Investigations on ROI selection for liver classification

Author

Singh, Monika ; Singh, Sushil ; Gupta, Swastik

Author_Institution

EIED, Thapar Univ., Patiala, India

fYear

2014

fDate

4-7 May 2014

Firstpage

1

Lastpage

6

Abstract

In medical imaging a Region of Interest (ROI) is a sub part of an image, which contains the vital information related to the diagnosis. Since an ROI is used as a `representative´ of the image, and all further computations and diagnosis depends upon the ROI, therefore, it is very crucial to select an appropriate image area as ROI. Further, the use of an ROI will reduce the computational time to extract the features from sub part rather than from the whole image. This paper investigates the importance of location, shape and size of the ROI for liver tissue characterization. The impact of ROI has been analyzed through texture features extracted from that ROI, and subsequently the experimental analysis for selection of ROI is presented.

Keywords

biological tissues; feature extraction; feature selection; image classification; image texture; liver; medical image processing; ROI texture feature extraction; image representation; liver tissue characterization; liver tissue classification; medical imaging; region-of-interest selection; Biomedical imaging; Feature extraction; Lesions; Liver diseases; Shape; Ultrasonic imaging;

fLanguage

English

Publisher

ieee

Conference_Titel

Electrical and Computer Engineering (CCECE), 2014 IEEE 27th Canadian Conference on

Conference_Location

Toronto, ON

ISSN

0840-7789

Print_ISBN

978-1-4799-3099-9

Type

conf

DOI

10.1109/CCECE.2014.6900942

Filename

6900942