Using 4D Flow MRI to characterize left ventricular failure
Phenotyping Left Ventricle Failure With Hemodynamic Biomarkers From 4D Flow Magnetic Resonance Imaging
This project will test whether automated 4D Flow MRI analysis can measure left ventricular dysfunction in adults with severe aortic stenosis who are scheduled for TAVR.
Quick facts
| Phase | Not applicable |
|---|---|
| Study type | Interventional |
| Enrollment | 190 (estimated) |
| Ages | 18 Years and up |
| Sex | All |
| Sponsor | IRCCS Policlinico S. Donato Academic / other |
| Locations | 2 sites (San Donato Milanese and 1 other locations) |
| Trial ID | NCT07455292 on ClinicalTrials.gov |
What this trial studies
The study uses a retrospective arm to build an anonymized database of short-axis bSSFP cine images with manually corrected LV endocardial contours and a prospective arm to acquire non-contrast 4D Flow MRI before TAVR. A convolutional neural network (e.g., ResNet) will be trained on the retrospective dataset (approximately 75% training, 25% test) to automate LV endocardial segmentation throughout the cardiac cycle. The prospective cohort will undergo 4D Flow MRI and routine invasive monitoring during TAVR to enable non-invasive pressure–volume loop reconstruction and calculation of simplified hemodynamic force descriptors. Automated MRI outputs will be benchmarked against manual segmentations and invasive signals to validate accuracy and support translational implementation.
Who should consider this trial
Good fit: Adults over 18 with guideline-defined severe aortic stenosis who are planned for TAVR, can undergo MRI, and provide written informed consent.
Not a fit: Patients with MRI contraindications (for example ferromagnetic implants), poor MRI image quality, claustrophobia, or those not undergoing TAVR are unlikely to benefit from this protocol.
Why it matters
Potential benefit: If successful, this approach could deliver faster, standardized MRI measures of heart pumping function to better inform and personalize care around TAVR.
How similar studies have performed: Deep learning has previously shown reliable cardiac MRI segmentation and 4D Flow MRI has been used to characterize intracardiac hemodynamics, but combining automated CNN segmentation with MRI-derived pressure–volume reconstruction in TAVR patients is relatively novel.
Eligibility criteria
Show full inclusion / exclusion criteria
Inclusion Criteria: * Adult patients (age \> 18 years old); * Diagnosis of severe AS defined according to ESC guidelines with indication to TAVR; * Severe aortic stenosis both in normal/high flow status and in low flow status; * Signed informed written consent. Exclusion Criteria: * Contraindication to cardiac MRI due to previous implant with ferromagnetic components; * Poor MRI quality impairing image post-processing; * Claustrophobia; * Unwilling to sign the informed consent.
Where this trial is running
San Donato Milanese and 1 other locations
- IRCCS Policlinico San Donato — San Donato Milanese, Italy (Recruiting)
- IRCCS Policlinico San Donato — San Donato Milanese, Italy (Recruiting)
Study contacts
- Principal investigator: Giandomenico Disabato, MD — IRCCS Policlinico S. Donato
- Study coordinator: Giandomenico Disabato, MD
- Email: giandomenico.disabato@grupposandonato.it
- Phone: +390252774804
How to participate
- Review the eligibility criteria above with your treating physician.
- Visit the official trial page on ClinicalTrials.gov for the most current contact information and recruitment status.
- Contact the listed study coordinator or principal investigator to request pre-screening. Pre-screening is free and never obligates you to enroll.