Skip to main page content
U.S. flag

An official website of the United States government

Dot gov

The .gov means it’s official.
Federal government websites often end in .gov or .mil. Before sharing sensitive information, make sure you’re on a federal government site.

Https

The site is secure.
The https:// ensures that you are connecting to the official website and that any information you provide is encrypted and transmitted securely.

Access keys NCBI Homepage MyNCBI Homepage Main Content Main Navigation
. 2019 Jan;16(1):42-48.
doi: 10.11909/j.issn.1671-5411.2019.01.010.

Diagnostic accuracy of a deep learning approach to calculate FFR from coronary CT angiography

Zhi-Qiang Wang  1 , Yu-Jie Zhou  1 , Ying-Xin Zhao  1 , Dong-Mei Shi  1 , Yu-Yang Liu  1 , Wei Liu  1 , Xiao-Li Liu  1 , Yue-Ping Li  1
Affiliations

Diagnostic accuracy of a deep learning approach to calculate FFR from coronary CT angiography

Zhi-Qiang Wang et al. J Geriatr Cardiol. 2019 Jan.

Abstract

Background: The computational fluid dynamics (CFD) approach has been frequently applied to compute the fractional flow reserve (FFR) using computed tomography angiography (CTA). This technique is efficient. We developed the DEEPVESSEL-FFR platform using the emerging deep learning technique to calculate the FFR value out of CTA images in five minutes. This study is to evaluate the DEEPVESSEL-FFR platform using the emerging deep learning technique to calculate the FFR value from CTA images as an efficient method.

Methods: A single-center, prospective study was conducted and 63 patients were enrolled for the evaluation of the diagnostic performance of DEEPVESSEL-FFR. Automatic quantification method for the three-dimensional coronary arterial geometry and the deep learning based prediction of FFR were developed to assess the ischemic risk of the stenotic coronary arteries. Diagnostic performance of the DEEPVESSEL-FFR was assessed by using wire-based FFR as reference standard. The primary evaluation factor was defined by using the area under receiver-operation characteristics curve (AUC) analysis.

Results: For per-patient level, taking the cut-off value ≤ 0.8 referring to the FFR measurement, DEEPVESSEL-FFR presented higher diagnostic performance in determining ischemia-related lesions with area under the curve of 0.928 compare to CTA stenotic severity 0.664. DEEPVESSEL-FFR correlated with FFR (R = 0.686, P < 0.001), with a mean difference of -0.006 ± 0.0091 (P = 0.619). The secondary evaluation factors, indicating per vessel accuracy, sensitivity, specificity, positive predictive value, and negative predictive value were 87.3%, 97.14%, 75%, 82.93%, and 95.45%, respectively.

Conclusion: DEEPVESSEL-FFR is a novel method that allows efficient assessment of the functional significance of coronary stenosis.

Keywords: Computed tomography angiography; Coronary artery; Deep learning; Fractional flow reserve.

PubMed Disclaimer

Figures

Figure 1.
Figure 1.. The process of DEEPVESSEL-FFR.
MLNN: multilevel neural network; RNN: multilevel neural network.
Figure 2.
Figure 2.. Representative examples of subjects from the study.
(A): Multiplanar reformat of coronary computed tomography (CT) angiogram; (B): the left anterior descending artery (blue arrow) and DEEPVESSEL-FFR 0.81; (C): invasive coronary angiogram; and (D): invasive FFR measurement, a measured FFR value of 0.81. FFR: fractional flow reserve.
Figure 3.
Figure 3.. Correlation (A & C) and agreement (B & D) analysis on a per-patient level and per-vessel level.
DVFFR: DEEPVESSEL fractional flow reserve.
Figure 4.
Figure 4.. AUC of DEEPVESSEL-FFR vs. coronary CTA for demonstration of ischemia (FFR 0.80) on a per-patient and per-vessel basis.
AUC: area under receiver-operation characteristics curve; CTA: computed tomography angiography; FFR: fractional flow reserve.
See this image and copyright information in PMC

Similar articles

See all similar articles

Cited by

See all "Cited by" articles

References

    1. Gaur S., Øvrehus KA, Dey D, et al. Coronary plaque quantification and fractional flow reserve by coronary computed tomography angiography identify ischaemia-causing lesions. Eur Heart J. 2016;37:1220–1227. - PMC - PubMed
    1. Pijls NHJ, Fearon WF, Tonino PA, et al. Fractional flow reserve versus angiography for guiding percutaneous coronary intervention in patients with multivessel coronary artery disease: 2-year follow-up of the FAME (Fractional Flow Reserve Versus Angiography for Multivessel Evaluation) Study. J Am Coll Cardiol. 2010;56:177–184. - PubMed
    1. Vanhoenacke PK, Heijenbrok-Kal MH, Van Heste R, et al. Diagnostic performance of multidetector CT angiography for assessment of coronary artery disease: meta-analysis. Radiology. 2007;244:419–428. - PubMed
    1. George RT, Mehra VC, Chen MY, et al. Myocardial CT perfusion imaging and SPECT for the diagnosis of coronary artery disease: a head-to-head comparison from the CORE320 multicenter diagnostic performance study. Radiology. 2014;272:407–416. - PMC - PubMed
    1. Nørgaard B.L., Leipsic J, Gaur S, et al. Diagnostic performance of noninvasive fractional flow reserve derived from coronary computed tomography angiography in suspected coronary artery disease. J Am Coll Cardiol. 2014;63:1145–1155. - PubMed

LinkOut - more resources