AI-based monitoring to detect and correct radiopharmaceutical extravasation during PET/CT and nuclear medicine therapy
New AI-based Technologies for Even Safer and More Precise Nuclear Medicine
This project tests an AI system combined with a wearable radiation detector to spot and predict radiopharmaceutical extravasation and estimate SUV correction for patients having PET/CT scans or radiopharmaceutical therapy.
Quick facts
| Study type | Observational |
|---|---|
| Enrollment | 1500 (estimated) |
| Ages | 18 Years to 90 Years |
| Sex | All |
| Sponsor | Azienda USL Reggio Emilia - IRCCS Government |
| Drugs / interventions | radiation |
| Locations | 1 site (Reggio Emilia) |
| Trial ID | NCT07174089 on ClinicalTrials.gov |
What this trial studies
This observational, non-profit project records dose-rate curves with a CE-marked portable spectrometric detector during radiopharmaceutical injections to identify normal, abnormal, and extravasation events. New semi-quantitative dosimetric metrics will be derived from those curves and combined with patient and injection data to train machine learning models for real-time classification and estimation of SUV correction factors. Monte Carlo simulations using anthropomorphic phantoms and patient geometries will be performed to estimate absorbed dose distributions in extravascular tissues. The approach focuses on improving detection and quantification of injection mishaps without altering standard clinical care.
Who should consider this trial
Good fit: Ideal participants are patients who can consent and are scheduled for PET/CT scans or therapeutic procedures using alpha- or beta-emitting radiopharmaceuticals.
Not a fit: Patients who cannot consent, are not receiving radiopharmaceuticals, or whose injections do not extravasate are unlikely to receive direct benefit from participation.
Why it matters
Potential benefit: If successful, this could enable earlier detection of injection problems, reduce local radiation injury risk, and provide more accurate SUV values to improve diagnostic and treatment decisions.
How similar studies have performed: Portable dose-rate detectors have been validated in prior ethics-approved work and prior literature documents SUV changes from extravasation, but ML-based real-time classification and automated SUV correction is novel and not yet widely proven.
Eligibility criteria
Show full inclusion / exclusion criteria
Inclusion Criteria: * patients undergoing PET/CT scans or therapeutic treatments with radiopharmaceuticals labelled with alpha or beta emitting nuclides Exclusion Criteria: * patients whose clinical or psychological conditions do not allow for their involvement
Where this trial is running
Reggio Emilia
- Azienda USL IRCCS di Reggio Emilia — Reggio Emilia, Italy (Recruiting)
Study contacts
- Study coordinator: Mauro Iori, MD
- Email: mauro.iori@ausl.re.it
- Phone: 0522/296655
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.