AI-Based Self-Supervised Learning Model Using Non-Contrast Breast MRI for Early Screening and Clinical Utility Evaluation

NCT07205276 | Not Yet Recruiting

• 2 other identifiers: SAHZhejiangU-202509162025-0736
• Study Type: interventional
• Target: 30,000
• Locations: 0 countries
• Sites: N/A

Brief Summary

Breast cancer is the most common malignant disease among women worldwide, with rising incidence and younger age at onset in China. Early detection is critical for improving survival, yet current screening methods such as mammography and ultrasound show limited sensitivity in Chinese women, particularly those with dense breast tissue. Contrast-enhanced MRI offers higher diagnostic performance but its use is limited by high costs, safety concerns with gadolinium-based contrast agents, and limited accessibility. This investigator-initiated trial aims to evaluate the clinical application of non-contrast multiparametric MRI, combined with advanced artificial intelligence algorithms, for the early detection and diagnosis of breast cancer. The study will collect MRI imaging data from multiple centers and integrate radiomic features across T2-weighted imaging, diffusion-weighted imaging, and apparent diffusion coefficient maps. A deep learning-based model will be developed and validated to improve lesion detection, differential diagnosis, and risk stratification. The ultimate goal of this project is to establish a safe, accurate, and scalable breast cancer screening pathway suitable for Chinese women. By reducing dependence on invasive procedures and contrast agents, and by leveraging AI for standardization and efficiency, this approach may significantly improve early detection rates and contribute to better patient outcomes.

Conditions

Breast Cancer Detection; Early Detection of Cancer; AI (Artificial Intelligence)

Keywords

Breast MRI; Non-contrast MRI; Radiomics; Deep Learning; Breast Cancer Screening

Outcome Measures

Primary Outcomes (1)

• Diagnostic accuracy of AI-based non-contrast multiparametric MRI for breast cancer detection

  Diagnostic performance of the AI-based radiomics model using non-contrast multiparametric breast MRI (T2WI, DWI, ADC) will be evaluated. The performance will be compared against the reference standard (histopathology or follow-up imaging).

  Within 12 months of study enrollment

Secondary Outcomes (1)

• Sensitivity and specificity stratified by breast cancer molecular subtype

  Within 12 months of enrollment

Study Arms (2)

Breast Cancer/Suspected Cases

EXPERIMENTAL

Participants will undergo non-contrast multiparametric breast MRI, including T2-weighted imaging, diffusion-weighted imaging (DWI), and apparent diffusion coefficient (ADC) mapping. Imaging data will be analyzed using radiomics and AI-based algorithms for breast cancer detection and diagnosis.

Diagnostic Test: Non-contrast multiparametric breast MRI with AI-based radiomics analysis

Standard Radiologist Reading

ACTIVE COMPARATOR

Participants undergo standardized non-contrast multiparametric breast MRI (T2WI, DWI, ADC). Imaging data are interpreted by radiologists without AI assistance, representing the current standard of care

Diagnostic Test: Standard radiologist reading of non-contrast multiparametric breast MRI

Interventions

Non-contrast multiparametric breast MRI with AI-based radiomics analysis DIAGNOSTIC_TEST

Participants will receive standardized non-contrast multiparametric breast MRI scans (T2WI, DWI, ADC). Imaging features will be extracted and analyzed using artificial intelligence-based radiomics and deep learning algorithms to improve early detection and diagnosis of breast cancer.

Breast Cancer/Suspected Cases

Standard radiologist reading of non-contrast multiparametric breast MRI DIAGNOSTIC_TEST

Imaging data interpreted by trained radiologists following routine clinical practice, without AI assistance.

Standard Radiologist Reading

Eligibility Criteria

• Age: 30 Years - 70 Years
• Sex: female
• Healthy Volunteers: No
• Age Groups: Adult (18-64), Older Adult (65+)

You may qualify if:

• Female, age 30-70 years
• Completed breast MRI scan, including at least T2WI, DWI, and ADC sequences
• Multimodal data acquired within the same time window (≤90 days)
• A clear clinical outcome: pathologically confirmed or ≥12-24 months of negative follow-up
• The time window between imaging examination and outcome determination was ≤90 days
• Signed informed consent

You may not qualify if:

• Absolute contraindications to MRI (pacemaker, cochlear implant, ocular metal foreign body, etc.)
• Pregnant or lactating women
• Recent history of breast surgery/radiotherapy (≤6 months) or imaging after neoadjuvant therapy
• Substandard image quality (severe motion artifact, signal-to-noise ratio below threshold)
• Incomplete clinical data or time window exceeded
• Known breast cancer metastasis or recurrence

Sponsors & Collaborators

• Second Affiliated Hospital, School of Medicine, Zhejiang University: lead
• Alibaba DAMO Academy: collaborator

Central Study Contacts

Chao Ni, Doctor

CONTACT

+86 13989463951; drnichao@zju.edu.cn

Study Design

• Study Type: interventional
• Phase: not applicable
• Allocation: NA
• Masking: NONE
• Purpose: DIAGNOSTIC
• Intervention Model: PARALLEL
• Sponsor Type: OTHER
• Responsible Party: SPONSOR

Model Details: All enrolled participants will undergo non-contrast multiparametric MRI. Imaging data will be analyzed using radiomics and AI-based algorithms. There is no comparator or randomization, as this is a single-arm diagnostic performance study

Study Record Dates

• First Submitted: September 25, 2025
• First Posted: October 3, 2025
• Study Start: October 1, 2025
• Primary Completion (Estimated): October 1, 2027
• Study Completion (Estimated): December 1, 2027
• Last Updated: October 3, 2025

Record last verified: 2025-09

Data Sharing

• IPD Sharing: Will share
• Shared Documents: STUDY PROTOCOL, SAP, ANALYTIC CODE
• Time Frame: De-identified individual participant data (IPD) and supporting documents will be available beginning 6 months after publication of the primary results and ending 5 years after publication.
• Access Criteria: Researchers who provide a methodologically sound proposal will be able to access de-identified IPD. Proposals should be directed to the corresponding investigator. Data will be shared via a controlled-access repository after approval of a data access agreement.