NORMA eResearch @NCI Library

Diagnosis of Covid-19 Pneumonia using Deep Learning and Transfer learning Techniques

Mohite, Paritosh Diwakar (2021) Diagnosis of Covid-19 Pneumonia using Deep Learning and Transfer learning Techniques. Masters thesis, Dublin, National College of Ireland.

[thumbnail of Master of Science]
Preview
PDF (Master of Science)
Download (2MB) | Preview
[thumbnail of Configuration manual]
Preview
PDF (Configuration manual)
Download (2MB) | Preview

Abstract

Coronavirus-2019 (Covid-19) is a deadly virus that has flu symptoms. It originated in a small town called Wuhan (China) and it soon rapidly spread across the world, starting an era of a pandemic. In many countries lockdown was imposed due to this pandemic. This illness causes pneumonia in many situations. As radiography images can be used to monitor pulmonary infections. Therefore, this study helps to detect and analyze chest X-rays by using deep learning models and transfer learning models with the intention that it can provide strong tools to medical doctors and workers to deal with this deadly virus. Specialized deep learning models have been introduced to detect pneumonia, it is assumed that detection of pneumonia will increase the chances of a patient having Covid-19 infection. Furthermore, health tools are suggested for predicting whether a patient is diagnosed with Covid-19, normal and viral pneumonia. From the results of experiment, the CNN model gave an accuracy of 71% and VGG-19 model with 91%, InceptionV3 with 83% and Xception model with 89% of accuracy. By comparing the models CNN model outperforms over other three models. To conclude, these findings suggest that implemented model’s capacity to assess the seriousness of COVID-19 lung infections might be utilized for health as well as medication performance assessment, particularly throughout the critical care unit.

Item Type: Thesis (Masters)
Uncontrolled Keywords: Deep Learning; Transfer Learning; COVID-19; Chest X-ray; Convolution Neutral Network; Pneumonia; Image processing; InceptionV3; VGG-16; Xception
Subjects: Q Science > QA Mathematics > Electronic computers. Computer science
T Technology > T Technology (General) > Information Technology > Electronic computers. Computer science
Q Science > QA Mathematics > Computer software
T Technology > T Technology (General) > Information Technology > Computer software
R Medicine > R Medicine (General)
H Social Sciences > HM Sociology > Information Science > Communication > Medical Informatics
Divisions: School of Computing > Master of Science in Data Analytics
Depositing User: Clara Chan
Date Deposited: 09 Dec 2021 12:43
Last Modified: 09 Dec 2021 12:43
URI: https://norma.ncirl.ie/id/eprint/5193

Actions (login required)

View Item View Item