iMerit, Segmed & Advocate Health Release Dataset for AI Research in Breast Cancer

The initiative is designed to provide researchers and developers with clinically validated imaging data to accelerate the development of AI tools and applications for early breast cancer detection.

iMerit, a leader in expert structured data for healthcare AI, in collaboration with Segmed and Advocate Health, has announced the release of an open-source annotated dataset of 3D mammography images to support AI-based research in breast cancer detection.

The initiative is designed to provide researchers and developers with clinically validated imaging data to accelerate the development of AI tools and applications for early breast cancer detection.

As per the announcement, the dataset includes annotated breast tomosynthesis images and is available as an open-source resource for research purposes.

It contains imaging studies from 558 female patients and is based on Digital Breast Tomosynthesis (DBT), commonly referred to as 3D mammography, which generates three-dimensional images of breast tissue for screening and diagnostic evaluation.

Further, the dataset has been curated with biopsy-confirmed diagnoses and annotations reviewed by U.S. board-certified radiologists and breast imaging specialists.

In addition, the dataset contains 271 malignant cases (48.5%) and 287 benign cases (51.5%), which provides clinically verified outcomes that are expected to support the development of AI models for breast cancer detection.

Reports also suggest that the dataset is suited for training AI models to detect early-stage breast cancer.

Furthermore, the imaging volume is provided in DICOM format, and the annotations are available in JSON format, including lesion classifications and coordinates, and are fully de-identified in compliance with HIPAA and GDPR standards.

Commenting on the new initiative, Dr. Sina Bari, VP of Healthcare and Life Science AI at iMerit, said, “At iMerit, we believe high-quality, responsibly annotated data is the foundation for meaningful advances in AI for healthcare. By releasing this dataset openly, we hope to empower researchers worldwide to develop tools that can support radiologists, improve outcomes, and ultimately save lives.”

Stay tuned for more such updates on Digital Health News