Detecção e classificação de pneumonia com base na análise de imagens de radiografia torácica: caso de estudo - Hospital Central de Maputo

Abstract

Pneumonia is one of the leading causes of death in children under five years old and the elderly in Mozambique. The lack of adequate vaccination, malnutrition, and limited access to quality healthcare are factors that contribute to the high incidence and mortality rates associated with pneumonia in the country. Additionally, socioeconomic challenges such as poverty and lack of basic sanitation also increase the risk of infection. The research in this study focuses on the detection and classification of pneumonia using Artificial Intelligence, aiming to propose an alternative mechanism for diagnosing the disease. The research involved a comprehensive literature review on pneumonia, image processing techniques, and machine learning algorithms. The data used in the study were obtained from a publicly available dataset of chest X-ray images. The methodology involved feature extraction from the images, training and evaluation of classification models. The results obtained demonstrated promising accuracy in differentiating between viral and bacterial pneumonia. The use of Machine Learning in image processing achieved an accuracy of 88%. These results are promising and reveal that the proposed model has the potential to assist healthcare professionals in early and accurate diagnosis of pneumonia, contributing to better clinical outcomes and a more effective approach to disease treatment.