HCFMRP COVID-19 & LID (v1)

Dataset designed to characterize lung interstitial diseases (LID) and COVID-19 on chest X-ray. For the composition of the dataset, frontal chest X-ray of patients from the Ribeirão Preto Medical School of University of São Paulo (Brazil) were classified into three groups: healthy (382 images), with LID (308 images), and with COVID-19 (189 images). All images were analyzed by a thoracic radiologist and COVID-19 diagnosis was confirmed by RT-PCR. For each of the groups, three types of files are available, all anonymized: the frontal view of the chest X-ray in DICOM format; the original images converted to PNG format; and the same images in 3-channel PNG format (RGB). The following directory and file structure is presented: <strong>1-Normal:</strong> for healthy cases <strong>normal-dcm-anonymized:</strong> anonymized DICOM files <strong>normal-png:</strong> image files converted to PNG <strong>normal-png-RGB:</strong> image files converted to 3-channel PNG <strong>2-LID:</strong> for LID cases <strong>lid-dcm-anonymized:</strong> anonymized DICOM files <strong> lid-png:</strong> image files converted to PNG <strong>lid-png-RGB:</strong> image files converted to 3-channel PNG <strong>3-COVID:</strong> for COVID-19 cases <strong>covid-dcm-anonymized:</strong> anonymized DICOM files <strong>covid-png:</strong> image files converted to PNG <strong>covid-png-RGB:</strong> image files converted to 3-channel PNG For more information, contact us: https://mainlab.fmrp.usp.br/