Segmentation Algorithms for Choroidal OCT Images

Reddy, Lakku Praveen Kumar (2016) Segmentation Algorithms for Choroidal OCT Images. Masters thesis, Indian Institute of Technology Hyderabad.

[img] Text
EE14MTECH11005.pdf
Restricted to Registered users only until 20 July 2019.

Download (4MB) | Request a copy

Abstract

Choroid of the human eye mostly consists of blood vessels, through these vessels it supplies oxygen and nutrition to retina, sclera regions. Blood vessels of choroid are an indication of health of the eye. Opthamologist will observe the structural changes in the choroid through Optiacl Coherence Tomography (OCT) scans. To assist the ophthamologist in the diagnosis, we present an automated algorithm for detection of choroidal blood vessels. We are proposing two methods. One method is simple, finding the region of interest and applying Laplacian of Gaussian. In the second method we formulated this segmentation problem as a binary classification problem. Classification is done by estimating the probability density functions of choroidal vessel region and stromal region by using mixture of gaussians.

[error in script]
IITH Creators:
IITH CreatorsORCiD
Item Type: Thesis (Masters)
Uncontrolled Keywords: Choroid, Optical Coherence Tomography,Gaussian Mixture Model,TD570
Subjects: Physics > Electricity and electronics
Divisions: Department of Electrical Engineering
Depositing User: Library Staff
Date Deposited: 25 Jul 2016 06:19
Last Modified: 25 Jul 2016 06:19
URI: http://raiith.iith.ac.in/id/eprint/2554
Publisher URL:
Related URLs:

Actions (login required)

View Item View Item
Statistics for RAIITH ePrint 2554 Statistics for this ePrint Item