Artificial Intelligence Assisted Breast Ultrasound in Breast Cancer Screening (AIBU)

Application Research of B-ultrasound Assisted by Artificial Intelligence in Breast Cancer Screening

AIBU is a randomized, open-label study assessing the effectiveness of an articificial intelligence-assisted breast ultrasound breast cancer screening strategy compared to standard screening (according to the current local guidelines in each participating area) in detecting late-stage breast cancers.

Study Overview

• Status: Completed
• Conditions: Breast Cancer; Screening
• Intervention / Treatment: Device: AI-assisted breast ultrasound; Device: Routine breast ultrasound

Detailed Description

we enrolled asymptomatic women Women From January 2021 to December 2022, and then followed up for the next 1 year. The main study endpoint will be measured at the end of the one year after intervention.

• Study Type: Interventional
• Enrollment (Actual): 21790
• Phase: Not Applicable

Contacts and Locations

Study Locations

• China
  • Shanghai, China
    • Fudan University Shanghai Cancer Center
  • Shanghai, China
    • Shanghai Pudong New Area Healthcare Hospital For Women & Children
  • Shanghai
    • Shanghai, Shanghai, China, 200086
      • Maternal and Infant Healthy Centre of Hongkou District, Shanghai

Participation Criteria

Eligibility Criteria

• Ages Eligible for Study: Adult; Older Adult
• Accepts Healthy Volunteers: Yes

Description

Inclusion Criteria:

• Women aged 35-70 who participated in breast cancer screening (Shanghai Rural Women "Women two cancer screening project", national major public health service project "Rural women breast cancer screening Project" and "Gynecological diseases and breast diseases screening project for retired and living difficult women") in Shanghai district

Exclusion Criteria:

• 1. Personal history of breast carcinoma, either invasive or ductal carcinoma in situ (DCIS); 2. Personal history of any types of malignant neoplasms; 3. Known condition or suspicion of severe cardiopulmonary insufficiency, liver and kidney insufficiency and other systemic diseases; 4. Known condition or suspicion of serious comorbidities and average life expectancy less than 5 years; 5. History of lateral or bilateral mastectomy; 6. Disagree to participate in the study and follow-up interviews.

Study Plan

How is the study designed?

Design Details

• Primary Purpose: Prevention
• Allocation: Randomized
• Interventional Model: Parallel Assignment
• Masking: None (Open Label)

Number of Arms

2

Arms and Interventions

Participant Group / Arm	Intervention / Treatment
Experimental: AI assisted B-ultrasound breast cancer screening; Participants aged 35-70 years will be screened for breast cancer with AI assisted B-ultrasound	Device: AI-assisted breast ultrasound; AI-assisted breast ultrasound in community-based breast cancer screening
Active Comparator: routine screening; Participants aged 35-70 years will be screened for breast cancer with routine B-ultrasound by experienced primary care physicians.	Device: Routine breast ultrasound; Routine breast ultrasound conducted by primary care physicians

What is the study measuring?

Primary Outcome Measures

Outcome Measure	Measure Description	Time Frame
Incidence rate of early breast cancer in each arm	Early cancers should meet any of the following criteria at the time of diagnosis: less than 20 milimeters in diameter, no metastatic lymph nodes in the axilla, no distant metastasis, non-invasive cancers, stage 0, stage I, and stage IIa IIb (T2N1M0) breast cancer according to American Joint Committee on Cancer (AJCC) 8th staging.	4 years

Secondary Outcome Measures

Outcome Measure	Measure Description	Time Frame
Sensitivity, specificity, positive predictive value, and negative predictive value of the screening methods	A true-positive screening result (sensitivity) was a positive result in a participant who was diagnosed with breast cancer by further diagnostic work-up. A false-positive screening result was a positive result in the absence of breast cancer. A true-negative screening result (specificity) was a negative result in the absence of breast cancer and a false-negative test result was a negative result followed by diagnosis of interval cancer.	4 years

Collaborators and Investigators

• Sponsor: Fudan University
• Investigators: Study Chair: Ying Zheng, Fudan University

Study record dates

Study Major Dates

• Study Start (Actual): September 1, 2020
• Primary Completion (Actual): August 31, 2023
• Study Completion (Actual): December 31, 2023

Study Registration Dates

• First Submitted: July 22, 2024
• First Submitted That Met QC Criteria: July 22, 2024
• First Posted (Actual): July 26, 2024

Study Record Updates

• Last Update Posted (Actual): July 26, 2024
• Last Update Submitted That Met QC Criteria: July 22, 2024
• Last Verified: July 1, 2024

More Information

Terms related to this study

• Keywords: Ultrasound; Artificial intelligence; Cancer epidemiology
• Additional Relevant MeSH Terms: Skin Diseases; Neoplasms; Neoplasms by Site; Breast Diseases; Breast Neoplasms
• Other Study ID Numbers: 20210712

Plan for Individual participant data (IPD)

• Plan to Share Individual Participant Data (IPD)?: YES
• IPD Plan Description: We will share de-identified individual data that underlie the results reported. A decision concerning the sharing of other study documents, including protocol and statistical analysis plan will be examined upon request.
• IPD Sharing Time Frame: The data shared will be limit to that required for independent mandated verification of the published results. And the data will only be transferred after signing of a data access agreement.
• IPD Sharing Access Criteria: The study chairman will consider access to study data upon written detailed request sent to her, from 6 months until 5 years after publication of summary data.
• IPD Sharing Supporting Information Type: STUDY_PROTOCOL; SAP

Drug and device information, study documents

• Studies a U.S. FDA-regulated drug product: No
• Studies a U.S. FDA-regulated device product: No