The Official Journal of EuroPCR and the European Association of Percutaneous Coronary Interventions (EAPCI)

Automatic and multimodal analysis for coronary angiography: training and validation of a deep learning architecture

DOI: 10.4244/EIJ-D-20-00570

1. Beijing University of Posts and Telecommunications, No.10 Xitucheng Road, Haidian District Beijing, 100876, China
2. Fu Wai Hospital, National Center for Cardiovascular Diseases, Chinese Academy of Medical Sciences, A 167, Beilishi Road, Xicheng District, Beijing, 100037, China, China
3. Beijing Redcdn Technology Co., Ltd, No.73 Fucheng Road, Haidian District, Beijing 100039, China
4. Yale University School of Medicine, 333 Cedar St, New Haven, CT 06510, USA
Disclaimer:

As a public service to our readership, this article - peer reviewed by the Editors of EuroIntervention and external reviewers - has been published immediately upon acceptance as it was received in the last round of revision. The content of this article is the responsibility of the authors.

Please note that supplementary movies are not available online at this stage. Once a paper is published in its edited and formatted form, it will be accompanied online by any supplementary movies.

To read the full content of this article, please log in to download the PDF.

AIMS Most existing machine learning methods for coronary angiography analysis are limited to a single aspect. We aimed to achieve an automatic and multimodal analysis to recognize and quantify coronary angiography, integrating multiple aspects, including the identification of coronary artery segments and the recognition of lesion morphology.

METHODS AND RESULTS A dataset of 20,612 angiograms was retrospectively collected: among which 13,373 angiograms were labeled with coronary artery segments, and 7,239 were labeled with special lesion morphology. Trained and optimized by these labeled data, one network recognized 20 different segments of coronary arteries, while the other detected lesion morphology, including measures of lesion diameter stenosis as well as calcification, thrombosis, total occlusion, and dissection detections in an input angiogram. For segment prediction, the recognition accuracy was 98.4%, and the recognition sensitivity was 85.2%. For detecting lesion morphologies including stenotic lesion, total occlusion, calcification, thrombosis, and dissection, the F1-scores were 0.829, 0.810, 0.802, 0.823, and 0.854 respectively. Only 2 seconds were needed for the automatic recognition.

CONCLUSIONS Our deep learning architecture automatically provides a coronary diagnostic map by integrating multiple aspects, which helps cardiologists to flag and diagnose lesion severity and morphology during the intervention.

.

Sign in to read and download the full article

Forgot your password?
No account yet? Sign up for free!
Create my pcr account

Join us for free and access thousands of articles from EuroIntervention, as well as presentations, videos, cases from PCRonline.com

Read next article
Peri-procedural stent thrombosis following bifurcational PCI of lipid-rich plaque: serial optical coherence tomography insights