Last reviewed · How we verify
NCT07500428: BUST-AI Bench
Construction of a Benchmark for Breast Ultrasound AI Interpretation and Performance Evaluation of Multimodal AI Models
trial testing Multimodal AI Model Diagnostic Evaluation in Breast Neoplasms in 1,380 participants. Currently enrolling.
1 December 2026
Quick facts
| Lead sponsor | Peking Union Medical College Hospital |
|---|---|
| Status | Recruiting now |
| Study type | OBSERVATIONAL |
| Enrollment | 1,380 |
| Start date | 12 March 2026 |
| Primary completion | 1 December 2026 |
| Estimated completion | 1 March 2027 |
| Sites | 1 location across China |
Drugs / interventions tested
- Multimodal AI Model Diagnostic Evaluation
Conditions studied
- Breast Neoplasms — all drugs for Breast Neoplasms →
- Breast Diseases — all drugs for Breast Diseases →
- Ultrasonography — all drugs for Ultrasonography →
Sponsor
Peking Union Medical College Hospital
Who can join
Adults 18 to 75, female only, with Breast Neoplasms or Breast Diseases. Patients with the condition only — healthy volunteers not accepted.
Sponsor's own description
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.
Publications & conference data
No peer-reviewed publications indexed yet for this trial.
Verify or expand the search:
- PubMed search for NCT07500428
- Europe PMC full search
- ASCO Meeting Library
- ESMO Meeting Library
- bioRxiv preprints
- medRxiv preprints
- Google Scholar
Related trials
Other recruiting trials for Breast Neoplasms
Currently open trials in the same condition.
- NCT07214532 — Signatera-Guided CDK4/6 Inhibitor Therapy in Breast Cancer · NA · recruiting
- NCT07581834 — Efficacy and Safety of Dalpiciclib Combined With Endocrine Adjuvant Therapy for Early HR +/HER2- Breast Cancer: a Multic · Phase 2 · recruiting
- NCT07222215 — PhII Randomized CAPecitabine + ELAcestrant vs. Capecitabine Alone in ER+ Breast Cancer (CAPELA) · Phase 2 · recruiting
- NCT07465393 — Facility-Based Multi-Modal Rehab vs. Home-Based Resistance Exercise for Quality of Life in Breast Cancer Survivors · NA · recruiting
- NCT07505797 — ATUSA Ultrasound Diagnostic Imaging for Breast Lesions Evaluation (AUDIBLE) · recruiting
Other Peking Union Medical College Hospital trials
Trials by the same sponsor.
- NCT07466251 — PCSK9 Inhibitor for Intracranial Atherosclerosis Related Acute Ischemic Stroke · Phase 4 · not yet recruiting
- NCT06743321 — Speech-to-speech Voice-cloning Care (SVCC) to Improve ICU-acquired Anxiety for Critically Ill Patients · NA · not yet recruiting
- NCT07590336 — 68Ga-NYM207 PET/CT Imaging in Hepatocellular Carcinoma · Phase 1, PHASE2 · not yet recruiting
- NCT07515976 — Mapping of Genomic Structural Variations in Major Birth Defects · not yet recruiting
- NCT07386756 — Early Precise Identification and Intervention Strategies for Individuals at High Risk of Prediabetes · not yet recruiting
Verify against primary sources
- ClinicalTrials.gov — authoritative US registry record
- WHO ICTRP — international registry index
- EU Clinical Trials Register
- Sponsor press releases (Google)
- Trial protocol + status: ClinicalTrials.gov NCT07500428 (US National Library of Medicine, public domain)
- Drug + disease cross-links: matched in real time against Drug Landscape's normalised drug + company + condition tables
- Sponsor: as reported to ClinicalTrials.gov by Peking Union Medical College Hospital
- Last refreshed: 30 March 2026
Drug Landscape aggregates and links these public records for informational use only. Always verify against the primary source before clinical or regulatory decisions. Canonical URL: https://druglandscape.com/trial/NCT07500428.
Primary sources · FDA · ClinicalTrials.gov · EMA · SEC EDGAR · ChEMBL · Wikidata · full sourcing