NORMA eResearch @NCI Library

Identification of Pneumothorax in X-ray images using Convolutional neural network

Sharma, Aditya (2020) Identification of Pneumothorax in X-ray images using Convolutional neural network. Masters thesis, Dublin, National College of Ireland.

[img]
Preview
PDF (Master of Science)
Download (1MB) | Preview
[img]
Preview
PDF (Configuration manual)
Download (436kB) | Preview

Abstract

Pneumothorax is a condition in which air gets accumulated in the pleural space of thorax, which lies between chest and lungs. It causes the air which is present in the lungs during breathing to come out of lung and gets trapped between chest and lungs, in the pleural space of chest which causes chest pains, breathing difficulty and can also lead to total collapse of one lung in case of tension pneumothorax. Therefore, this should be diagnosed early so that the treatment could get started soon. Neural networks have proved to be effective in image classification tasks and many researchers have proved that chest anomalies like pneumonia, pneumothorax etc, which are diagnosed by radiologists, can be detected by training a neural network model. In this research, ResNet-50 neural network will be trained on a dataset of chest x-ray images having more than 10,000 images to create a model which would predict the presence of pneumothorax from chest x-ray images.

Item Type: Thesis (Masters)
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
Divisions: School of Computing > Master of Science in Data Analytics
Depositing User: Dan English
Date Deposited: 25 Jan 2021 14:48
Last Modified: 25 Jan 2021 14:48
URI: http://norma.ncirl.ie/id/eprint/4468

Actions (login required)

View Item View Item