Feature extraction and classification of COPD chest X-ray images
by P. Bhuvaneswari; A. Brintha Therese
International Journal of Computer Aided Engineering and Technology (IJCAET), Vol. 12, No. 3, 2020

Abstract: Chronic obstructive pulmonary disease (COPD) is a group of lung disease like emphysema, chronic bronchitis, asthma and some kinds of bronchiectasis. This group of diseases are expected to be one of the major causes of morbidility and the third case of mortality by 2020. If the disease is identified in the early stage itself the survival rate will be increased. In this paper a novel method is proposed to classify the disease COPD in chest X-ray images. Prior to classification essential features are to be extracted. In this regards, some structural features include number of ribs in the chest X-ray, heart shape, diaphragm shape and distance between ribs of the given X-ray image are extracted by means of various image processing techniques. Based on the above said features the input image is classified as normal or COPD with various classifiers include MLC, LDA, neural network, genetic algorithm. The maximum classification accuracy achieved is 97.9%. This work not only ends up with the classification of COPD images, it also enables the medicos to identify the heart disease cardiomegaly.

Online publication date: Thu, 02-Apr-2020

The full text of this article is only available to individual subscribers or to users at subscribing institutions.

 
Existing subscribers:
Go to Inderscience Online Journals to access the Full Text of this article.

Pay per view:
If you are not a subscriber and you just want to read the full contents of this article, buy online access here.

Complimentary Subscribers, Editors or Members of the Editorial Board of the International Journal of Computer Aided Engineering and Technology (IJCAET):
Login with your Inderscience username and password:

    Username:        Password:         

Forgotten your password?


Want to subscribe?
A subscription gives you complete access to all articles in the current issue, as well as to all articles in the previous three years (where applicable). See our Orders page to subscribe.

If you still need assistance, please email subs@inderscience.com