Cancer RiskNCT07121972
Mirai-MRI: Validation of AI Models for Breast Cancer Risk
A study testing Magnetic resonance imaging (MRI) and Artificial Intelligence (AI) in people with Cancer Risk and Breast Cancer Risk, run by University of California, San Francisco at 4 sites in United States.
Trial 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. Read more about this study
- Who is it for?
- Ages 40 to 89 years, women onlyHealthy volunteers can take part
- Conditions the study is for
- Cancer Risk, Breast Cancer Risk
- What is being tested?
- Magnetic resonance imaging (MRI) and Artificial Intelligence (AI)
- Type of treatment
- Medical device, Surgery or procedure
- Could I receive a placebo?
- No, everyone receives an active treatment
- How many people
- 400 participants
- Where
- 4 sitesUnited States
- Study dates
- 3 Nov 2025to 31 Jan 2027
- Phase
- Interventional
- Are there results?
- Not yet: the study is under way
Key requirements
Who can take part, as listed by the sponsor. Only the study team can confirm whether you are eligible, so take this list to your doctor.
- Ages 40 to 89 years
- Women only
- Healthy volunteers accepted
- Adult, Older adult
Who may be able to join
- 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.
- 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.
Who cannot join
- 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.
Show all 15Show fewer
- Claustrophobia.
- Exceeds site specific size and/or weight limit for MRI.
- 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:
- History of "kidney disease" as an adult, including renal tumor or transplant.
- Diabetes treated with insulin or other prescribed medications.
- Hypertension (high blood pressure) requiring medication.
- Multiple myeloma.
- Solid organ transplant.
- History of severe hepatic disease/liver transplant/pending liver transplant.
Trial locations and contacts
4 sites in 1 country. Contact the study team or a site near you to ask about taking part.
United States4 sites, 4 recruiting
- Not yet recruiting
University of Chicago Comprehensive Cancer Center
Chicago, Illinois, 60637
- Not yet recruiting
University of California, San Diego
San Diego, California, 92093
- Recruiting
University of California, San Francisco
San Francisco, California, 94143
Tiffany Tran, tiffany.tran3@ucsf.edu
cancertrials@ucsf.edu
- Recruiting
University of Massachusetts Memorial Medical Center
Worcester, Massachusetts, 01655
About this study
Official title: Mirai-MRI: Multi-site Prospective 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 who are high-risk by Mirai-MRI assessment. Mirai is an accurate cancer risk model based on full-resolution mammograms.
Read the detailed description
PRIMARY OBJECTIVE:
- To estimate the cancer detection rate (CDR) of supplemental screening breast MRI in participants who are high-risk by the Mirai model
SECONDARY OBJECTIVES:
- 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.
- 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.
- Conditions
- Cancer Risk, Breast Cancer Risk
- Being tested
- Magnetic resonance imaging (MRI), Artificial Intelligence (AI)
- Keywords
- Screening, BI-RADS
What participants receive
What participants receive. In a randomised study each person is assigned to one group by chance.
Magnetic resonance imaging (MRI)Procedure or surgery
Also called MRI, MRI Scan
Undergo Magnetic resonance (MR) imaging
Artificial Intelligence (AI)Device
Also called AI Models, AI Algorithm
AI applied to MRI images
| Study group | Role | What they receive |
|---|---|---|
| Supplemental MRI | Experimental | 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. Receives: Procedure: Magnetic resonance imaging (MRI); Device: Artificial Intelligence (AI) |
What is being measured
The primary outcome is the main question the study is designed to answer.
Cancer detection rate (CDR)
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.
Measured: Up to 1 year
Secondary outcomes (15)
CDR of participants designated as low risk using the Tyrer-Cuzick (TC) criteria
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.
Measured: Up to 1 year
Comparison of CDR in low and high TC risk groups
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.
Measured: Up to 1 year
Positive predictive value of supplemental MRI screening and BI-RADS Score (PPV1)
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.
Measured: Up to 1 year
Positive predictive value of supplemental MRI screening recommending histological or surgical follow-up (PPV2)
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.
Measured: Up to 1 year
Positive predictive value of biopsies resulting in histological diagnosis (PPV3)
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.
Measured: Up to 1 year
False Positive Rate (FPR)
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.
Measured: Up to 1 year
Mean tumor size detected in supplemental imaging
Mean tumor size in millimeters (mm) with in situ and invasive components separately on supplemental screening MRI in Mirai high risk participants.
Measured: Up to 1 year
Frequency of tumor stage detected in supplemental imaging
The frequency of tumor stage diagnosed using the supplemental screening MRI in Mirai high risk participants will be reported.
Measured: Up to 1 year
Proportion of participants with Ki-67 expressed biomarker
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.
Measured: Up to 1 year
Proportion of participants with lymph node involvement detected in supplemental imaging
The proportion of participants with demonstrated lymph node involvement of cancers detected on the supplemental screening MRI in Mirai high risk participants.
Measured: Up to 1 year
Correlation between race/ethnicity and CDR
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
Measured: Up to 1 year
Correlation between menopausal status and CDR
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
Measured: Up to 1 year
Correlation between hormonal status and CDR
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.
Measured: Up to 1 year
Correlation between breast density and CDR
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.
Measured: Up to 1 year
Correlation between family history of cancer and CDR
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.
Measured: Up to 1 year
Timeline
From the start of the study to its completion; the mark is today. Estimated dates are the sponsor’s plan.
- First posted14 Aug 2025
- Study start3 Nov 2025
- Primary completion31 Jan 2027 (estimated)
- Study completion31 Jan 2027 (estimated)
Resources
- Official record on ClinicalTrials.govThe registry entry this page is built from, with its full change history.
- Other trials for Cancer RiskStudies of the same condition, open and under way.
- More trials run by University of California, San FranciscoThe sponsor's other registered studies.
- What the trial phases meanHow a treatment moves from first tests in people to approval.
More details
For doctors and researchers: how the study is designed, who runs it, and its registry IDs.
Study design
- Study type
- Interventional
- Phase
- Phase N/A
- Primary purpose
- Screening
- Allocation
- Not applicable
- Intervention model
- Single group
- Masking
- None (open label)
- Enrolment
- 400 participants (estimated)
Sponsor and investigators
- Lead sponsor
- University of California, San Francisco
- Sponsor type
- University, hospital or other
- Collaborators
- Breast Cancer Research Foundation
- Responsible party
- Sponsor
- Investigators
- Maggie Chung, MD, Principal investigator, University of California, San Francisco
IDs, dates and publications
- ClinicalTrials.gov ID
- NCT07121972
- Sponsor's protocol ID
- 25756
- Other IDs
- NCI-2025-06040
- Status last verified
- Nov 2025
- First submitted
- 6 Aug 2025
- Last updated
- 6 Nov 2025
- Results posted
- No
- Data monitoring committee
- No
- FDA-regulated drug
- No
- FDA-regulated device
- Yes
- Individual data sharing
- Yes: De-identified data may be shared with research collaborators during the course of the study.
Study at a glance
From the registry record, last updated by the sponsor on 6 Nov 2025. Recruitment status is as the sponsor reported it: confirm with the study team.
- Official title
- Mirai-MRI: Multi-site Prospective Validation of AI Models for Breast Cancer Risk
- ClinicalTrials.gov ID
- NCT07121972
- Acronym / sponsor ID
- 25756
- Conditions
- Cancer Risk, Breast Cancer Risk
- Keywords
- Screening, BI-RADS
- Study type
- Interventional
- Recruitment status
- Recruiting
- Enrolment
- 400 participants (estimated)
- Lead sponsor
- University of California, San FranciscoUniversity, hospital or other
- Collaborators
- Breast Cancer Research Foundation
- Study start
- 3 Nov 2025 (actual)
- Primary completion
- 31 Jan 2027 (estimated)
- Study completion
- 31 Jan 2027 (estimated)
- First posted
- 14 Aug 2025 (actual)
- Results
- Not posted in the source record
Clinical summary
The research question as the sponsor registered it. This describes what the study plans to test, not what it found.
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:
- To estimate the cancer detection rate (CDR) of supplemental screening breast MRI in participants who are high-risk by the Mirai model
SECONDARY OBJECTIVES:
- 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.
- 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 design
- Primary purpose
- Screening
- Allocation
- Not applicable
- Intervention model
- Single group
- Masking
- None (open label)
- Number of arms
- 1
| Arm | Type | Receives |
|---|---|---|
| Supplemental MRI | Experimental | Procedure: Magnetic resonance imaging (MRI), Device: Artificial Intelligence (AI)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 may qualify
- Ages
- 40 to 89 years
- Sex
- Female only
- Healthy volunteers
- Accepted
- Age groups
- Adult, Older adult
Key inclusion criteria (4 listed)
- 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.
- 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.
Key exclusion criteria (15 listed)
- Screening mammogram that is assessed as BI-RADS 0 for technical recall.
- Contraindications for MRI:
- 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:
Eligibility is decided by the study team after screening; this overview does not establish that a patient qualifies. Full inclusion and exclusion criteria.
Interventions
| Intervention | Type | Arms |
|---|---|---|
| Magnetic resonance imaging (MRI)Also: MRI, MRI ScanUndergo Magnetic resonance (MR) imaging | Procedure or surgery | Supplemental MRI |
| Artificial Intelligence (AI)Also: AI Models, AI AlgorithmAI applied to MRI images | Device | Supplemental MRI |
Primary outcome
Cancer detection rate (CDR)
Time frame: 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.
15 secondary outcomes
CDR of participants designated as low risk using the Tyrer-Cuzick (TC) criteria
Time frame: Up to 1 year
Comparison of CDR in low and high TC risk groups
Time frame: Up to 1 year
Positive predictive value of supplemental MRI screening and BI-RADS Score (PPV1)
Time frame: Up to 1 year
Positive predictive value of supplemental MRI screening recommending histological or surgical follow-up (PPV2)
Time frame: Up to 1 year
Positive predictive value of biopsies resulting in histological diagnosis (PPV3)
Time frame: Up to 1 year
False Positive Rate (FPR)
Time frame: Up to 1 year
Mean tumor size detected in supplemental imaging
Time frame: Up to 1 year
Frequency of tumor stage detected in supplemental imaging
Time frame: Up to 1 year
Proportion of participants with Ki-67 expressed biomarker
Time frame: Up to 1 year
Proportion of participants with lymph node involvement detected in supplemental imaging
Time frame: Up to 1 year
Correlation between race/ethnicity and CDR
Time frame: Up to 1 year
Correlation between menopausal status and CDR
Time frame: Up to 1 year
Correlation between hormonal status and CDR
Time frame: Up to 1 year
Correlation between breast density and CDR
Time frame: Up to 1 year
Correlation between family history of cancer and CDR
Time frame: Up to 1 year
Results and safety
This study is still under way. Results are not available in the source record yet.
Research links
- Official record on ClinicalTrials.govLast updated by the sponsor 6 Nov 2025.
- Individual participant dataSharing planned: Yes. De-identified data may be shared with research collaborators during the course of the study.
Related trials for Cancer Risk
RecruitingPhase 1
IL-17 Blockade to Decrease irAEs (REPLAY)
Metastatic Melanoma
RecruitingPhase 3
Testing Whether Hormone Therapy With Ribociclib is as Effective as Chemotherapy Followed by Hormone Therapy With Ribociclib for the Treatment of High Anatomic Stage Breast Cancer With Low Recurrence Risk, The RxFINE-Low Trial
Anatomic Stage II Breast Cancer AJCC v8, Anatomic Stage IIIA Breast Cancer AJCC v8
Recruiting
Decision Support for Chemoprevention
Breast Cancer
Not yet recruitingPhase 4
MACE and BTK Inhibitors
Hematologic Cancer, MACE
RecruitingPhase 2
Testing New Therapies for Patients With Acute Myeloid Leukemia Who Are Newly Diagnosed and Have Not Yet Started Treatment (A MyeloMATCH Treatment Trial)
Acute Myeloid Leukemia, Acute Myeloid Leukemia Arising From Previous Myelodysplastic/Myeloproliferative Neoplasm
Referral and contact
AzTrials does not enrol participants or take referrals. Contact the study team or a site listed below; they decide who can take part.
Maggie Chung, MD principal investigator
University of California, San Francisco
4 sites in 1 country: see every site and its status.
Questions about this trial
What is this clinical trial studying?
A study testing Magnetic resonance imaging (MRI) and Artificial Intelligence (AI) in people with Cancer Risk and Breast Cancer Risk, run by University of California, San Francisco at 4 sites in United States.
The full registered description is in the About this study section and the official record.
Who may be eligible to take part?
The sponsor lists 4 inclusion and 15 exclusion criteria. Eligibility is decided by the study team after screening, so read the full criteria and contact a listed site.
Is this clinical trial currently recruiting?
The record says: looking for participants now, as of the sponsor's last update on 6 Nov 2025. Status can change between updates, so confirm with the study contact before making plans.
Where is the study taking place?
The record lists 4 sites in United States. Whether a site is taking part right now should be confirmed with that site. See every site.
What are the possible benefits and risks?
They depend on the study and the treatment, and no study can promise a benefit. The study team explains the known risks during informed consent, before anyone joins; the record itself does not list them.
Are results available for this study?
This study is still under way. Results are not available in the source record yet.
How can a doctor refer a patient or contact the research team?
Contact Tiffany Tran (877-827-3222, tiffany.tran3@ucsf.edu), or a site near the patient. AzTrials does not enrol participants or take referrals.
What does the primary outcome measure?
Cancer detection rate (CDR) (time frame: Up to 1 year). It is what the study was designed to measure, not a finding.
Where can I read the original study information?
Does a listing mean the treatment is approved or proven to work?
No. A listing means the study is registered. It does not show that the treatment is safe, works, or is approved by a regulator.
How often is this information updated?
AzTrials copies changed records from ClinicalTrials.gov every night and reloads the whole registry every week. The sponsor last updated this record on 6 Nov 2025.