X-ray image-based pneumonia detection and classification using deep learning

Pneumonia is a dangerous lung disease that has affected millions of people worldwide. Several people have died as a result of incorrect pneumonia diagnosis and treatment. This has necessitated the urgent need for quick detection and classification methods of pneumonia detection for efficient treatment and quick recovery of affected persons. However, the causes of pneumonia are not accurately diagnosed using outmoded methods which use chest X-rays. This paper therefore presents a method for identifying and classifying chest X-ray images of normal and pneumonia-infected persons. The designed deep learning model first preprocesses the X-ray images to extract useful features, then segments them using a threshold segmentation technique, detects normal and pneumonia infected persons from X-ray images using the YOLOv3 detector, and classifies them as normal and with pneumonia using Support vector machine (SVM) and softmax. The suggested model was trained and evaluated using a dataset of chest X-ray images. The results show that the overall accuracy, precision, recall, and F1-score are all 99%. The findings show that deep features produced accurate and consistent characteristics for pneumonia detection. Using the presented approach, radiologists can assess pneumonia patients and deliver a rapid diagnosis.