Please use this identifier to cite or link to this item:
http://hdl.handle.net/10609/132630
Title: | Screening Chest X-rays for Covid-19 with Deep Learning |
Author: | Robert Gill, Eric |
Tutor: | Nunez do Rio, Joan M |
Others: | Arnedo-Moreno, Joan |
Abstract: | The novel Coronavirus has caused a global pandemic with high economic and social costs. The emergent nature of the Coronavirus' associated disease, Covid-19, found many nations ill-prepared to control its spread, leading to high rates of infection and strain on health systems. Rapid detection and the subsequent quarantine of infected people is the most effective measure against the spread of the virus outside of vaccination. Diagnosis is generally carried out by Reverse Polymer or antigens tests which can be expensive and not always readily available. These methods require specialised staff and physical contact with the patient, as well as time to process results. X-ray machines are available in hospitals across the world in countries of nearly all economic situations. Radiography has been used in many screening and diagnostic use cases and there is wide-spread investigation into its applicability in the Coronavirus pandemic. This project investigates the viability of employing Convolutional Neural Networks to screen radiographic images of lungs for symptoms of Covid-19. X-rays are massively available, economical, and non-invasive. The results show that Convolutional Neural Networks can classify x-ray images into Covid, Normal and Viral Pneumonia classes with high levels of Precision and Recall. |
Keywords: | COVID-19 X-rays Convolutional Neural Network |
Document type: | info:eu-repo/semantics/bachelorThesis |
Issue Date: | 13-Jun-2021 |
Publication license: | http://creativecommons.org/licenses/by-nc-nd/3.0/es/ |
Appears in Collections: | Bachelor thesis, research projects, etc. |
Files in This Item:
File | Description | Size | Format | |
---|---|---|---|---|
egill31TFG0621memory.pdf | Memory of TFG | 2 MB | Adobe PDF | View/Open |
egill31TFG0621presentation.pdf | Presentation of TFG | 1,47 MB | Adobe PDF | View/Open |
Share:
This item is licensed under a Creative Commons License