← Back to Clinical Trials
Recruiting NCT07500428

NCT07500428 Construction of a Benchmark for Breast Ultrasound AI Interpretation and Performance Evaluation of Multimodal AI Models

◆ AI Clinical Summary
Plain-language summary for patients
Clinical Trial Summary
NCT ID NCT07500428
Status Recruiting
Phase
Sponsor Peking Union Medical College Hospital
Condition Breast Neoplasms
Study Type OBSERVATIONAL
Enrollment 1,380 participants
Start Date 2026-03-12
Primary Completion 2026-12-01

Eligibility & Interventions

Sex Female only
Min Age 18 Years
Max Age 75 Years
Study Type OBSERVATIONAL
Interventions
Multimodal AI Model Diagnostic Evaluation

Eligibility Fast-Check

Enter your details for a quick preliminary check. This does not replace medical advice.

What to Expect as a Participant

This is an observational study. You will not receive an experimental treatment; researchers will collect data based on your existing condition or standard treatment.

This trial targets 1,380 participants in total. It began in 2026-03-12 with a primary completion date of 2026-12-01.

⚠ This information is for research awareness only. Always consult your physician before joining any clinical trial. Participation is voluntary and you may withdraw at any time.

Brief Summary

This single-center, retrospective, observational study aims to construct a standardized benchmark evaluation system for intelligent breast ultrasound image interpretation and to systematically assess the diagnostic performance of current mainstream multimodal artificial intelligence (AI) models. De-identified B-mode breast ultrasound images with confirmed pathological diagnoses will be retrospectively collected from the institutional archive (2018-2025) and supplemented with images from published open-access datasets. Expert radiologists with varying experience levels will independently annotate all images according to the American College of Radiology (ACR) Breast Imaging Reporting and Data System (BI-RADS) v2025 criteria, including glandular tissue composition, lesion characterization (mass vs. non-mass lesion), morphological descriptors, and final BI-RADS classification. Baseline deep learning models (CNN-based ResNet-50 and Transformer-based USFM) will be trained to establish performance baselines and to stratify cases by diagnostic difficulty through cross-architecture consensus. Multiple multimodal large language models (MLLMs), including both general-purpose and medical-domain models, will then be evaluated via standardized API calls using BI-RADS-guided chain-of-thought prompts at temperature 0 for reproducibility. Primary endpoints include BI-RADS classification accuracy and diagnostic AUC for benign-malignant differentiation. Model robustness and safety will be assessed through out-of-distribution rejection testing, temperature-stability experiments, and thinking-mode ablation studies. This study adheres to the FLAIR and TRIPOD-LLM reporting guidelines.

Eligibility Criteria

Inclusion Criteria: * B-mode breast ultrasound grayscale images from the institutional PACS database or from published open-access breast ultrasound datasets with documented original institutional ethics approval * Image quality adequate for clinical diagnosis with clear visualization of the region of interest * Pathological diagnosis confirmed (for benign and malignant lesion groups), or normal breast status confirmed by a senior radiologist with \>15 years of breast ultrasound experience (for the normal group) * Complete de-identification with removal of all personally identifiable information Exclusion Criteria: * Severely degraded image quality precluding meaningful BI-RADS assessment * Duplicate images from the same patient (only the most representative image retained per lesion) * Images with residual personally identifiable information after de-identification processing * Cases with ambiguous, disputed, or unavailable pathological results * Non-B-mode ultrasound images, including elastography, contrast-enhanced ultrasound, and Doppler imaging

Contact & Investigator

Central Contact

Qingli Zhu, MD

✉ zqlpumch@126.com

📞 +86 13621376699

Principal Investigator

Qingli Zhu, MD

PRINCIPAL INVESTIGATOR

Peking Union Medical College Hospital

Frequently Asked Questions

Who can join the NCT07500428 clinical trial?

This trial is open to female participants only, aged 18 Years or older, up to 75 Years, studying Breast Neoplasms. Full inclusion and exclusion criteria are listed in the Eligibility Criteria section. Always confirm your eligibility with the research team before applying.

Is NCT07500428 currently recruiting?

Yes, NCT07500428 is actively recruiting participants. Contact the research team at zqlpumch@126.com for enrollment information.

Where is the NCT07500428 trial being conducted?

This trial is being conducted at Beijing, China.

Who is sponsoring the NCT07500428 clinical trial?

NCT07500428 is sponsored by Peking Union Medical College Hospital. The principal investigator is Qingli Zhu, MD at Peking Union Medical College Hospital. The trial plans to enroll 1,380 participants.

Related Trials

ClinicalMetric — Independent clinical trial intelligence platform. Not affiliated with NIH, ClinicalTrials.gov, the U.S. FDA, or any pharmaceutical company, hospital, or clinical research organization. Trial data is sourced from ClinicalTrials.gov for informational purposes only and does not constitute medical advice. Do not make any treatment, enrollment, or health decisions based solely on information found here — always consult a qualified healthcare professional. Full Disclaimer  ·  Last Reviewed: April 2026  ·  Data Methodology