Deep learning–based image restoration algorithm for coronary CT angiography

  • Fuminari TatsugamiEmail author
  • Toru Higaki
  • Yuko Nakamura
  • Zhou Yu
  • Jian Zhou
  • Yujie Lu
  • Chikako Fujioka
  • Toshiro Kitagawa
  • Yasuki Kihara
  • Makoto Iida
  • Kazuo Awai



The purpose of this study was to compare the image quality of coronary computed tomography angiography (CTA) subjected to deep learning–based image restoration (DLR) method with images subjected to hybrid iterative reconstruction (IR).


We enrolled 30 patients (22 men, 8 women) who underwent coronary CTA on a 320-slice CT scanner. The images were reconstructed with hybrid IR and with DLR. The image noise in the ascending aorta, left atrium, and septal wall of the ventricle was measured on all images and the contrast-to-noise ratio (CNR) in the proximal coronary arteries was calculated. We also generated CT attenuation profiles across the proximal coronary arteries and measured the width of the edge rise distance (ERD) and the edge rise slope (ERS). Two observers visually evaluated the overall image quality using a 4-point scale (1 = poor, 4 = excellent).


On DLR images, the mean image noise was lower than that on hybrid IR images (18.5 ± 2.8 HU vs. 23.0 ± 4.6 HU, p < 0.01) and the CNR was significantly higher (p < 0.01). The mean ERD was significantly shorter on DLR than on hybrid IR images, whereas the mean ERS was steeper on DLR than on hybrid IR images. The mean image quality score for hybrid IR and DLR images was 2.96 and 3.58, respectively (p < 0.01).


DLR reduces the image noise and improves the image quality at coronary CTA.

Key Points

• Deep learning–based image restoration is a new technique that employs the deep convolutional neural network for image quality improvement.

• Deep learning–based restoration reduces the image noise and improves image quality at coronary CT angiography.

• This method may allow for a reduction in radiation exposure.


Computed tomography angiography Cardiac imaging techniques Artificial intelligence Image enhancement 



Contrast-to-noise ratio


Computed tomography angiography


Deep convolutional neural network


Deep learning–based image restoration


Edge rise distance


Edge rise slope



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

Compliance with ethical standards


The scientific guarantor of this publication is Kazuo Awai.

Conflict of interest

Kazuo Awai received a research grant from Canon Medical Systems Co. Ltd. Zhou Yu, Jian Zhou, and Yujie Lu are employees of Canon Medical Research USA. The other authors declare that they have no conflict of interest.

Statistics and biometry

No complex statistical methods were necessary for this paper.

Informed consent

Written informed consent was waived by the Institutional Review Board.

Ethical approval

Institutional Review Board approval was obtained.


• retrospective

• diagnostic or prognostic study

• performed at one institution


  1. 1.
    Raff GL, Gallagher MJ, O’Neill WW, Goldstein JA (2005) Diagnostic accuracy of noninvasive coronary angiography using 64-slice spiral computed tomography. J Am Coll Cardiol 46:552–557CrossRefGoogle Scholar
  2. 2.
    Nikolaou K, Knez A, Rist C et al (2006) Accuracy of 64-MDCT in the diagnosis of ischemic heart disease. AJR Am J Roentgenol 187:111–117CrossRefGoogle Scholar
  3. 3.
    Herzog C, Zwerner PL, Doll JR et al (2007) Significant coronary artery stenosis: comparison on per-patient and per-vessel or per-segment basis at 64-section CT angiography. Radiology 244:112–120CrossRefGoogle Scholar
  4. 4.
    Dreyer KJ, Geis JR (2017) When machines think: radiology’s next frontier. Radiology 285:713–718CrossRefGoogle Scholar
  5. 5.
    Kahn CE Jr (2017) From images to actions: opportunities for artificial intelligence in radiology. Radiology 285:719–720CrossRefGoogle Scholar
  6. 6.
    Chartrand G, Cheng PM, Vorontsov E et al (2017) Deep learning: a primer for radiologists. Radiographics 37:2113–2131CrossRefGoogle Scholar
  7. 7.
    Anthimopoulos M, Christodoulidis S, Ebner L, Christe A, Mougiakakou S (2016) Lung pattern classification for interstitial lung diseases using a deep convolutional neural network. IEEE Trans Med Imaging 35:1207–1216CrossRefGoogle Scholar
  8. 8.
    Becker AS, Marcon M, Ghafoor S, Wurnig MC, Frauenfelder T, Boss A (2017) Deep learning in mammography: diagnostic accuracy of a multipurpose image analysis software in the detection of breast cancer. Invest Radiol 52:434–440CrossRefGoogle Scholar
  9. 9.
    Yoshida H, Nappi J (2007) CAD in CT colonography without and with oral contrast agents: progress and challenges. Comput Med Imaging Graph 31:267–284CrossRefGoogle Scholar
  10. 10.
    Bauer S, Wiest R, Nolte LP, Reyes M (2013) A survey of MRI-based medical image analysis for brain tumor studies. Phys Med Biol 58:R97–R129Google Scholar
  11. 11.
    Chen H, Zhang Y, Zhang W et al (2017) Low-dose CT via convolutional neural network. Biomed Opt Express 8:679–694CrossRefGoogle Scholar
  12. 12.
    Yang Q, Yan P, Zhang Y et al (2018) Low-dose CT image denoising using a generative adversarial network with Wasserstein distance and perceptual loss. IEEE Trans Med Imaging 37:1348–1357CrossRefGoogle Scholar
  13. 13.
    Fan Y, Zamyatin A, Nakanishi S (2012) Noise simulation for low-dose computed tomography. 2012 IEEE Nuclear Science Symposium and Medical Imaging Conference Record (NSS/MIC), Anaheim, CA, pp 3641–3643Google Scholar
  14. 14.
    Hausleiter J, Meyer T, Hermann F et al (2009) Estimated radiation dose associated with cardiac CT angiography. JAMA 301:500–507CrossRefGoogle Scholar
  15. 15.
    Lembcke A, Wiese TH, Schnorr J et al (2004) Image quality of noninvasive coronary angiography using multislice spiral computed tomography and electron-beam computed tomography: intraindividual comparison in an animal model. Invest Radiol 39:357–364CrossRefGoogle Scholar
  16. 16.
    Tatsugami F, Husmann L, Herzog BA et al (2009) Evaluation of a body mass index-adapted protocol for low-dose 64-MDCT coronary angiography with prospective ECG triggering. AJR Am J Roentgenol 192:635–638CrossRefGoogle Scholar
  17. 17.
    Tatsugami F, Higaki T, Sakane H et al (2017) Coronary artery stent evaluation with model-based iterative reconstruction at coronary CT angiography. Acad Radiol 24:975–981CrossRefGoogle Scholar
  18. 18.
    Nelson RC, Feuerlein S, Boll DT (2011) New iterative reconstruction techniques for cardiovascular computed tomography: how do they work, and what are the advantages and disadvantages? J Cardiovasc Comput Tomogr 5:286–292CrossRefGoogle Scholar
  19. 19.
    Geyer LL, Schoepf UJ, Meinel FG et al (2015) State of the art: iterative CT reconstruction techniques. Radiology 276:339–357CrossRefGoogle Scholar
  20. 20.
    Birnbaum BA, Hindman N, Lee J, Babb JS (2007) Multi-detector row CT attenuation measurements: assessment of intra- and interscanner variability with an anthropomorphic body CT phantom. Radiology 242:109–119CrossRefGoogle Scholar
  21. 21.
    Suzuki S, Machida H, Tanaka I, Ueno E (2013) Vascular diameter measurement in CT angiography: comparison of model-based iterative reconstruction and standard filtered back projection algorithms in vitro. AJR Am J Roentgenol 200:652–657CrossRefGoogle Scholar
  22. 22.
    Yokomachi K, Tatsugami F, Higaki T et al (2018) Neointimal formation after carotid artery stenting: phantom and clinical evaluation of model-based iterative reconstruction (MBIR). Eur Radiol.

Copyright information

© European Society of Radiology 2019

Authors and Affiliations

  1. 1.Department of Diagnostic RadiologyHiroshima UniversityHiroshimaJapan
  2. 2.Canon Medical Research USA, Inc.Vernon HillsUSA
  3. 3.Department of RadiologyHiroshima UniversityHiroshimaJapan
  4. 4.Department of Cardiovascular MedicineHiroshima UniversityHiroshimaJapan

Personalised recommendations