Texture-based Feature Extraction for COVID-19 Pneumonia Classification using Chest Radiography

Abstract

INTRODUCTION: The identification of COVID-19 pneumonia using chest radiography is challenging. OBJECTIVES: We investigate classification models to differentiate COVID-19-based and typical pneumonia in chest radiography. METHODS: We use 136 segmented chest X-rays to train and evaluate the performance of support vector machine (SVM), random forest (RF), AdaBoost (AB), and logistic regression (LR) classification methods. We use the PyRadiomics to extract statistical texture-based features in the right, left, and in six lung zones. We use a stratified k-folds (k=5) cross-validation within the training dataset, selecting the most relevant features with validation accuracy and relative feature importance. RESULTS: The AB model seems to be the best discriminant method, using six lung zones (AUC = 0.98). CONCLUSION: Our study shows a predominance of radiomic texture-based features related to COVID-19 pneumonia within the right lung, with a tendency within the upper lung zone.

Comparison Of K-nearest Neighbor (KNN) And Linear Discriminant Analysis (LDA) Algorithms For Mature Ajwa Date Fruit Classification

“…As one of the hybrid ensemble learning methods, AdaBoost is an excellent classifier for image classification, as shown in studies such as in multi-class imbalanced datasets, where it achieves an accuracy value of 91.78% [27], in the COVID-19 Pneumonia classification using Chest Radiography, with an accuracy score of 98% [28], and in the MINIST-based image classification, with an average accuracy value of 99% [29]. In this research, we built a model using the Adaboost algorithm to classify the feature extraction dataset into American, English, or French bulldog, with an illustration of the model shown in Figure 5.…”