DETECTION AND CLASSIFICATION OF LUNG DISEASES

Abstract

Lung diseases are the disorders that affect the lungs, the organs that allow us to breathe and it is the most common medical conditions worldwide especially in India. The diseases such as pneumonia and normal lung are detected and classified in this work. The purpose ofthe work is to detect and classify the lung diseases by effective feature extraction through Convolutional Neural Network. The preprocessing techniques will remove the noises and the feature extraction are done to extract the useful features in the image and the feature selection technique will optimize the top ranking features that are relevant for the tagged image and the classifiers employed to classify the images and the performance measures are found for the same and accurate results. Deep learning algorithms, in particular convolutional networks, have rapidly become a methodology of choice for analysing medical images. In this project, we will use the dataset called Chest X-Ray Images (Pneumonia) that can be downloaded from the following link: https://www.kaggle.com/paultimothvmoonev/chest-xrav-pneumonia/home. dataset is organized into 3 folders (train, test, Val) and contains subfolders for each image category (Pneumonia/Normal). There are 5,863 X-Ray images (JPEG) and 2 categories (Pneumonia/Nomial). The project will involve development, training and testing of a classifier that can classify X-ray images correctly. It is a multi-level classification problem and a convolutional neural network will be developed for this purpose.