Authors - Valeria Alexandra Yunga Manzanillas, Pablo Andres Figueroa Juca, Nelson Oswaldo Piedra Pullaguari Abstract - In the digital era, the global emergence of COVID-19 has necessitated the development of transformative technology to redefine how we interact with and manage public health crises. To effectively slow mortality rates, this work emphasizes the critical requirement for accurate and rapid diagnostic methods that enable early-stage disease detection. Drawing on the necessity for more efficient systems, this paper proposes a high-fidelity diagnostic framework utilizing Convolutional Neural Networks (CNN), Deep Neural Networks (DNN), and Transfer Learning algorithms. Implemented through a TensorFlow-based 3-class classification strategy, the system was evaluated using a dataset of 817 chest X-ray images (comprising COVID-19, pneumonia-affected, and normal images). The experimental results yielded accuracies of 93.29% for the CNN, 92.68% for the DNN, and a superior 97.56% for the Transfer Learning approach, which outperforms the state of the art methods. These results demonstrate that such high-fidelity computational models provide the conceptual clarity and robustness needed to revolutionize traditional diagnostic methods. By providing instant feedback and a meaningful interpretation of complex medical imagery, the proposed system allows clinical practitioners to achieve precise detections in significantly less time.
Open Zoom