Designing an Improved Deep Learning-based Model for COVID-19 Recognition in Chest X-ray Images: A Knowledge Distillation Approach

The COVID-19 pandemic has had a significant impact on society, necessitating accurate identification and suitable medical treatment. This study addresses two primary objectives: reducing computational costs for running the model on embedded devices, mobile devices, and conventional computers and improving the model's performance relative to existing methods for high-performance and accurate medical recognition. To achieve these goals, we utilized two neural networks, VGG19 and ResNet50V2, for improved feature extraction from the dataset. Consequently, the semantic features supplied by these networks were combined in a fully connected classifier layer to achieve satisfactory classification results for normal and COVID-19 cases. In addition, MobileNetV2, which is effective on mobile and embedded devices, was adopted to reduce computational demands. Furthermore, knowledge distillation was used to transfer information from the teacher networks (ResNet50V2 and VGG19) to the student network (MobileNetV2), improving its performance in COVID-19 identification. Pre-trained networks and fivefold cross-validation were used to evaluate the proposed method. The model achieved an accuracy of 98.8% and an F1 score of 99.1% in detecting infectious and normal cases. These results demonstrate the superior performance of our approach. The student model is suitable for conventional computers, embedded systems, and clinical experts' cell phones, with acceptable accuracy and F1 score using cross-validation. Our method provides a cost-effective solution for COVID-19 identification, enabling wider accessibility and accurate diagnosis. Moreover, the proposed method outperforms previous works by improving accuracy, F1 score, and other related metrics by at least 1%.