Faster cardiac MRI using deep-learning image reconstruction to measure left ventricular ejection fraction

Evaluation of Left Ventricular Ejection Fraction Using an Accelerated Cardiac Cine-MRI Sequence With Deep Learning-based Image Reconstructions Compared to the Reference Cine-MRI Sequence in the Assessment or Follow-up of Left Ventricular Hypertrophy

NA · Centre Hospitalier Universitaire, Amiens · NCT07061821

This will test whether a faster cardiac MRI scan using deep-learning reconstruction can accurately measure ejection fraction in adults referred for left ventricular hypertrophy.

Quick facts

PhaseNA
Study typeInterventional
Enrollment61 (estimated)
Ages18 Years and up
SexAll
SponsorCentre Hospitalier Universitaire, Amiens (other)
Locations1 site (Amiens)
Trial IDNCT07061821 on ClinicalTrials.gov

What this trial studies

Cardiac MRI is the reference standard for measuring left ventricular ejection fraction, but conventional cine sequences require multiple breath-holds that can be difficult for elderly or dyspneic patients. This project uses an accelerated cine-CMR sequence combined with deep learning-based image reconstruction to shorten acquisition time and reduce breath-hold requirements. Adults referred for CMR for left ventricular hypertrophy will undergo the accelerated imaging and results will be compared with standard cine techniques for LVEF, ventricular volumes, and image quality. The aim is to determine whether accelerated, DL-reconstructed images maintain diagnostic accuracy while improving patient comfort and scan efficiency.

Who should consider this trial

Good fit: Ideal participants are adults (18+) referred for cardiac MRI to evaluate or follow left ventricular hypertrophy who can give informed consent and meet MRI safety requirements.

Not a fit: Patients with arrhythmias, severe obesity preventing scanner entry, inability to hold breath for at least 10 seconds, claustrophobia, pregnancy, gadolinium allergy, or other MRI contraindications are unlikely to benefit or may be excluded.

Why it matters

Potential benefit: If successful, patients could have shorter, more comfortable MRI exams that still provide accurate ejection fraction measurements, which would particularly help elderly or breathless patients.

How similar studies have performed: Prior studies of accelerated cine MRI with deep-learning reconstructions have shown promising results for preserving image quality and LVEF accuracy, though broader clinical validation is still ongoing.

Eligibility criteria

Show full inclusion / exclusion criteria
Inclusion Criteria:

* Patient referred for cardiac MRI as part of the assessment or follow-up of left ventricular hypertrophy
* Age ≥ 18 years old
* Ability of the subject to understand and express his consent
* Affiliation to the social security scheme

Exclusion Criteria:

* Severe obesity (\>140 kg) preventing the patient from entering the scanner bore, which has a diameter of less than 70 cm
* Age ≥ 18 years old
* Person under guardianship or curators, or deprived of liberty
* Pregnant or breastfeeding woman
* Known allergy to gadolinium chelates
* Claustrophobia
* Any contraindication to MRI
* Arrhythmia
* Inability to hold breath for more than 10 seconds

Where this trial is running

Amiens

Study contacts

How to participate

  1. Review the eligibility criteria above with your treating physician.
  2. Visit the official trial page on ClinicalTrials.gov for the most current contact information and recruitment status.
  3. Contact the listed study coordinator or principal investigator to request pre-screening. Pre-screening is free and never obligates you to enroll.

View on ClinicalTrials.gov →

Conditions: Left Ventricular Ejection Fraction, Cardiac Magnetic Resonance Imaging, Deep Learning, Image Reconstruction, Left Ventricular Hypertrophy

Last reviewed 2026-05-15 by the Find a Trial editorial team. Information on this page is for educational purposes and is not medical advice. Always consult qualified healthcare professionals about clinical trial participation.