NCT03980470

Deep-Learning Image Reconstruction in CCTA

Completed NA Results posted Last updated 24 November 2021

What this trial tests

NA trial testing TrueFidelity in Coronary Artery Disease in 50 participants. Completed in 20 June 2019.

Timeline

8 May 2019

Primary endpoint
20 June 2019

20 June 2019

Quick facts

Lead sponsor	University of Zurich
Phase	NA
Status	Completed
Study type	INTERVENTIONAL
Allocation	na
Design	single group
Masking	none
Primary purpose	diagnostic
Enrollment	50
Start date	8 May 2019
Primary completion	20 June 2019
Estimated completion	20 June 2019
Sites	1 location across Switzerland

Drugs / interventions tested

• TrueFidelity

Conditions studied

• Coronary Artery Disease — all drugs for Coronary Artery Disease →

Sponsor

University of Zurich

Who can join

18 and older, any sex, with Coronary Artery Disease. Patients with the condition only — healthy volunteers not accepted.

Results — posted to ClinicalTrials.gov

Per-arm endpoint measurements with 95% confidence intervals where reported. Source: trial results section.

Subjective Image Quality Primary · Day 1

Subjective image quality as measured by Likert scale from 1 (non-evaluable) to 5 (excellent)

Low-Dose

Group	Value	95% CI
Normal-dose Versus Low-dose	5	± 0

Normal-Dose

Group	Value	95% CI
Normal-dose Versus Low-dose	5	± 0

Signal Intensity Secondary · Day 1

Signal intensity as average hounsfield units within a region of interest in the aortic root, change from experimental interventional to the control intervention

Low-Dose

Group	Value	95% CI
Normal-dose Versus Low-dose	462	± 76

Normal Dose

Group	Value	95% CI
Normal-dose Versus Low-dose	443	± 85

Image Noise Secondary · Day 1

Image noise as standard deviation of hounsfield units within a region of interest in the aortic root, change from experimental interventional to the control intervention

Low-Dose

Group	Value	95% CI
Low-dose	27	± 4

Normal-Dose

Group	Value	95% CI
Low-dose	28	± 6

Signal-to-noise Ratio Secondary · Day 1

Signal-to-noise ratio

Low-Dose

Group	Value	95% CI
Low-dose	17	± 3

Normal-Dose

Group	Value	95% CI
Low-dose	16	± 2

Dose-length Products Secondary · Day 1

Comparison of dose-length products

Low-Dose

Group	Value	95% CI
Normal-Dose Versus Low-dose	31	25 – 34

Normal-Dose

Group	Value	95% CI
Normal-Dose Versus Low-dose	52	42 – 58

Plaque Volumes Secondary · Day 1

Quantitative analysis of coronary artery plaque volumes

Low-Dose

Group	Value	95% CI
Normal-Dose Versus Low-dose	12.42	± 13.14

Normal-Dose

Group	Value	95% CI
Normal-Dose Versus Low-dose	13.84	± 14.41

Sponsor's own description

Cardiac CT allows the assessment of the heart and of the coronary arteries by use of ionising radiation. Although radiation exposure was significantly reduced in recent years, further decrease in radiation exposure is limited by increased image noise and deterioration in image quality. Recent evidence suggests that further technological refinements with artificial intelligence allows improved post-processing of images with reduction of image noise.

The present study aims at assessing the potential of a deep-learning image reconstruction algorithm in a clinical setting. Specifically, after a standard clinical scan, patients are scanned with lower radiation exposure and reconstructed with the DLIR algorithm. This interventional scan is then compared to the standard clinical scan.

Publications & conference data

1 peer-reviewed publication reference this trial (live from Europe PMC):

1. Digital health technologies and artificial intelligence in cardiovascular clinical trials: A landscape of the European space.
   Lampreia F, Madeira C, Dores H. · · 2024 · cited 4× · PMID 39291150 · DOI 10.1177/20552076241277703