72-year-old with intermediate (50-70%) stenosis in distal right coronary artery, who underwent coronary CTA due to atypical chest pain.

72-year-old with intermediate (50-70%) stenosis in distal right coronary artery, who underwent coronary CTA due to atypical chest pain. (A) 3D volumetric rendering of coronary arteries, and (B) multiplanar reconstruction, show distal right coronary artery lesion (dashed box). (C) Image from onsite deep learning-based FFR-CT algorithm shows corresponding lesion (arrow). FFR-CT was 0.87. (D) Image from subsequent invasive coronary angiography shows corresponding lesion (arrow). Invasive FFR was 0.85, consistent with absence of hemodynamically significant stenosis. 


May 5, 2023 — According to an accepted manuscript published in ARRS’ own American Journal of Roentgenology (AJR), a high-speed onsite deep-learning based fractional flow reserve (FFR)-CT algorithm yielded excellent diagnostic performance for the presence of hemodynamically significant stenosis, with both high interobserver and intraobserver reproducibility. 

“A rapid and accurate onsite approach for determining FFR-CT should address challenges encountered in the clinical adoption of prior FFR-CT implementations,” wrote corresponding author Ronny Ralf Buechel, MD, from University Hospital Zurich in Switzerland. 


In this AJR accepted manuscript, 59 patients (46 men, 13 women; mean age 66.5 years) underwent coronary CTA (including calcium scoring) followed within 90 days by invasive angiography with invasive FFR and/or instantaneous wave-free ratio (iwFR) measurements from December 2014 to October 2021. Coronary artery lesions were considered to show hemodynamically significant stenosis in the presence of invasive FFR ≤0.80 and/or iwFR ≤0.89. A single cardiologist evaluated CTA images using an onsite deep-learning based semiautomated algorithm employing a 3D computational flow dynamics model to determine FFR-CT for coronary artery lesions detected by invasive angiography. Then, time for FFR-CT analysis was recorded. FFR-CT analysis was repeated by the same cardiologist in 26 randomly selected examinations, as well as by a different cardiologist in 45 randomly selected examinations.

Ultimately, Buechel et al.’s onsite deep-learning based FFR-CT algorithm evidenced AUC for hemodynamically significant stenosis—based on invasive angiography—of 0.975, sensitivity of 93.5%, and specificity of 97.7%. Among severely calcified lesions, their same algorithm had AUC of 0.991, sensitivity of 94.7%, and specificity of 95.0%. Moreover, the mean analysis time was 7 minutes and 54 seconds.   

“To our knowledge,” the authors of this AJR accepted manuscript added, “the currently reported mean processing timer represents the fastest reported time for onsite FFR-CT analysis.” 

For more information: www.arrs.org 


Find more ARRS23 conference coverage here 


Related Content

News | Computed Tomography (CT)

May 26, 2023 — GE HealthCare, a leading medical technology innovator, announced today its largest ever CT deal in the ...

Time May 26, 2023
arrow
News | Ultrasound Women's Health

May 25, 2023 — According to an accepted manuscript published in ARRS’ own American Journal of Roentgenology (AJR), deep ...

Time May 25, 2023
arrow
News | Pediatric Imaging

May 24, 2023 — A new advanced form of computed tomography (CT) imaging called photon-counting computed tomography (PCCT) ...

Time May 24, 2023
arrow
News | Radiology Imaging

May 19, 2023 — Asymptomatic adults with a high accumulation of fat in their muscles, known as myosteatosis, are at an ...

Time May 19, 2023
arrow
News | Computed Tomography (CT)

May 18, 2023 — Royal Philips, a global leader in health technology, announced the launch of the Philips CT 3500, a new ...

Time May 18, 2023
arrow
News | Computed Tomography (CT)

May 17, 2023 — According to an accepted manuscript published in ARRS’ own American Journal of Roentgenology (AJR), SARS ...

Time May 17, 2023
arrow
News | Breast Imaging

May 11, 2023 — According to an accepted manuscript published in ARRS’ own American Journal of Roentgenology (AJR) ...

Time May 11, 2023
arrow
News | Artificial Intelligence

May 8, 2023 — Artificial intelligence and machine learning (AI/ML) technologies are constantly finding new applications ...

Time May 08, 2023
arrow
News | Mammography

May 5, 2023 — The American College of Radiology (ACR), Breast Cancer Research Foundation (BCRF) and GE HealthCare ...

Time May 05, 2023
arrow
Feature | Contrast Media | By Christine Book

In the past year, the radiology community has been a first-hand, hands-on witness to myriad unexpected challenges and ...

Time May 03, 2023
arrow
Subscribe Now