AI takes on breast cancer detection: can machines match expert radiologists?

NCT ID NCT07500428

First seen Apr 07, 2026 · Last updated Jun 06, 2026 · Updated 7 times

Summary

This study will test how well artificial intelligence (AI) can interpret breast ultrasound images using the latest BI-RADS criteria. Researchers will collect over 1,300 past ultrasound images with confirmed diagnoses and have expert radiologists annotate them. Then, various AI models will be evaluated on their accuracy in classifying breast lesions as benign or malignant. The goal is to build a standard benchmark to assess AI performance in breast imaging, which could help improve future diagnosis.

Disclaimer Read more

This is a summary of the original study . Summaries may miss details or leave out important information. Before applying or accepting participation, make sure you have read and understood the full study. Curemydisease.com takes no responsibility whatsoever for anything missed, misunderstood, or acted upon as a result of our summary — we know it does not capture everything.

Get updates

Get notified about this study

Sign up to get updates when this study changes or when new studies for ULTRASONOGRAPHY are added.

Our safety recommendation!

By submitting, you agree to our Terms of use

Contacts and locations

Study contacts

  • Contact

    Phone: •••-•••-•••• Email: •••••@•••••

  • Contact

    Phone: •••-•••-•••• Email: •••••@•••••

Locations

  • Peking Union Medical College Hospital

    RECRUITING

    Beijing, 100730, China

    Contact Phone: •••-•••-•••• Email: •••••@•••••

Conditions

Explore the condition pages connected to this study.