CovDNet: A Hybrid Multi - Level Densely Connected Neural Network for Improvised Analysis and Classification of COVID-19 Using Chest CT-Scans

COVID-19, caused by the new coronavirus SARS-Co V-2, has turned into a worldwide health emergency, needing speedy and precise diagnostic techniques. This abstract provides a thorough evaluation of research works focusing on COVID-19 identification using DenseNet, a cutting-edge convolutional neural network architecture. DenseNet is notable for its innovative design, which fosters feature reuse while relieving the vanishing gradient problem and enhancing network information flow. Researchers have created novel ways for COVID-19 identification using medical imaging, such as chest X-rays and CT scans, by harnessing the capabilities of DenseNet. The analyzed studies demonstrate DenseNet's efficiency in recognizing COVID-19-specific patterns and distinguishing them from other lung diseases. These investigations have shown remarkable accuracy, sensitivity, and precision, exceeding established machine learning approaches and even professional radiologists. This research study also highlights the difficulties and constraints experienced while using DenseNet to identify COVID-19. Issues such as dataset quantity, class imbalance, and model decision-making process interpretability are addressed. Furthermore, future research paths and prospective enhancements, such as multi-modal data integration and the development of explainable AI systems, are investigated. The experimental results indicate that the proposed approach achieves high accuracy, sensitivity, and precision in the identification of COVID - 19. The proposed methodology achieved an accuracy of 89.74%, sensitivity of 87.25
^%
, and precision of 79.56%, which outperforms the existing state-of-the-art methods. The proposed approach is robust and can effectively differentiate between COVID-19 positive and negative cases, which is essential for early detection and prompt treatment.