Disease Classification of Chest X-Ray using CNN

Abstract

With the advancement of technology, many things with greater accuracy and ease than past had been made possible. Using image processing and machine learning techniques, various noticeable achievements have been seen in medical science. This paper stands on the foundation of the Convolution Neural Network to diagnose the disease of patients from Chest X-Ray. The dataset used is from the National Institutes of Health Chest X-Ray Dataset available in Kaggle. Considerable output for seven diseases namely Atelectasis, Consolidation, Effusion, Mass, Nodule, Pleural Thickening, and Pneumothorax was found out of fourteen diseases available in the dataset. The accuracy for multilabel classification among these 7 diseases was found to be 60% and 75% while considering it as an individual disease.

Ähnliche Arbeiten