Automated COVID-19 Multiclass Detection Using Pretrained Deep Learning Models

Abstract

The rapid spread of COVID-19 has highlighted the urgent need for accurate and efficient diagnostic systems to support clinical decision-making. This study proposes an automated multiclass detection framework for distinguishing COVID-19, pneumonia, and normal cases using chest X-ray images and pretrained deep learning models. Leveraging transfer learning, state-of-the-art convolutional neural networks such as ResNet50, VGG16, and MobileNet are employed to extract high-level features from medical imaging data, reducing the dependency on large annotated datasets and extensive training time. The proposed system involves preprocessing steps including image resizing, normalization, and data augmentation to improve model generalization. The pretrained models are fine-tuned on a labeled chest X-ray dataset to perform three-class classification. Performance evaluation is conducted using standard metrics such as accuracy, precision, recall, F1-score, and confusion matrix analysis. Experimental results demonstrate that the proposed approach achieves high classification accuracy and effectively differentiates between COVID-19, pneumonia, and normal conditions. Furthermore, the use of pretrained models enhances computational efficiency while maintaining robust performance, making the system suitable for real-time clinical applications. This automated framework can assist radiologists in early detection and screening, thereby reducing diagnostic workload and improving patient outcomes. The study emphasizes the potential of deep learning-based solutions in advancing intelligent healthcare systems for infectious disease diagnosis.