Non-Invasive Coronary Artery Functional Assessment

Request Demo
*CE Marked, NMPA Approved. Not for sale in the United States.

Enabling Better Diagnosis & Treatment of Patients with Coronary Artery Disease

DEEPVESSEL FFR uses deep learning technology to perform a non-invasive physiological functional assessment of the coronary arteries using coronary CTA (CCTA) scans. Using DEEPVESSEL FFR, clinicians can automatically calculate the FFR value at any location on the coronary artery tree. This enables healthcare professionals to diagnose patients with suspected coronary artery disease more accurately while reducing unnecessary invasive testing to lower costs and avoid potential complications.


Existing approaches have mostly relied on traditional flow field simulation-based methods. DEEPVESSEL FFR applies Feature Flow, a proprietary deep learning technology built on the latest advances from the computer vision industry as optimized by our scientific team for medical image analysis. This new approach gives a strong performance advantage with fast processing speed and accurate non-invasive FFR analysis.

In addition to increased processing speed and accuracy, DEEPVESSEL FFR allows clinicians to calculate the FFR value for any location within the coronary artery tree. DEEPVESSEL FFR provides accurate and timely quantitative test results required by clinical practices. This non-invasive analysis of the CTA image is a cost-effective way to determine the most appropriate treatment plan. Some patients may avoid unnecessary catheterization lab procedures. Because non-invasive FFR has clear cost-saving implications, the procedure is covered by government and private insurance in the USA.

Indications for Use

CTA scans are increasingly used in the cardiology diagnostic process as a first line tool. Once the image has been acquired, it can be processed in a manner of minutes through DEEPVESSEL FFR to deliver complete non-invasive assessments of coronary artery physiologic function. This makes it attractive for general use, such as during physical examinations, the screening of high-risk populations, the accurate auxiliary diagnosis of suspected patients, and the treatment planning of confirmed patients.

Product Features


Non-invasive functional assessment from CTA scan


Enables accurate and fast FFR analysis


Provides both anatomical and functional information


Novel coronary CT FFR technique driven by AI


Reduces medical cost


CE marked



Input is DICOM files produced from CTA exam.


Results can be delivered in minutes, not hours.


Achieves 89% diagnostic accuracy using invasive FFR as the groundtruth.


Reduces costs from invasive procedures and unnecessary therapies.


FFR values can be observed at any location in the coronary tree.


Results can be viewed on smart phones, PCs, and tablets.

Clinical Performance Assessment

DEEPVESSEL FFR conducted clinical trials of prospective [1] and retrospective multicenter, self-controlled studies in 2017 and 2019, respectively. In these trials, the FFR measured invasively by using a pressure wire was used as the gold standard to evaluate the sensitivity and specificity of DEEPVESSEL FFR in evaluating functional myocardial ischemia in patients with stable coronary heart disease (SCAD).
Prospective Retrospective
Multicenter, self-controlled Multicenter, self-controlled
Accuracy 89.2% 90.8%
Sensitivity 94.2% 94.7%
Specificity 84.3% 88.6%
Positive Prediction Value 86.9% 83.0%
Negative Prediction Value 92.2% 96.7%

[1] Wang ZQ, Zhou YJ, Zhao YX, et al. Diagnostic accuracy of a deep learning approach to calculate FFR from coronary CT angiography. J Geriatr Cardiol 2019;16:42-48.


In 2017, DEEPVESSEL FFR has been tested via a multi-center prospective clinical trial which recruited patients from:

  • Beijing Anzhen Hospital affiliated to Capital Medical University
  • Air Force General Hospital PLA
  • Cangzhou Central Hospital

In 2019, DEEPVESSEL FFR has been tested via a multi-center retrospective clinical trial which recruited patients from:

  • Beijing Anzhen Hospital affiliated to Capital Medical University
  • Fuwai Hospital, Chinese Academy of Medical Sciences
  • Beijing Friendship Hospital
  • The First Affiliated Hospital of Wenzhou Medical University
  • The Second Affiliated Hospital of Zhejiang University Medical College
  • Wuhan Asia Heart Hospital

The prospective and retrospective multi-center clinical trials and performance assessments are in support of the regulatory submissions for approval by the National Medical Products Administration (NMPA) in China.

How it Works

Upload DICOM files to the platform


Deep learning algorithms automatically perform a functional assessment of the coronary arteries


Doctors receive an interactive analysis report

Collaborate with us

We are recruiting collaboration partners in the US to help bring DEEPVESSEL FFR to clinical use. If you are interested in learning more about potential collaboration opportunities, please contact us.