Computational methods for objective assessment of conjunctival vascularity

Author

Derakhshani, R. ; Saripalle, S.K. ; Doynov, P.

Author_Institution

Dept. of Comput. Sci. Electr. Eng., Univ. of Missouri at Kansas City, Kansas City, MO, USA

fYear

2012

fDate

Aug. 28 2012-Sept. 1 2012

Firstpage

1490

Lastpage

1493

Abstract

Assessment of vascularity of conjunctival has many diagnostic and prognostic applications, thus creation of computational methods for its fast and objective assessment is of importance. Here we provide two different methods for estimation of conjunctiva´s vascularity from color digital images, with our best results showing a correlation coefficient of 0.89 between the predicted and ground truth values using a committee of artificial neural networks.

Keywords

biomedical optical imaging; blood vessels; cancer; eye; image colour analysis; medical image processing; neural nets; artificial neural networks; color digital imaging; computational methods; conjunctival vascularity; correlation coefficient; diagnostic applications; objective assessment; prognostic applications; Arteries; Artificial neural networks; Cities and towns; Humans; Lenses; Training; Conjunctiva; Databases, Factual; Humans; Image Processing, Computer-Assisted; Neural Networks (Computer); Photography; Sclera;

fLanguage

English

Publisher

ieee

Conference_Titel

Engineering in Medicine and Biology Society (EMBC), 2012 Annual International Conference of the IEEE

Conference_Location

San Diego, CA

ISSN

1557-170X

Print_ISBN

978-1-4244-4119-8

Electronic_ISBN

1557-170X

Type

conf

DOI

10.1109/EMBC.2012.6346223

Filename

6346223