In this competition, you have to automatically localize and classify 14 types of thoracic abnormalities from chest radiographs. The subset is based on a dataset consisting of a total of 15,000 scans that have been annotated by experienced radiologists. From those, 8,573 images have been used for training and 6,427 images for testing.  The train csv contains 45,925 rows and the test csv 21,989. 

Details on building the dataset can be found in our recent paper “VinDr-CXR: An open dataset of chest X-rays with radiologist's annotations”.