His role was confined to providing the DLICA image sets, and he did not participate in data analysis. Other authors declare no relationships with any companies, whose products or services may be related to the subject matter of the article.

Ethical approval

This retrospective study was approved by the Institutional Review Board of Seoul National University Hospital.

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 660 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

Lee, T., Yoon, J.H., Park, J.Y. et al. Deep learning-based iodine contrast-augmenting algorithm for low-contrast-dose liver CT to assess hypovascular hepatic metastasis. Abdom Radiol 48, 3430–3440 (2023). https://doi.org/10.1007/s00261-023-04039-0

Download citation

  • Received:

  • Revised:

  • Accepted:

  • Published:

  • Issue Date:

  • DOI: https://doi.org/10.1007/s00261-023-04039-0

Keywords

Search

Navigation