Artificial Intelligence Analysis for Magnetic Resonance Imaging in Screening Breast Cancer in High-risk Women

Peking University People's Hospital5,000 enrolled

Overview

Use Convolutional Neural Networks Analysis for Classification of Contrast-enhancing Lesions at Multiparametric Breast MRI. Build an abbreviated protocal, and investigate whether an abbreviated protocol was suitable for breast magnetic resonance imaging screening for breast cancer in high-risk Chinese women, which can shorten the examination time and avoid enhanced imaging while ensuring the accuracy of the diagnosis.

Study Type

OBSERVATIONAL

Enrollment

5,000

Conditions

Breast Cancer Magnetic Resonance Imaging

Interventions

no interventionOTHER

no intervention

Eligibility

Sex: FEMALE

Medical Language ↔ Plain English

Inclusion Criteria: * Patients undergoing full sequence BMRI examination * Written informed consent and complete the clinical data questionnaire * Through the follow-up database, at least 6 months of follow-up results can be obtained to determine whether the diagnosis result is negative/benign/malignant; for patients who need pathological biopsy, the pathological biopsy results shall prevail to determine the lesion benign/malignant. Exclusion Criteria: * The breast had received radiotherapy, chemotherapy, biology and other treatments before BMRI. * Signs or symptoms of breast disease * There are contraindications for breast-enhanced MRI examinations such as allergy to contrast agents. * Patients during lactation or pregnancy

Locations (2)

Peking university people's hospital

Beijing, Beijing Municipality, China

RECRUITING

Peking University People's Hospital

Beijing, Beijing Municipality, China

RECRUITING

Outcomes

Primary Outcomes

screening yield

compare the rates of detection of breast cancers in the screening of high-risk populations between the Breast MRI full sequence, contrast-enhanced and non-contrast-enhanced sequence.

Time frame: 5 years

Secondary Outcomes

The accuracy of radiologists and deep learning models

compare the sensitivity，specificity， positive predictive value and negative predictive value of breast tumor detection by radiologists and deep learning models.

Time frame: 5 years

Central Contacts

shu wang, doctor

CONTACT

86+010-88324010 shuwang@pkuph.edu.cn

Data from ClinicalTrials.gov

This platform is for informational purposes only and does not constitute medical advice. Always consult a qualified healthcare professional.