Robust Intelligent System for COVID-19 Detection using CT-Scan

• Published in: 2023 International Conference Automatics and Informatics (ICAI) pp. 423 - 427
• Main Authors: Al Smadi, Ahmad, Abugabah, Ahed, Al-smadi, Ahmad Mohammad
• Format: Conference Proceeding
• Language: English
• Published: IEEE 05.10.2023
• Subjects: Classification; COVID-19; CT-scans; Data models; Deep Learning; Feature extraction; Medical services; Robustness; Sensitivity; Training
• DOI: 10.1109/ICAI58806.2023.10339084

In the beginning of 2020, the world witnessed the rapid spread of the new coronavirus, COVID-19, affecting millions of people globally. However, at the outset, the availability of corona test kits was scarce, leading researchers to explore alternative detection methods. Among these methods, the COVID-19 detection approach using CT-scans emerged, and artificial intelligence (AI)-based solutions proved to offer superior outcomes. Despite the potential of AI-based models, the issue of overfitting arose, significantly impacting model performance. In response to this challenge, we present a coherent and cohesive solution in this paper, utilizing a Convolutional Neural Network (CNN)-based approach for accurate classification of COVID-19 vs. non-COVID cases. To enhance the model's robustness, we incorporated data augmentation and batch normalization techniques for regularization. To evaluate the effectiveness of our proposed model, we conducted experiments with four different data splitting ratios (50%-50; 70%-30; 75%-25; 80%-20) for training and testing. As a result, our suggested model achieved an impressive classification accuracy of 98.56% for distinguishing between COVID-19 and non-COVID cases. These promising results highlight the efficacy of our CNN-based approach with regularization techniques. Furthermore, we conducted a comparative analysis with other deep learning-based algorithms, and our model consistently outperformed them, demonstrating its superiority in COVID-19 detection. By providing such reliable and accurate results, our proposed model contributes significantly to the ongoing efforts in combating the COVID-19 pandemic and holds the potential to aid healthcare professionals in timely and precise diagnosis.