Related Experiment Video
Updated: Sep 11, 2025

07:41
Performing Data Mining And Integrative Analysis Of Biomarker in Breast Cancer Using Multiple Publicly Accessible Databases
Published on: May 17, 2019
9.1K
MammosighTR: Nationwide Breast Cancer Screening Mammogram Dataset with BI-RADS Annotations for Artificial
Ural Koç1, Muhammed Said Beşler2, Ebru Akçapınar Sezer3
1Department of Radiology, Ankara Bilkent City Hospital, Üniversiteler Mahallesi 1604, Cadde No: 9 Çankaya, Ankara 06800, Türkiye.
Radiology. Artificial Intelligence
|August 13, 2025
Summary
The MammosighTR dataset offers BI-RADS-labeled mammograms from Türkiye's national breast cancer screening program. This resource aids in developing and validating artificial intelligence models for enhanced breast cancer detection.
Area of Science:
- Medical Imaging
- Artificial Intelligence in Radiology
- Oncology
Background:
- Breast cancer screening is crucial for early detection.
- Developing robust artificial intelligence (AI) models requires large, well-annotated datasets.
- Existing datasets may not fully represent diverse populations or screening protocols.
Purpose of the Study:
- To introduce and describe the MammosighTR dataset.
- To provide a valuable resource for AI model development in breast cancer detection.
- To facilitate research on AI-driven mammography analysis.
Main Methods:
- The MammosighTR dataset was curated from Türkiye's national breast cancer screening mammography program.
- Mammograms are labeled according to the Breast Imaging Reporting and Data System (BI-RADS).
- Detailed annotations include breast composition and lesion location within quadrants.
Main Results:
- The dataset contains a significant collection of mammograms suitable for AI training and testing.
- Annotations provide granular information for precise model evaluation.
- The dataset's origin ensures relevance to a specific national screening context.
Conclusions:
- The MammosighTR dataset is a valuable contribution to the field of AI in medical imaging.
- It offers a unique resource for advancing AI-powered breast cancer detection tools.
- This dataset can accelerate the development and validation of AI algorithms for mammography.

