Skip to main content
SpringerLink
Log in

Automatic coronary artery segmentation and diagnosis of stenosis by deep learning based on computed tomographic coronary angiography

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

Abstract

Objectives

Coronary computed tomography angiography (CCTA) has rapidly developed in the coronary artery disease (CAD) field. However, manual coronary artery tree segmentation and reconstruction are time-consuming and tedious. Deep learning algorithms have been successfully developed for medical image analysis to process extensive data. Thus, we aimed to develop a deep learning tool for automatic coronary artery reconstruction and an automated CAD diagnosis model based on a large, single-centre retrospective CCTA cohort.

Methods

Automatic CAD diagnosis consists of two subtasks. One is a segmentation task, which aims to extract the region of interest (ROI) from original images with U-Net. The second task is an identification task, which we implemented using 3DNet. The coronary artery tree images and clinical parameters were input into 3DNet, and the CAD diagnosis result was output.

Results

We built a coronary artery segmentation model based on CCTA images with the corresponding labelling. The segmentation model had a mean Dice value of 0.771 ± 0.021. Based on this model, we built an automated diagnosis model (classification model) for CAD. The average accuracy and area under the receiver operating characteristic curve (AUC) were 0.750 ± 0.056 and 0.737, respectively.

Conclusion

Herein, using a deep learning algorithm, we realized the rapid classification and diagnosis of CAD from CCTA images in two steps. Our deep learning model can automatically segment the coronary artery quickly and accurately and can deliver a diagnosis of ≥ 50% coronary artery stenosis. Artificial intelligence methods such as deep learning have the potential to elevate the efficiency in CCTA image analysis considerably.

Key Points

• The deep learning model rapidly achieved a high Dice value (0.771 ± 0.0210) in the autosegmentation of coronary arteries using CCTA images.

• Based on the segmentation model, we built a CAD autoclassifier with the 3DNet algorithm, which achieved a good diagnostic performance (AUC) of 0.737.

• The deep neural network could be used in the image postprocessing of coronary computed tomography angiography to achieve a quick and accurate diagnosis of CAD.

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

Similar content being viewed by others

Abbreviations

AUC:

Area under the curve

BP:

Backpropagation

CAD:

Coronary artery disease

CAD-RADS:

Coronary Artery Disease Reporting and Data System

CCTA:

Coronary computed tomography angiography

DSC:

Dice similarity coefficient

PPV:

Positive predictive value

ROI:

Region of interest

SCCT:

Society of Cardiovascular Computed Tomography

SD:

Standard deviation

TPVF:

True positive volume fraction

References

  1. Joseph P, Leong D, McKee M et al (2017) Reducing the global burden of cardiovascular disease, part 1: the epidemiology and risk factors. Circ Res 121:677–694

    Article  CAS  Google Scholar 

  2. Campeau L (1989) Percutaneous radial artery approach for coronary angiography. Catheter Cardiovasc Diagn 16:3–7

    Article  CAS  Google Scholar 

  3. Budoff MJ, Dowe D, Jollis JG et al (2008) Diagnostic performance of 64-multidetector row coronary computed tomographic angiography for evaluation of coronary artery stenosis in individuals without known coronary artery disease: results from the prospective multicenter ACCURACY (Assessment by Coronary Computed Tomographic Angiography of Individuals Undergoing Invasive Coronary Angiography) trial. J Am Coll Cardiol 52:1724–1732

    Article  Google Scholar 

  4. Miller JM, Rochitte CE, Dewey M et al (2008) Diagnostic performance of coronary angiography by 64-row CT. N Engl J Med 359:2324–2336

    Article  CAS  Google Scholar 

  5. Knuuti J, Wijns W, Saraste A et al (2020) 2019 ESC Guidelines for the diagnosis and management of chronic coronary syndromes. Eur Heart J 41:407–477

    Article  Google Scholar 

  6. LeCun Y, Bengio Y, Hinton G (2015) Deep learning. Nature 521:436–444

    Article  CAS  Google Scholar 

  7. Goodfellow I, Bengio Y, Courville A (2016) Deep learning. MIT Press

    Google Scholar 

  8. Ring F (2018) Deep learning for coronary artery segmentation in cta images,

  9. Chen M, Wang X, Hao G et al (2020) Diagnostic performance of deep learning-based vascular extraction and stenosis detection technique for coronary artery disease. Br J Radiol 93:20191028

    Article  Google Scholar 

  10. Huang W, Huang L, Lin Z et al (2018) Coronary artery segmentation by deep learning neural networks on computed tomographic coronary angiographic images. 2018 40th Annual international conference of the IEEE engineering in medicine and biology society (EMBC). IEEE, pp 608-611

  11. Ronneberger O, Fischer P, Brox T (2015) U-net: convolutional networks for biomedical image segmentationInternational. Conference on Medical image computing and computer-assisted intervention. Springer, pp 234-241

  12. Braspenning PJ, Thuijsman F, Weijters AJMM (1995) Artificial neural networks: an introduction to ANN theory and practice. Springer Science & Business Media

    Book  Google Scholar 

  13. Imambi S, Prakash KB, Kanagachidambaresan G (2021) PyTorchProgramming with TensorFlow. Springer, pp 87–104

    Book  Google Scholar 

  14. Taha AA, Hanbury A (2015) Metrics for evaluating 3D medical image segmentation: analysis, selection, and tool. BMC Med Imaging 15:1–28

    Article  Google Scholar 

  15. Yeghiazaryan V, Voiculescu ID (2018) Family of boundary overlap metrics for the evaluation of medical image segmentation. J Med Imaging 5:015006

    Article  Google Scholar 

  16. Ling CX, Huang J, Zhang H (2003) AUC: a statistically consistent and more discriminating measure than accuracy. Ijcai, pp 519–524

    Google Scholar 

  17. Tatsugami F, Higaki T, Nakamura Y et al (2019) Deep learning–based image restoration algorithm for coronary CT angiography. Eur Radiol 29:5322–5329

    Article  Google Scholar 

  18. Oktay O, Schlemper J, Folgoc LL et al (2018) Attention u-net: learning where to look for the pancreas. arXiv preprint arXiv:180403999

    Google Scholar 

  19. Raff GL, Abidov A, Achenbach S et al (2009) SCCT guidelines for the interpretation and reporting of coronary computed tomographic angiography. J Cardiovasc Comput Tomogr 3:122–136

    Article  Google Scholar 

  20. Denzinger F, Wels M, Ravikumar N et al (2019) Coronary artery plaque characterization from CCTA scans using deep learning and radiomics. International Conference on Medical Image Computing and Computer-Assisted Intervention. Springer, pp 593-601

  21. Moon JH, Cha WC, Chung MJ, Lee K-S, Cho BH, Choi JH (2021) Automatic stenosis recognition from coronary angiography using convolutional neural networks. Comput Methods Prog Biomed 198:105819

    Article  Google Scholar 

  22. Isensee F, Petersen J, Klein A et al (2018) nnu-net: self-adapting framework for u-net-based medical image segmentation. arXiv preprint arXiv:180910486

    Google Scholar 

  23. Wohlkinger W, Aldoma A, Rusu RB, Vincze M (2012) 3dnet: large-scale object class recognition from cad models. 2012 IEEE international conference on robotics and automation. IEEE, pp 5384-5391

  24. Çiçek Ö, Abdulkadir A, Lienkamp SS, Brox T, Ronneberger O (2016) 3D U-Net: learning dense volumetric segmentation from sparse annotationInternational conference on medical image computing and computer-assisted intervention. Springer, pp 424–432

    Google Scholar 

  25. Baskaran L, Maliakal G, Al’Aref SJ et al (2020) Identification and quantification of cardiovascular structures from CCTA: an end-to-end, rapid, pixel-wise, deep-learning method. Cardiovasc Imaging 13:1163–1171

    Google Scholar 

  26. Kumamaru KK, Fujimoto S, Otsuka Y et al (2020) Diagnostic accuracy of 3D deep-learning-based fully automated estimation of patient-level minimum fractional flow reserve from coronary computed tomography angiography. Eur Heart J-Cardiovasc Imaging 21:437–445

    PubMed  Google Scholar 

  27. Lee MCH, Petersen K, Pawlowski N, Glocker B, Schaap M (2019) TeTrIS: template transformer networks for image segmentation with shape priors. IEEE Trans Med Imaging 38:2596–2606

    Article  Google Scholar 

  28. Choi AD, Marques H, Kumar V et al (2021) CT evaluation by artificial intelligence for atherosclerosis, stenosis and vascular morphology (CLARIFY): a multi-center, international study. J Cardiovasc Comput Tomogr 15:470–476

    Article  Google Scholar 

Download references

Funding

Funding of this work was supported by the National Major Science and Technology Projects (grant number 2018AAA0100201) to Z.Y.; the National Natural Science Foundation of China (grant 81970325 to M.C.; grant number 61906127 to J.W.); the 1.3.5 project for disciplines of excellence, West China Hospital, Sichuan University to M.C.; the Science and Technology Achievement Transformation Fund of West China Hospital of Sichuan University (CGZH19009) to M.C; and Open Fund Research from State Key Laboratory of Hydraulics and Mountain River Engineering (SKHL1920 to Xiong. T.Y.)

Author information

Author notes

  1. Yiming Li and Yu Wu contributed equally to this work.

Authors and Affiliations

  1. Department of Cardiology, West China Hospital, Sichuan University, No. 37 Guoxue Street, Chengdu, 610041, People’s Republic of China

    Yiming Li, Jingjing He, Yong Peng, Yuheng Jia, Tianyuan Xiong, Kaiyu Jia & Mao Chen

  2. Machine Intelligence Laboratory, College of Computer Science, Sichuan University, No. 24 South Section 1, Yihuan Road, Chengdu, 610065, People’s Republic of China

    Yu Wu, Weili Jiang, Jianyong Wang & Zhang Yi

Authors
  1. Yiming Li
    View author publications

    You can also search for this author in PubMed Google Scholar

  2. Yu Wu
    View author publications

    You can also search for this author in PubMed Google Scholar

  3. Jingjing He
    View author publications

    You can also search for this author in PubMed Google Scholar

  4. Weili Jiang
    View author publications

    You can also search for this author in PubMed Google Scholar

  5. Jianyong Wang
    View author publications

    You can also search for this author in PubMed Google Scholar

  6. Yong Peng
    View author publications

    You can also search for this author in PubMed Google Scholar

  7. Yuheng Jia
    View author publications

    You can also search for this author in PubMed Google Scholar

  8. Tianyuan Xiong
    View author publications

    You can also search for this author in PubMed Google Scholar

  9. Kaiyu Jia
    View author publications

    You can also search for this author in PubMed Google Scholar

  10. Zhang Yi
    View author publications

    You can also search for this author in PubMed Google Scholar

  11. Mao Chen
    View author publications

    You can also search for this author in PubMed Google Scholar

Corresponding authors

Correspondence to Zhang Yi or Mao Chen.

Ethics declarations

Guarantor

The scientific guarantors of this publication are Prof. Zhang Yi and Prof. Mao Chen.

Conflict of interest

The authors declare no competing interests.

Statistics and biometry

No complex statistical methods were necessary for this paper.

Informed consent

Written informed consent was obtained from all subjects (patients) in this study.

Ethical approval

Institutional Review Board approval was obtained.

Methodology

• retrospective

• diagnostic 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

ESM 1

(DOCX 24 kb)

Rights and permissions

Reprints and permissions

About this article

Check for updates. Verify currency and authenticity via CrossMark

Cite this article

Li, Y., Wu, Y., He, J. et al. Automatic coronary artery segmentation and diagnosis of stenosis by deep learning based on computed tomographic coronary angiography. Eur Radiol 32, 6037–6045 (2022). https://doi.org/10.1007/s00330-022-08761-z

Download citation

  • Received:

  • Revised:

  • Accepted:

  • Published:

  • Issue Date:

  • DOI: https://doi.org/10.1007/s00330-022-08761-z

Keywords

Search

Navigation