Prof. Lamiaa Abdallah Ahmed Elrefaei :: Publications:

Lung diseases such as COVID-19 and pneumonia can lead to severe complications, including breathing difficulties, decreased lung function and respiratory failure, which can be life-threatening if not promptly treated. Chest X-ray imaging techniques have proven to be quick, effective and cost-efficient in diagnosing and monitoring these diseases. Additionally, artificial intelligence, particularly through deep learning and machine learning, has shown promising results in detecting various lung diseases, including COVID-19 and pneumonia. This technology’s ability to analyze large datasets rapidly has contributed to reducing the spread of these diseases and has significantly advanced biomedical research in various medical disciplines. In this research paper, we introduced various advanced ensemble techniques as bagging, boosting, stacking and blending with different algorithms, to enhance the performance of our classification models in detecting coronavirus and pneumonia. We specifically focused on combining convolutional neural network (CNN) and vision transformer (ViT) models to create powerful ensemble models. Our objective was to determine the most accurate ensemble technique for diagnosing lung diseases. We assessed their ability to correctly classify chest X-ray images as either COVID-19, pneumonia or normal. The CatBoost model achieved the highest accuracy, F1-score and ROC-AUC score of 99.753%, 99.51% and 99.99%, respectively using the COVID-19 Radiography dataset. The bagging ensemble model achieved the highest accuracy, F1-score and ROC-AUC score of 95.08%, 95.2% and 99.69%, respectively using COVIDx CXR-4. The results indicate that the advanced ensemble techniques can significantly improve the performance of machine-learning models.