Classification of Pneumonia, Tuberculosis and Covid-19 from Chest X-Ray Images Using Convolution Neural Network Model

Area of Science:

• Medical Imaging Analysis
• Artificial Intelligence in Healthcare
• Radiology

Background:

• Accurate diagnosis of respiratory diseases like pneumonia, tuberculosis (TB), and COVID-19 is critical for patient care and public health.
• Deep learning (DL) offers advanced capabilities for medical image classification and automated screening.

Purpose of the Study:

• To develop and evaluate a DL-based approach for classifying chest X-ray images into three categories: pneumonia, TB, and COVID-19.
• To assess the performance of the DL model against traditional machine learning techniques.

Main Methods:

• Utilized convolutional neural networks (CNNs) for feature extraction from chest X-ray images.
• Trained the CNN model on a large dataset of annotated chest X-rays.
• Evaluated performance using accuracy, sensitivity, specificity, and AUC-ROC, comparing with SVM, decision trees, and XGBoost.

Main Results:

• The proposed DL model achieved high classification accuracy for pneumonia, TB, and COVID-19 from chest X-rays.
• The DL approach demonstrated superior performance compared to traditional machine learning methods.
• The model's effectiveness was validated on an independent test set.

Conclusions:

• The DL model shows significant potential for accurate and efficient classification of common respiratory infections via chest X-rays.
• This approach could be deployed as a clinical screening tool, particularly in resource-limited settings.
• Further validation and integration into clinical workflows are warranted.