Crossmark

TECRR: a benchmark dataset of radiological reports for BI-RADS classification with machine learning, deep learning, and large language model baselines

Crossref DOI link: https://doi.org/10.1186/s12911-024-02717-7

Published Online: 2024-10-24

Update policy: https://doi.org/10.1007/springer_crossmark_policy

Authors

Hussain, Sadam

Naseem, Usman

Ali, Mansoor

Avendaño Avalos, Daly Betzabeth

Cardona-Huerta, Servando

Bosques Palomo, Beatriz Alejandra

Tamez-Peña, Jose Gerardo
License Information

Text and Data Mining valid from 2024-10-24

Version of Record valid from 2024-10-24
More Information

Article History

Received: 7 September 2023

Accepted: 10 October 2024

First Online: 24 October 2024

Declarations

:

: This retrospective study received approval from the local institutional ethical committee (protocol number: P000542-MIRAI-MODIFICADO-CEIC-CR002). The local institutional ethical committee also provided a waiver for written informed consent. A comprehensive retrospective review of the digital mammography database was conducted at TecSalud, a private hospital-based breast cancer center in Mexico. The study identified 58,321 consecutive mammography examinations (both diagnostic and screening examinations) in 37,916 women who voluntarily underwent mammography from January 2014 to June 2021. Subsequently, this was narrowed down to 20,297 screening mammography examinations from January 2014 to December 2016 (to ensure that all included women had at least 5 years of follow-up) in 13,028 women. Women were excluded if they were younger than 40 years, had an incomplete mammography.

: Not applicable.

: The authors declare no competing interests.

Document is current

Any future updates will be listed below