Differentiation of breast abnormalities in infrared images using Riesz and quaternion Hilbert transform based features
by S. Prabha; C.M. Sujatha; S.S. Suganthi
International Journal of Biomedical Engineering and Technology (IJBET), Vol. 19, No. 3, 2015

Abstract: In this paper, an attempt is made to characterise the normal and abnormal breast tissues in infrared images using Riesz and quaternion Hilbert transform based features. Left and right breast regions are separated using midpoint of inframammary folds. Riesz and quaternion based features are extracted from these separated breast tissues. An index based on the extracted features is calculated and proposed for breast tissue analysis. The results show that the features extracted using Riesz and quaternion Hilbert transform are able to discriminate normal and pathological conditions of breast tissues. The extracted features could capture the thermal variations among various abnormalities that are introduced due to varied metabolic conditions. Also, the index calculated using quaternion features is found to be statistically significant in distinguishing normal and carcinoma tissues. Hence, it appears that the proposed index using quaternion features can be useful for efficient diagnosis of breast pathologies.

Online publication date: Wed, 11-Nov-2015

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 Biomedical Engineering and Technology (IJBET):
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