The University of Southampton
University of Southampton Institutional Repository

Emphysema diagnoses in lungs using medical imaging methods

Emphysema diagnoses in lungs using medical imaging methods
Emphysema diagnoses in lungs using medical imaging methods
Chronic Obstructive Pulmonary Disease (COPD) refers to a group of diseases of the lungs which cause narrowing of the airways, leading to a limitation of the flow of air in to and out of the lungs. Ultimately, this will manifest itself as a shortness of breath. In current clinical practice, COPD is diagnosed by spirometry. The disease leads to impaired lung function and considerable disability, particularly among the elderly population. By 2020, it is predicted that COPD will become the third leading cause of death worldwide. This death rate is even higher in large cities such Tehran. COPD is caused by the ingress of toxic particles into the lung which in some cases results in an abnormal inflammatory response. In the larger airways, this is known as chronic bronchitis. Deeper within the lungs, the inflammation results in damage to the lung tissue, a condition known as emphysema. The onset of the disease is gradual and tends not to present itself clinically until there has been substantial irreversible airway damage. Early emphysema is difficult to diagnose. Traditional measures of COPD such as spirometry can be near normal or only mildly deranged even in severe cases of emphysema. In this talk, I will present a series of research work undertaken in the University of Southampton by starting with the automatic detection and segmentation of lungs in HRCT images by exploiting statistical prior shape techniques. The statistical prior shape in the variational segmentation of lung is used due to the noise and the faintness of lung features in HRCT images. Our observation shows that with the progression of the disease, the lung texture also changes. I then show how texture analysis based on Gaussian Markov Random fields can be employed to detect the location, extent and the severity of the disease inside the lungs even in early stages of emphysema. The areas of lungs affected by emphysema therefore have a different texture in comparison with tissues in a normal lung. The parameters of Gaussian Markov Random fields model are then considered as features to represent the textures of lungs. The histograms of such features demonstrate powerful tools for texture segmentation and recognition and therefore for the detection and diagnosis of emphysema in the lung images. Our methods are tested in large texture databases as well as in our database of lungs obtained from Southampton General Hospital.
Mahmoodi, S.
91ca8da4-95dc-4c1e-ac0e-f2c08d6ac7cf
Mahmoodi, S.
91ca8da4-95dc-4c1e-ac0e-f2c08d6ac7cf

Mahmoodi, S. (2015) Emphysema diagnoses in lungs using medical imaging methods. Keynote Speech: 22nd Iranian Conference on Biomedical Engineering, Tehran, Iran, Islamic Republic of. 25 - 27 Nov 2015.

Record type: Conference or Workshop Item (Other)

Abstract

Chronic Obstructive Pulmonary Disease (COPD) refers to a group of diseases of the lungs which cause narrowing of the airways, leading to a limitation of the flow of air in to and out of the lungs. Ultimately, this will manifest itself as a shortness of breath. In current clinical practice, COPD is diagnosed by spirometry. The disease leads to impaired lung function and considerable disability, particularly among the elderly population. By 2020, it is predicted that COPD will become the third leading cause of death worldwide. This death rate is even higher in large cities such Tehran. COPD is caused by the ingress of toxic particles into the lung which in some cases results in an abnormal inflammatory response. In the larger airways, this is known as chronic bronchitis. Deeper within the lungs, the inflammation results in damage to the lung tissue, a condition known as emphysema. The onset of the disease is gradual and tends not to present itself clinically until there has been substantial irreversible airway damage. Early emphysema is difficult to diagnose. Traditional measures of COPD such as spirometry can be near normal or only mildly deranged even in severe cases of emphysema. In this talk, I will present a series of research work undertaken in the University of Southampton by starting with the automatic detection and segmentation of lungs in HRCT images by exploiting statistical prior shape techniques. The statistical prior shape in the variational segmentation of lung is used due to the noise and the faintness of lung features in HRCT images. Our observation shows that with the progression of the disease, the lung texture also changes. I then show how texture analysis based on Gaussian Markov Random fields can be employed to detect the location, extent and the severity of the disease inside the lungs even in early stages of emphysema. The areas of lungs affected by emphysema therefore have a different texture in comparison with tissues in a normal lung. The parameters of Gaussian Markov Random fields model are then considered as features to represent the textures of lungs. The histograms of such features demonstrate powerful tools for texture segmentation and recognition and therefore for the detection and diagnosis of emphysema in the lung images. Our methods are tested in large texture databases as well as in our database of lungs obtained from Southampton General Hospital.

This record has no associated files available for download.

More information

Accepted/In Press date: 26 November 2015
Published date: 26 November 2015
Venue - Dates: Keynote Speech: 22nd Iranian Conference on Biomedical Engineering, Tehran, Iran, Islamic Republic of, 2015-11-25 - 2015-11-27
Related URLs:
Organisations: Vision, Learning and Control

Identifiers

Local EPrints ID: 382701
URI: http://eprints.soton.ac.uk/id/eprint/382701
PURE UUID: d6950f84-8ac6-4ff9-ad64-aa0eb104234c

Catalogue record

Date deposited: 09 Oct 2015 10:28
Last modified: 11 Dec 2021 07:50

Export record

Contributors

Author: S. Mahmoodi

Download statistics

Downloads from ePrints over the past year. Other digital versions may also be available to download e.g. from the publisher's website.

View more statistics

Atom RSS 1.0 RSS 2.0

Contact ePrints Soton: eprints@soton.ac.uk

ePrints Soton supports OAI 2.0 with a base URL of http://eprints.soton.ac.uk/cgi/oai2

This repository has been built using EPrints software, developed at the University of Southampton, but available to everyone to use.

We use cookies to ensure that we give you the best experience on our website. If you continue without changing your settings, we will assume that you are happy to receive cookies on the University of Southampton website.

×