Deep Learning For the Classification of Lung Diseases Using Chest X-Rays

Abstract

   The discovery of X-rays marked a significant milestone in the field of medicine. One of the most common types of X-rays, the chest X-ray (CXR), allows doctors to examine an individual’s internal structure without surgery. Over the years, deep learning methods and algorithms have been developed to automate lung disease detection and identification. This paper introduces RADIA, a project that combines multiple deep learning techniques to identify abnormal areas and abnormalities in chest X-rays. RADIA builds upon previous studies conducted by the Stanford ML group, such as ChexNet and ChexPert. Our team utilized the ConvNeXt-Large, a deep learning convolutional model, implemented with a pre-trained ConvNext algorithm on the ImageNet database to classify various pathologies from public datasets like ChestX-ray14, CheXpert, MIMIC-CXR, PadChest, and VinDr-CXR, as well as a private dataset obtained from the Picture Archiving Communication System (PACS) at Verdun and Notre Dame Hospitals in Montreal in the collaboration with CIUSSS (Centre Integre Universitaire de Sante et de Services Sociaux du Centre-Sud-de-l’Ilede- Montreal) and valuable consultants from the radiology team at Notre Dame Hospital contributed to the project’s success. Our team employed image enhancement and augmentation techniques to create various image versions. We used different approaches to address the challenges, and the results were evaluated using metrics such as AUC, F1, and G-means to analyze performance with imbalanced input data. For a baseline measure, our team tried to show the performance with the state-of-the-art CheXpert and CheXzero results from Stanford University from a measurement perspective. It is essential to note that the project’s development extends beyond the creation of a web tool based on deep learning techniques. Our future plans involve building a decision helper that combines inference models and web tools to assist healthcare professionals.