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

Not Applicable

Not yet recruiting

• Conditions: Cancer Risk; Breast Cancer Risk

• Registration Number: NCT07121972
• Lead Sponsor: University of California, San Francisco

Brief Summary

This is a multi-center, single arm trial to evaluate the cancer detection rate of supplemental screening magnetic resonance imaging (MRI) in participants who are high-risk by Mirai-MRI assessment. Mirai is an accurate cancer risk model based on full-resolution mammograms.

Detailed Description

PRIMARY OBJECTIVE:

I. To estimate the cancer detection rate (CDR) of supplemental screening breast MRI in participants who are high-risk by the Mirai model

SECONDARY OBJECTIVES:

I. To estimate the CDR of supplemental screening breast MRI in participants with high Mirai risk and low (\<20%) lifetime Tyrer-Cuzick (TC) risk.

II. To compare the CDR of supplemental screening breast MRI in participants with high Mirai risk and high (≥ 20%) lifetime TC risk versus CDR in participants with high Mirai risk and low (\<20%) lifetime TC risk.

III. To estimate the positive predictive value (PPV)1, PPV2, and PPV3 of supplemental MRI screening in participants with high Mirai risk.

IV. To estimate the false positive rate (1 - specificity) of supplemental screening MRI in participants with high Mirai risk.

V. To evaluate the tumor size, stage, grade, histological and molecular subtypes, Ki-67 percentage, and lymph node involvement of cancers detected on supplemental screening MRI in Mirai high risk participants.

VI. To evaluate the association between race/ethnicity, menopausal status, hormonal status, breast density, family history of cancer, and CDR in Mirai high-risk participants.

Study Timeline

• Status Verified: 2025-08
• Study First Submitted: 2025-08-06
• Study First Submitted QC: 2025-08-06
• Last Update Submitted: 2025-08-06
• Study Start: 2025-08-10
• Study First Posted: 2025-08-14
• Last Update Posted: 2025-08-14
• Primary Completion: 2027-01-31
• Study Completion: 2027-01-31

Recruitment & Eligibility

• Status: NOT_YET_RECRUITING
• Sex: Female
• Target Recruitment: 400

Inclusion Criteria

1. All asymptomatic participants assigned female at birth, ages 40-89 years old with screening mammography assessed as Breast Imaging Reporting and Data System (BI-RADS) 1, BI-RADS 2, or initial BI-RADS 0 with subsequent diagnostic mammogram assessed as BI-RADS 1 or BI-RADS 2.
2. Screening mammogram assessed as high-risk by Mirai (top 3 percentile of 2-year risk).
3. 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.
4. Ability to understand and the willingness to sign a written informed consent document.

Exclusion Criteria

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

2. Contraindications for MRI:

   1. Metallic foreign body in the eye.
   2. MRI unsafe implants and/or medical devices.
   3. Adverse reaction to a (gadolinium-based) contrast agent in the past.
   4. Pregnant women.
   5. Claustrophobia.
   6. Exceeds site specific size and/or weight limit for MRI.

3. If the participant meets site-specific criteria for screening estimated glomerular filtration rate (eGFR) prior to MRI, participants with severely impaired renal function (GFR < 30 mL/min) will be excluded. According to University of California, San Francisco's policy for MRI with contrast (gadolinium-containing), serum creatinine with calculation of eGFR should be obtained within 6 weeks of the MRI study for participants with any of the following risk factors:

   1. History of "kidney disease" as an adult, including renal tumor or transplant.
   2. Diabetes treated with insulin or other prescribed medications.
   3. Hypertension (high blood pressure) requiring medication.
   4. Multiple myeloma.
   5. Solid organ transplant.
   6. History of severe hepatic disease/liver transplant/pending liver transplant.

Study & Design

• Study Type: INTERVENTIONAL
• Study Design: SINGLE_GROUP

Primary Outcome Measures

Name	Time	Method
Cancer detection rate (CDR)	Up to 1 year	The CDR is defined as the number of breast cancers identified per 1,000 magnetic resonance imaging (MRI) screening examinations performed 1 year following supplemental screening MRI.

Secondary Outcome Measures

Name	Time	Method
Comparison of CDR in low and high TC risk groups	Up to 1 year	The CDR of supplemental screening breast MRI in participants with high Mirai risk and high (≥ 20%) lifetime TC risk versus CDR in participants with high Mirai risk and low (\<20%) lifetime TC risk will be compared using a two-proportion exact test.
Proportion of participants with lymph node involvement detected in supplemental imaging	Up to 1 year	The proportion of participants with demonstrated lymph node involvement of cancers detected on the supplemental screening MRI in Mirai high risk participants.
CDR of participants designated as low risk using the Tyrer-Cuzick (TC) criteria	Up to 1 year	Cancer detection rate is defined as the number of breast cancers identified per 1,000 MRI screening examinations performed of supplemental screening breast MRI in participants with high Mirai risk and low (\<20%) lifetime TC risk.
Positive predictive value of supplemental MRI screening and BI-RADS Score (PPV1)	Up to 1 year	PPV1 is the percentage of all positive supplemental MRI screening in participants with high Mirai risk (Breast Imaging Reporting and Data System (BI-RADS) 3, 4, or 5) for which the participant was found to be positive for cancer within 1 year from the time of MRI.
Positive predictive value of supplemental MRI screening recommending histological or surgical follow-up (PPV2)	Up to 1 year	PPV2 is the percentage of all supplemental MRI screenings in participants with high Mirai risk recommended for tissue diagnosis or surgical consultation (BI-RADS 4 and 5) that resulted in a histological diagnosis of cancer within 1 year.
Positive predictive value of biopsies resulting in histological diagnosis (PPV3)	Up to 1 year	PPV3 is the percentage of all known biopsies performed as a result of positive supplemental MRI screening (BI-RADS 4 or 5) that resulted in a tissue diagnosis of cancer within 1 year.
False Positive Rate (FPR)	Up to 1 year	A false positive is defined as an imaging result that incorrectly identifies a condition as present. The FPR = (False Positives / Total Tests) × 100 (or 1 - specificity) of results on supplemental screening MRIs in participants with high Mirai risk.
Mean tumor size detected in supplemental imaging	Up to 1 year	Mean tumor size in millimeters (mm) with in situ and invasive components separately on supplemental screening MRI in Mirai high risk participants.
Correlation between menopausal status and CDR	Up to 1 year	The Spearman's correlation coefficient (rs) will be used to measure the strength and direction of association between menopausal status and CDR. The Spearman correlation coefficient, rs, results in values from +1 to -1 where a value of +1 indicates a perfect association, and rs of 0 indicates no association and an rs of -1 indicates a perfect negative association. The closer rs is to 0, the weaker the association
Frequency of tumor stage detected in supplemental imaging	Up to 1 year	The frequency of tumor stage diagnosed using the supplemental screening MRI in Mirai high risk participants will be reported.
Proportion of participants with Ki-67 expressed biomarker	Up to 1 year	Ki-67 is divided according to percentage levels: \< 15% and \> 15%. The proportion of participants with pathologically confirmed Ki-67 by percentage level will be reported.
Correlation between race/ethnicity and CDR	Up to 1 year	The Spearman's correlation coefficient (rs) will be used to measure the strength and direction of association between race/ethnicity and CDR. The Spearman correlation coefficient, rs, results in values from +1 to -1 where a value of +1 indicates a perfect association, and rs of 0 indicates no association and an rs of -1 indicates a perfect negative association. The closer rs is to 0, the weaker the association
Correlation between hormonal status and CDR	Up to 1 year	The Spearman's correlation coefficient (rs) will be used to measure the strength and direction of association between hormonal status and CDR. The Spearman correlation coefficient, rs, results in values from +1 to -1 where a value of +1 indicates a perfect association, and rs of 0 indicates no association and an rs of -1 indicates a perfect negative association. The closer rs is to 0, the weaker the association.
Correlation between breast density and CDR	Up to 1 year	The Pearson correlation coefficient (r) will be used to measure the strength and direction of association between breast density and CDR. The Pearson correlation coefficient (r) can take values from +1 to -1 where a value of +1 indicates a perfect association, a value of 0 indicates no association, and a value of -1 indicates a perfect negative association. The closer r is to 0, the weaker the association.
Correlation between family history of cancer and CDR	Up to 1 year	The Spearman's correlation coefficient (rs) will be used to measure the strength and direction of association between history of cancer and CDR. The Spearman correlation coefficient, rs, results in values from +1 to -1 where a value of +1 indicates a perfect association, and rs of 0 indicates no association and an rs of -1 indicates a perfect negative association. The closer rs is to 0, the weaker the association.

Trial Locations

Locations (4)

University of California, San Diego; 🇺🇸 San Diego, California, United States

University of California, San Francisco; 🇺🇸 San Francisco, California, United States

University of Chicago Comprehensive Cancer Center; 🇺🇸 Chicago, Illinois, United States

University of Massachusetts Memorial Medical Center; 🇺🇸 Worcester, Massachusetts, United States