Please use this identifier to cite or link to this item: http://hdl.handle.net/10609/139529
Title: Aprendizaje profundo y neumonía: modelo de clasificación de imágenes de rayos-X para una detección más rápida
Author: Sauras Salas, Raquel
Tutor: Rebrij, Romina  
Others: Perez-Navarro, Antoni  
Abstract: Pneumonia is currently a prevalent lung disease and one of the leading causes of death in the world. Without going any further, the current pandemic caused by COVID-19 and its variants has brought us face to face with the reality of the importance of early detection for rapid and effective treatment. The diagnostic tool for pneumonia is usually chest X-rays, due to their speed and cost. They offer less ionizing exposure but also less clarity in the resolution of the image as opacities or diffuse grays appear. In this Master's thesis it has been proposed to design a deep learning model, using the Python language and using TensorFlow and Keras libraries through Google Colab. The model has been generated using a convolutional neural network (CNN) and the proposed accuracy improvement has been proposed through data augmentation. The database used for this project has been extracted from the Kaggle repository and consists of 5856 thoracic radiographs classified according to whether they do not present pneumonia (normal) or present pneumonia (pneumonia virus, pneumonia bacteria). Finally, a web application developed in NextJS and published in AWS has been created to facilitate image classification for the user.
Keywords: pneumonia
thoracic radiographs
deep learning
Document type: info:eu-repo/semantics/masterThesis
Issue Date: 3-Jan-2022
Publication license: http://creativecommons.org/licenses/by-nc-nd/3.0/es  
Appears in Collections:Trabajos finales de carrera, trabajos de investigación, etc.

Files in This Item:
File Description SizeFormat 
rsaurassTFM0122memoria.pdfMemoria del TFM1,89 MBAdobe PDFThumbnail
View/Open