Breast Micro-Calcifications Dataset with Precisely Annotated Sequential Mammograms

Dataset Version 3 Update

The ground truth images (.jpg) match the dimensions of the corresponding original images (.dcm), ensuring consistency across the dataset.

Breast Micro-Calcifications Dataset with Precisely Annotated Sequential Mammograms

Citing the Dataset

The dataset is released under a Creative Commons Attribution license, so please cite the dataset if it is used in your work in any form. Published academic papers should use the academic paper citation for our paper.  Personal works, such as projects or blog posts, should provide a URL to this Zenodo page, though a reference to our paper would also be appreciated.

Academic paper citation

Loizidou, K., Skouroumouni, G., Pitris, C. et al. Digital subtraction of temporally sequential mammograms for improved detection and classification of microcalcifications. Eur Radiol Exp 5, 40 (2021). https://doi.org/10.1186/s41747-021-00238-w

Personal use citation

Include a link to this Zenodo page - 10.5281/zenodo.14859694

ACKNOWLEDGMENT

This research is funded by the European Union’s Horizon 2020 research and innovation program under grant agreement No. 739551 (KIOS CoE) and from the Republic of Cyprus through the Directorate General for European Programs, Coordination and Development.

Contact Information

If you would like further information about the dataset, or if you experience any issues downloading files, please contact us at [e-mail].

General Information

This dataset consists of 100 pairs of mammograms, from two temporally sequential rounds. Specifically, this dataset includes the prior and recent mammograms of CC and MLO view of each patient. This is a complete dataset for the detection and BI-RADS classification of breast micro-calcifications, using digital mammograms. It contains normal (BI-RADS 1), benign (BI-RADS 2), and suspicious (BI-RADS 4-5) cases, and for each mammogram, an image with precise annotation of each individual micro-calcification, by two expert radiologists, is provided. In 32 suspicious cases, the biopsy results are also available.

More details are available in the README.txt