Artificial Intelligence Analysis for Magnetic Resonance Imaging in Screening and Diagnosis of Breast Cancer

Sponsor

Peking University People's Hospital (Other)

Overall Status

Recruiting

CT.gov ID

NCT05243121

Collaborator

(none)

5,000

Enrollment

Location

Anticipated Duration (Months)

116.2

Patients Per Site Per Month

Study Details

Study Description

Brief Summary

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 mass in Chinese women, which can shorten the examination time and avoid enhanced imaging while ensuring the accuracy of the diagnosis.

Condition or Disease	Intervention/Treatment	Phase
Breast Neoplasms Magnetic Resonance Imaging	Diagnostic Test: MRI

Study Design

Study Type:

Observational [Patient Registry]

Anticipated Enrollment :

5000 participants

Observational Model:

Cohort

Time Perspective:

Prospective

Official Title:

Peking University People's Hospital Radiology

Anticipated Study Start Date :

Feb 28, 2022

Anticipated Primary Completion Date :

Sep 30, 2025

Anticipated Study Completion Date :

Sep 30, 2025

Arms and Interventions

Arm	Intervention/Treatment
Clinically symptomatic patients Clinically symptomatic patients (defined as palpable masses, nipple discharge, asymmetric thickening or nodules, and abnormal skin changes according to the guidelines) should be examined by BMRI at the judgment of the clinician.	Diagnostic Test: MRI undergoing enhanced MRI

Arm

Intervention/Treatment

Clinically symptomatic patients

Clinically symptomatic patients (defined as palpable masses, nipple discharge, asymmetric thickening or nodules, and abnormal skin changes according to the guidelines) should be examined by BMRI at the judgment of the clinician.

Diagnostic Test: MRI

undergoing enhanced MRI

Outcome Measures

Primary Outcome Measures

Breast Cancer Screening [5 years]
Compare the area under the curve of the deep learning model of the BMRI full sequence, contrast-enhanced and non-contrast-enhanced sequence in the diagnosis of breast cancer.

Secondary Outcome Measures

The accuracy of radiologists and deep learning models [5 years]
Under the conditions of BMRI full sequence, contrast-enhanced and non-contrast-enhanced sequences, compare the sensitivity, specificity, positive predictive value and negative predictive value of breast tumor detection by radiologists and deep learning models.
Health economics [5 years]
Compare the examination time, reading time and cost of BMRI full sequence, contrast-enhanced and non-contrast-enhanced sequences.

Eligibility Criteria

Criteria

Ages Eligible for Study:

N/A and Older

Sexes Eligible for Study:

Female

Accepts Healthy Volunteers:

Inclusion Criteria:

Patients with clinical symptoms (define as palpable mass, nipple discharge, asymmetric thickening or nodules, and abnormal skin changes)
Patients undergoing full sequence BMRI examination
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.
There are contraindications for breast-enhanced MRI examinations such as allergy to contrast agents.
A prosthesis is implanted in the affected breast.
Patients during lactation or pregnancy