COVID-19 Classification Based on Deep Convolution Neural Network Over a Wireless Network.

Area of Science:

• Medical Imaging
• Artificial Intelligence
• Wireless Communication

Background:

• The global spread of COVID-19 necessitates rapid and accurate diagnostic tools.
• Chest X-rays are a common imaging modality for COVID-19 detection.
• Deep Convolution Neural Networks (DCNNs) show promise for image-based disease classification.

Purpose of the Study:

• To develop and evaluate a wireless communication and DCNN system for detecting COVID-19 from X-ray images.
• To compare different modulation techniques for efficient wireless transmission of medical images.
• To optimize DCNN hyperparameters for improved classification performance.

Main Methods:

• A DCNN architecture with deep feature extraction and classification layers was proposed.
• Hyperparameters including optimization algorithm, learning rate, mini-batch size, and epochs were tuned.
• Wireless communication aspects, including modulation techniques, were analyzed for reliability and bandwidth efficiency.
• Performance was evaluated using metrics like accuracy, specificity, and Area Under the Curve (AUC).

Main Results:

• The proposed DCNN scheme outperformed existing pre-trained networks.
• The system achieved high diagnostic accuracy (97.8%), specificity (98.5%), and AUC (98.9%).
• Optimized hyperparameters significantly contributed to the model's effectiveness.

Conclusions:

• The developed wireless DCNN system offers a reliable and efficient method for rapid COVID-19 diagnosis using X-ray images.
• The study highlights the potential of AI and wireless technology in combating infectious disease outbreaks.
• Further research can explore integration into clinical workflows for real-time diagnostics.