BRAX, Brazilian labeled chest x-ray dataset.

Autor: Reis EP; Hospital Israelita Albert Einstein - Big Data Analytics, São Paulo, Brazil. eduardo.reis@einstein.br.; Hospital Israelita Albert Einstein - Imaging Department, São Paulo, Brazil. eduardo.reis@einstein.br., de Paiva JPQ; Hospital Israelita Albert Einstein - Imaging Department, São Paulo, Brazil., da Silva MCB; Hospital Israelita Albert Einstein - Imaging Department, São Paulo, Brazil., Ribeiro GAS; Hospital Israelita Albert Einstein - Imaging Department, São Paulo, Brazil., Paiva VF; Hospital Israelita Albert Einstein - Big Data Analytics, São Paulo, Brazil., Bulgarelli L; Massachusetts Institute of Technology - Laboratory for Computational Physiology, Cambridge, USA., Lee HMH; Hospital Israelita Albert Einstein - Imaging Department, São Paulo, Brazil., Santos PV; Hospital Israelita Albert Einstein - Imaging Department, São Paulo, Brazil., Brito VM; Hospital Israelita Albert Einstein - Imaging Department, São Paulo, Brazil., Amaral LTW; Hospital Israelita Albert Einstein - Imaging Department, São Paulo, Brazil., Beraldo GL; Hospital Israelita Albert Einstein - Imaging Department, São Paulo, Brazil., Haidar Filho JN; Hospital Israelita Albert Einstein - Big Data Analytics, São Paulo, Brazil., Teles GBS; Hospital Israelita Albert Einstein - Imaging Department, São Paulo, Brazil., Szarf G; Hospital Israelita Albert Einstein - Imaging Department, São Paulo, Brazil., Pollard T; Massachusetts Institute of Technology - Laboratory for Computational Physiology, Cambridge, USA., Johnson AEW; The Hospital for Sick Children - Peter Gilgan Centre for Research and Learning, Toronto, Canada., Celi LA; Massachusetts Institute of Technology - Laboratory for Computational Physiology, Cambridge, USA.; Beth Israel Deaconess Medical Center - Department of Medicine, Boston, USA.; Harvard T.H. Chan School of Public Health - Department of Biostatistics, Boston, USA., Amaro E Jr; Hospital Israelita Albert Einstein - Big Data Analytics, São Paulo, Brazil.; Hospital Israelita Albert Einstein - Imaging Department, São Paulo, Brazil.
Jazyk: angličtina
Zdroj: Scientific data [Sci Data] 2022 Aug 10; Vol. 9 (1), pp. 487. Date of Electronic Publication: 2022 Aug 10.
DOI: 10.1038/s41597-022-01608-8
Abstrakt: Chest radiographs allow for the meticulous examination of a patient's chest but demands specialized training for proper interpretation. Automated analysis of medical imaging has become increasingly accessible with the advent of machine learning (ML) algorithms. Large labeled datasets are key elements for training and validation of these ML solutions. In this paper we describe the Brazilian labeled chest x-ray dataset, BRAX: an automatically labeled dataset designed to assist researchers in the validation of ML models. The dataset contains 24,959 chest radiography studies from patients presenting to a large general Brazilian hospital. A total of 40,967 images are available in the BRAX dataset. All images have been verified by trained radiologists and de-identified to protect patient privacy. Fourteen labels were derived from free-text radiology reports written in Brazilian Portuguese using Natural Language Processing.
(© 2022. The Author(s).)
Databáze: MEDLINE
Externí odkaz: