Pneumonia Classification in Chest X-Rays (CXRs) is organized by Segmind. As you maybe aware, "Pneumonia killed more than 808,000 children under the age of 5 in 2017, accounting for 15% of all deaths of children under 5 years. People at-risk for pneumonia also include adults over the age of 65 and people with preexisting health problems." — WHO
While prevalent, diagnosing pneumonia in a CXR accurately is difficult. Expert radiologists are required to review the CXR and also require confirmation through clinical examinations. To classify CXRs with pneumonia from their normal CXR counterparts, using machine learning and computer vision techniques.
It consists of 2425 CXRs for training and 606 CXRs for testing. Training data: 1145 Pneumonia CXRs and 1280 Normal CXRs. Every CXR is a 1024 X 1024 image in the PNG format.
The labels for each CXR were extracted using an NLP label extractor from corresponding radiology reports.