Using AI to measure aortic size from CT scans
AI-CARE: Artificial Intelligence for Cardiovascular Analysis and Risk Evaluation - Clinical Evaluation of Aorta Automated Imaging Measurement (Aorta AIM)
This project will test whether an AI tool called Aorta AIM can automatically measure the aorta on CT scans for adults who have or are being checked for aortic aneurysms.
Quick facts
| Study type | Observational |
|---|---|
| Enrollment | 250 (estimated) |
| Ages | 22 Years and up |
| Sex | All |
| Sponsor | Aiatella Oy Industry-sponsored |
| Locations | 3 sites (Chapel Hill, North Carolina and 2 other locations) |
| Trial ID | NCT07438327 on ClinicalTrials.gov |
What this trial studies
This observational study compares automated aortic diameter measurements from an AI software (Aorta AIM) with manual measurements made by experienced radiologists or cardiologists using existing CT scans. Researchers will use retrospective CT images collected between January 1, 2016 and August 31, 2025 from multiple hospitals in the United States and Brazil, including whole, thoracic, or abdominal aorta exams with slice thickness ≤ 3 mm. No new scans or procedures are required; the AI and expert measurements will be compared region-by-region, excluding only areas with truncation or poor image quality that prevent reliable measurement. Approximately 250 adult participants (age ≥ 22 at imaging) will be included to test the AI’s consistency and agreement with human readers.
Who should consider this trial
Good fit: Ideal candidates are adults (≥22 years at imaging) who have a CT scan capturing the whole, thoracic, or abdominal aorta (slice thickness ≤ 3 mm) performed between 2016 and August 2025, including exams with or without contrast.
Not a fit: Patients whose CT images have severe motion artifacts, congenital aortic anomalies, recent prior aortic surgery, metal implants very close to the aorta, or imaging truncation that prevents reliable regional measurements may not benefit from the AI analysis.
Why it matters
Potential benefit: If successful, the AI could provide faster, more consistent aortic measurements that help clinicians monitor aneurysm growth and make treatment decisions sooner.
How similar studies have performed: Other research using AI for vascular segmentation and diameter measurement has shown promising accuracy in controlled settings, though such tools are not yet universally adopted in routine clinical practice.
Eligibility criteria
Show full inclusion / exclusion criteria
* Adults ≥22 years at time of imaging * Studies performed 1 Jan 2016 - 31 August 2025 * CT imaging of the whole, thoracic, or abdominal aorta, with or without contrast enhancement, acquired with any gating protocol (including non-gated) * Slice thickness ≤ 3mm * CT imaging in which truncation creates discontinuity within a targeted aortic region, preventing reliable diameter measurement (e.g., cardiac-focused CT acquisitions where an incomplete or absent aortic arch creates discontinuity between the aortic root and the descending thoracic aorta) o Partial aortic coverage is not grounds for exclusion. Where truncation affects individual regions, only those specific regions will be excluded from analysis; remaining fully captured regions will be retained for measurement. * Metal implants \<5cm from aorta (e.g. thoracic stent) * Prior aortic surgery * Severe motion artifacts (e.g. \>3mm vessel blurring) * Congenital aortic anomalies (e.g. coarctation, vascular rings) * Post-traumatic aortic repairs * The patient opted out of having their data used for medical research before the date of cross-referencing by the site team
Where this trial is running
Chapel Hill, North Carolina and 2 other locations
- University of North Carolina at Chapel Hill — Chapel Hill, North Carolina, United States (Not_yet_recruiting)
- Innovation Health Services — Norfolk, Virginia, United States (Recruiting)
- Hospital Israelita Albert Einstein — São Paulo, São Paulo, Brazil (Not_yet_recruiting)
Study contacts
- Principal investigator: Scott Flamm — SimonMed Imaging
- Study coordinator: Jack Parker
- Email: jack@aiatella.com
- Phone: 4578313729
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.