MRI + AI for Breast Cancer Risk

Recruiting at 3 trial locations

Overseen By Tiffany Tran

Age: 18+

Sex: Female

Trial Phase: Academic

Sponsor: University of California, San Francisco

Disqualifiers: Pregnancy, Claustrophobia, Diabetes, Hypertension, others

No Placebo Group All trial participants will receive the active study treatment (no placebo)

Compensation: Varies

Number of Visits: 1

400 Participants Needed

What You Need to Know Before You Apply

What is the purpose of this trial?

This trial aims to evaluate how effectively an MRI (a type of detailed body scan) can detect breast cancer in individuals identified as high-risk by a new assessment tool called Mirai. Mirai uses mammogram images to predict cancer risk. Participants flagged as high-risk by Mirai, despite having a clear or benign mammogram, will receive an additional MRI for further examination. Those with a mammogram indicating high risk and no breast cancer symptoms may be suitable candidates for this study. As an unphased trial, this study offers participants the chance to contribute to innovative research that may enhance early detection methods for breast cancer.

Will I have to stop taking my current medications?

The trial information does not specify whether you need to stop taking your current medications. It might be best to discuss this with the trial coordinators or your doctor.

What prior data suggests that this MRI + AI method is safe for breast cancer screening?

In a previous study, the Mirai model demonstrated promising results in predicting breast cancer risk. This tool employs artificial intelligence to identify individuals who might soon face a higher risk of developing breast cancer. While the model itself is safe, as it only assesses risk, the safety of follow-up steps, such as undergoing an MRI, should be considered.

MRIs are generally safe for most individuals and rarely cause serious side effects. However, some may feel cramped inside the machine or hear loud noises during the scan. Discuss any concerns with the medical team before joining the trial.

Since the study is not in a specific phase, it does not provide detailed safety data. However, because the study focuses on screening with an MRI rather than testing a new drug, the risks are likely minimal. Always consult a healthcare professional for personalized advice. ^{1 2 3 4 5}

Why are researchers excited about this trial?

Researchers are excited about using MRI combined with AI technology, known as Mirai, for assessing breast cancer risk because it offers a more personalized and potentially more accurate approach than traditional methods. Unlike the current standard of care, which often relies on mammograms alone, Mirai identifies high-risk individuals even when mammogram results appear negative or benign, allowing for earlier and more targeted intervention with supplemental MRIs. This method could enhance early detection and improve outcomes by providing a clearer risk assessment tailored to each patient.

What evidence suggests that MRI and Mirai are effective for breast cancer risk detection?

This trial will evaluate the use of the Mirai AI model alongside supplemental MRI for breast cancer risk assessment. Studies have shown that the Mirai AI model significantly aids in early breast cancer detection. Research indicates that by re-evaluating just 10% of MRIs with AI, early detection can improve by up to 30%. The AI tool correctly identified potential cancer development in 71% of the cases it flagged for a second review. It also outperformed other methods in predicting cancers that may appear between regular screenings. Mirai's ability to identify women at high risk is supported by its performance score, ranging from 0.75 to 0.84, demonstrating high reliability. ^{6 7 8 9 10}

Who Is on the Research Team?

Maggie Chung, MD

Principal Investigator

University of California, San Francisco

Are You a Good Fit for This Trial?

This trial is for individuals at high risk of breast cancer as determined by the Mirai-MRI assessment. Details on specific inclusion and exclusion criteria are not provided, but typically participants would have a family history or genetic predisposition to breast cancer.

Inclusion Criteria

Screening mammogram assessed as high-risk by Mirai (top 3 percentile of 2-year risk)

Availability of a routine screening mammogram report, along with a subsequent diagnostic mammogram report if applicable, and access to the corresponding Digital Imaging and Communications in Medicine (DICOM) images

Ability to understand and the willingness to sign a written informed consent document

Exclusion Criteria

My kidney function is severely impaired (GFR < 30 mL/min).

Screening mammogram that is assessed as BI-RADS 0 for technical recall

Contraindications for MRI: Metallic foreign body in the eye, MRI unsafe implants and/or medical devices, Adverse reaction to a (gadolinium-based) contrast agent in the past, Pregnant women, Claustrophobia, Exceeds site specific size and/or weight limit for MRI

Timeline for a Trial Participant

Screening

Participants are screened for eligibility to participate in the trial

2-4 weeks

Supplemental MRI

Participants identified as Mirai high-risk on a negative/benign screening mammogram will receive a supplemental MRI

Up to 12 months

1 visit (in-person)

Follow-up

Participants are monitored for cancer detection rate and other secondary outcomes

Up to 1 year

What Are the Treatments Tested in This Trial?

Interventions

• Magnetic resonance imaging
• Mirai

Trial Overview

The study is testing how well an AI model called Mirai can predict breast cancer risk using full-resolution mammograms. Participants will undergo supplemental screening with MRI to validate the accuracy of this AI-based risk assessment.

How Is the Trial Designed?

Group I: Supplemental MRI Experimental Treatment 2 Interventions

Participants identified as Mirai high-risk on a negative/benign screening mammogram will receive a supplemental MRI within 12 months of receiving a screening mammogram. Breast cancer risk following the Tyrer-Cuzick risk model will be assessed for comparison.

Who Is Running the Clinical Trial?

University of California, San Francisco

Lead Sponsor

Trials

2,636

Recruited

19,080,000+

Breast Cancer Research Foundation

Collaborator

Trials

79

Recruited

40,500+

Citations

1.

clinicaltrials.gov

clinicaltrials.gov/study/NCT07121972

Mirai-MRI: Validation of AI Models for Breast Cancer Risk

This is a multi-center, single arm trial to evaluate the cancer detection rate of supplemental screening magnetic resonance imaging (MRI) in participants ...

2.

sciencedirect.com

sciencedirect.com/science/article/pii/S1076633224007748

Early Detection of Breast Cancer in MRI Using AI

Re-evaluation of 10% of MRIs could increase early detection by up to 30%. •. The AI localized the future cancer in 71% of cases recommended for re-evaluation.

3.

rsna.org

rsna.org/media/press/2025/2611

AI Tool Identifies Women at High Risk of Interval Breast ...

The AI tool performed better at predicting interval cancers within a year of the screening examination versus 12 to 24 months or 24 to 36 months ...

4.

pmc.ncbi.nlm.nih.gov

pmc.ncbi.nlm.nih.gov/articles/PMC9148689/

Multi-Institutional Validation of a Mammography-Based ...

Recent work has demonstrated that Mirai, an AI model to predict 5-year cancer risk from screening mammograms, has shown considerable promise, obtaining area ...

5.

ascopubs.org

ascopubs.org/doi/full/10.1200/JCO.21.02908

Artificial Intelligence Risk Model (Mirai) Delivers Robust ...

As a result, Mirai maintained high performance (range, 0.75-0.84) and could accurately identify high-risk subsets across all test cohorts.

6.

insightsimaging.springeropen.com

insightsimaging.springeropen.com/articles/10.1186/s13244-024-01808-3

Validation of the Mirai model for predicting breast cancer risk ...

In conclusion, our study demonstrates the moderate effectiveness of the Mirai model in assessing future breast cancer risk among Mexican women.

7.

pmc.ncbi.nlm.nih.gov

pmc.ncbi.nlm.nih.gov/articles/PMC11202482/

Artificial Intelligence-Powered Imaging Biomarker Based ...

Mirai has showed promising results in short-term breast cancer risk prediction within 5 years, and the AI model developed using the cancer- ...

8.

pubs.rsna.org

pubs.rsna.org/doi/full/10.1148/radiol.222679

Evaluation of an AI Model to Assess Future Breast Cancer ...

The AI model was found to be a strong predictor of breast cancer risk for 3–6 years following a negative mammographic screening.

9.

clinicaltrials.gov

clinicaltrials.gov/study/NCT07121972

Mirai-MRI: Validation of AI Models for Breast Cancer Risk

This is a multi-center, single arm trial to evaluate the cancer detection rate of supplemental screening magnetic resonance imaging (MRI) in participants ...

10.

jamanetwork.com

jamanetwork.com/journals/jamanetworkopen/fullarticle/2823253

Cost-Effectiveness of AI for Risk-Stratified Breast Cancer ...

The AI model offers an immediate estimation of an individual's short-term risk of cancer incidence following a mammogram with negative findings.