Improved MRI methods to distinguish benign from cancerous pelvic findings
Clinical Evidence Generation of AI Enabled Fast, Accurate and Precise Screening and Staging of Benign vs Malignant Pelvic Abnormalities
This test tries new deep-learning image-processing methods on MRI scans to get clearer images faster for adults scanned for prostate screening or suspected endometriosis.
Quick facts
| Study type | Observational |
|---|---|
| Enrollment | 60 (estimated) |
| Ages | 18 Years and up |
| Sex | All |
| Sponsor | Mayo Clinic Academic / other |
| Locations | 1 site (Rochester, Minnesota) |
| Trial ID | NCT07407959 on ClinicalTrials.gov |
What this trial studies
This observational study applies two non–FDA-approved image reconstruction approaches (Adaptive Image Reconstruction Deep Learning and Sonic Deep Learning) to pelvic MRI scans and compares image quality and scan processing time with current techniques. Adults referred for prostate MRI screening (with no prior prostate treatment or biopsy) or referred for pre-surgical evaluation of suspected endometriosis will be included. The study collects MRI data at a single site and processes images using the novel algorithms without changing clinical care. Standard MRI safety exclusions (eg, incompatible implants, pregnancy) and the ability to consent are required.
Who should consider this trial
Good fit: Adults 18 and older referred for prostate MRI screening with no prior prostate treatment or biopsy, or adults referred for evaluation of suspected endometriosis before surgery, who can safely undergo MRI and provide consent.
Not a fit: People under 18, pregnant individuals, those with MR-incompatible implants or other MRI contraindications, patients unable to consent, and prostate patients with prior prostate treatment or biopsy are unlikely to qualify or benefit from this protocol.
Why it matters
Potential benefit: If successful, these methods could produce clearer MRI images in less time, helping clinicians better distinguish benign from malignant pelvic abnormalities and speed diagnosis and treatment planning.
How similar studies have performed: Related deep-learning MRI reconstruction techniques have shown promising improvements in image quality and speed in prior research, but the specific AIR Recon and Sonic DL approaches used here are novel and not FDA-approved.
Eligibility criteria
Show full inclusion / exclusion criteria
Inclusion Criteria: * Patient over the age of 18 * For prostate group, any patient referred for prostate MR for screening purposes with no prior prostate related treatment or prior biopsy * For endometriosis group, any patient referred for possible endometriosis evaluation (pre-surgical) Exclusion Criteria: * Individuals unable to undergo MRI imaging (MR-conditional or MR-nonconditional devices which would need additional procedures/conditions for scanning, pregnant people, individuals with implanted metal, etc.) * Patient under the age of 18 * Patient who is unable to consent
Where this trial is running
Rochester, Minnesota
- Mayo Clinic in Rochester — Rochester, Minnesota, United States (Recruiting)
Study contacts
- Principal investigator: Candice A. Bookwalter, MD, PhD — Mayo Clinic in Rochester
- Study coordinator: Clinical Trials Referral Office
- Email: mayocliniccancerstudies@mayo.edu
- Phone: 855-776-0015
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.