A Machine Learning based Approach for Detection of Pneumonia by Analyzing Chest X-Ray Images

Pneumonia is a thoracic illness that affects human lungs areas, and chest X-Rays mainly diagnose it. With the recent advances in soft computing techniques, various algorithmic approaches are used to predict Pneumonia which can save millions of lives by detecting illness early. This study uses machine learning techniques to analyze chest X-ray images and predict Pneumonia. We have proposed a model by using some of the machine learning classifiers like Logistic Regression (LR), Neural Network (NN), and Support Vector Machine (SVM) that can detect the presence or absence of Pneumonia in chest X-ray images. Initially, image pre-processing techniques were applied to enhance the image quality; then, a texture-based feature extraction, namely Gray-Level Co-Occurrence Matrix (GLCM) technique, was used to represent image characteristics inside them. Further, the classifiers like LR, NN, and SVM were used to categorize the collected features using k-fold validation. Experiments are conducted with Kaggle dataset on MATLAB 2021. The results are compared on the basis of recall, accuracy, area under the receiver operating characteristic curve (AUC) and precision. The proposed approach performs better as compared to existing approaches.