Published on 29/10/2021
The INCISIVE consortium is delighted to have been granted access to the INbreast database which will be used for kick-starting the training of our AI tools for breast cancer. The project partners would like to sincerely thank Ms. Inês Domingues for granting to us access and the Breast Research Group, INESC Porto, Portugal for this significant contribution to the INCISIVE project.
Mammographic databases play an important role in the development of algorithms aiming at the detection and diagnosis of mammary lesions. The new INbreast database has a total of 115 cases (410 images) from which 90 cases are from women with both breasts affected (four images per case) and 25 cases are from mastectomy patients (two images per case). Several types of lesions (masses, calcifications, asymmetries, and distortions) were included. Accurate contours made by specialists are also provided in XML format. More information regarding the INbreast database can be found in the following paper: Moreira, I. C., Amaral, I., Domingues, I., Cardoso, A., Cardoso, M. J., & Cardoso, J. S. (2012). INbreast: Toward a Full-field Digital Mammographic Database. Academic Radiology, 19(2), 236–248.
The strength of the INbreast database relies on the fact that it was built with full-field digital mammograms (in opposition to digitized mammograms), it presents a wide variability of cases, and is made publicly available together with precise annotations. This database will provide INCISIVE with a number of important possibilities to move the AI research against breast cancer forward.