NORMA eResearch @NCI Library

Development Validation and Detection of Covid–19 using chest Radiography

Shivabasappa Kumbi, Veeresh (2021) Development Validation and Detection of Covid–19 using chest Radiography. Masters thesis, Dublin, National College of Ireland.

[thumbnail of Master of Science]
PDF (Master of Science)
Download (3MB) | Preview
[thumbnail of Configuration manual]
PDF (Configuration manual)
Download (1MB) | Preview


Covid19 or Coronavirus, is a dangerous condition that has put many people’s lives at risk by directly harming the lungs. A medium-sized, coated single-stranded RNA virus. This virus is around 120 nm long and contains one of the biggest RNA genomes. This paper gives a brief overview of the recent development in systems using deep learning methods. Although this method is time consuming and complicated which would take 6-12 hours to get the results. In early infected patients due to low virus loads. This method is prone to show false negative results in fewer cases. The study aims at building a CNN model to detect the virus with explainability. In the field of health care, explainability plays a vital role as this would help the practitioners to make sensitive approach. By the result obtained using this model would be used to lessen the burden on doctors and prioritise the tests and treatments. Earlier models relied on tiny datasets, which might lead to overfitting. We created a model that could produce a binary classification F1-score of 84 percent and a multi-class classification F1-score of 78 percent.

Item Type: Thesis (Masters)
Subjects: Q Science > QA Mathematics > Electronic computers. Computer science
T Technology > T Technology (General) > Information Technology > Electronic computers. Computer science
R Medicine > RB Pathology
Q Science > Q Science (General) > Self-organizing systems. Conscious automata > Machine learning
Divisions: School of Computing > Master of Science in Data Analytics
Depositing User: Tamara Malone
Date Deposited: 11 Mar 2023 12:40
Last Modified: 11 Mar 2023 12:40

Actions (login required)

View Item View Item