AI for Impact on Breast Cancer
Free Annotated Mammogram Dataset to Advance AI Research in Breast Cancer Detection
Collaboration for Women’s Health
.svg)
.svg)
Request Access
This dataset provides access to a curated collection of annotated Digital Breast Tomosynthesis (DBT) studies intended to support academic and translational research in breast cancer detection and imaging AI.
To request access, please complete the application form including institutional affiliation and intended research purpose.
Dataset Summary
• 558 female patients
• Digital Breast Tomosynthesis (3D Mammography)
• 271 malignant (48.5%) / 287 benign (51.5%) cases
• Average size: 1.34 cm
• Approximately 85% of lesions <2 cm
• Expert segmentation annotations
• DICOM, NRRD, and structured JSON outputs
• Fully de-identified in compliance with HIPAA and GDPR
Citation & Acknowledgment
Users of this dataset are requested to acknowledge the Segmed–iMerit collaboration in any resulting publications or public disclosures, as well as refer to the DBT-2026 preprint, co-authored by clinical experts from Segmed and iMerit, as follow:
Wu J, Perandini L, Batra T, Igoshin S, Bari S, de Araujo AL, Willemink MJ. DBT-2026, a de-identified publicly available dataset of digital breast tomosynthesis exams with ground truth biopsies. medRxiv 2026.03.03.25337924; doi: 10.64898/2026.03.03.25337924.
For additional details, please refer to the Joint Research Use Agreement accepted when submitting the application form, to the Release Announcement or contact andreia@segmed.ai.
To request access, please complete the application form including institutional affiliation and intended research purpose.
Dataset Summary
• 558 female patients
• Digital Breast Tomosynthesis (3D Mammography)
• 271 malignant (48.5%) / 287 benign (51.5%) cases
• Average size: 1.34 cm
• Approximately 85% of lesions <2 cm
• Expert segmentation annotations
• DICOM, NRRD, and structured JSON outputs
• Fully de-identified in compliance with HIPAA and GDPR
Citation & Acknowledgment
Users of this dataset are requested to acknowledge the Segmed–iMerit collaboration in any resulting publications or public disclosures, as well as refer to the DBT-2026 preprint, co-authored by clinical experts from Segmed and iMerit, as follow:
Wu J, Perandini L, Batra T, Igoshin S, Bari S, de Araujo AL, Willemink MJ. DBT-2026, a de-identified publicly available dataset of digital breast tomosynthesis exams with ground truth biopsies. medRxiv 2026.03.03.25337924; doi: 10.64898/2026.03.03.25337924.
For additional details, please refer to the Joint Research Use Agreement accepted when submitting the application form, to the Release Announcement or contact andreia@segmed.ai.
