Litcius/Paper detail

BRAX, Brazilian labeled chest x-ray dataset

Eduardo Pontes Reis, Joselisa Péres Queiroz de Paiva, Maria C. B. da Silva, Guilherme Ribeiro, Victor Fornasiero de Paiva, Lucas Bulgarelli, Henrique Min Ho Lee, Paulo Victor Santos, Vanessa Mizubuti Brito, Lucas Tadashi Wada Amaral, Gabriel Laverdi Beraldo, Jorge N. Haidar Filho, Gustavo B. S. Teles, Gilberto Szarf, Tom Pollard, Alistair E. W. Johnson, Leo Anthony Celi, Edson Amaro

2022Scientific Data43 citationsDOIOpen Access PDF

Abstract

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.

Topics & Concepts

Computer scienceRadiologyRadiographyMedical physicsArtificial intelligenceMedicineCOVID-19 diagnosis using AIRadiomics and Machine Learning in Medical ImagingAI in cancer detection
BRAX, Brazilian labeled chest x-ray dataset | Litcius