Enhancing COVID-19 Diagnosis from Chest X-Ray Images Using Deep Convolutional Neural Networks
Athanasios Kanavos, Orestis Papadimitriou, Manolis Μaragoudakis
Abstract
The rapid spread of the COVID-19 pandemic has presented formidable challenges to healthcare systems worldwide. To address this, researchers have been investigating diverse techniques to aid in the detection and diagnosis of COVID-19 cases. This research paper introduces a novel approach utilizing convolutional neural networks (CNNs) for COVID-19 image classification, leveraging the remarkable success of CNNs in image recognition tasks and their potential in analyzing medical images for disease identification. The results demonstrate the CNN-based approach's impressive accuracy in classifying COVID-19 images, thereby enabling reliable disease detection. The model's robustness is thoroughly assessed using diverse datasets, encompassing images from multiple healthcare facilities and various imaging techniques. Additionally, the research explores transfer learning techniques to enhance the model's ability to generalize effectively, particularly when faced with limited training data.