NORMA eResearch @NCI Library

Optic Disc and Cup Segmentation in Glaucoma Screening using Mask RCNN

Sharma, Nandita (2020) Optic Disc and Cup Segmentation in Glaucoma Screening using Mask RCNN. Masters thesis, Dublin, National College of Ireland.

[img]
Preview
PDF (Master of Science)
Download (3MB) | Preview
[img]
Preview
PDF (Configuration manual)
Download (1MB) | Preview

Abstract

Glaucoma is a prevalent ocular disease, which leads to irreversible loss in vision because the optic nerves, that are connected directly to the brain gets damaged. Compared to the healthy fundus image, enlargement of an optic cup could be observed by covering a portion of the optic disc in the fundus image of glaucoma. Ophthalmologists believe that it can be treated to some extent if early detection is possible. Several studies have been done so far in this field. However, the detection and segmentation of the optic cup and disc is a challenging task. Therefore, in this paper, a different deep learning approach is adopted to detect and segment the prominent location of optic disc and cup from the fundus image using Mask RCNN. The promising result by Mask-RCNN could be seen in other state-of-art in detecting and segmenting salient objects from images. This work is formulated on high resolution public available RIGA dataset of fundus images comprises of ophthalmologists labeled data. Various performance metrics such as F1 score, Precision, Recall, Accuracy has been analysed in this study.

Item Type: Thesis (Masters)
Subjects: Q Science > QA Mathematics > Electronic computers. Computer science
T Technology > T Technology (General) > Information Technology > Electronic computers. Computer science

Q Science > QA Mathematics > Computer software
T Technology > T Technology (General) > Information Technology > Computer software
Divisions: School of Computing > Master of Science in Data Analytics
Depositing User: Dan English
Date Deposited: 25 Jan 2021 15:04
Last Modified: 25 Jan 2021 15:04
URI: http://norma.ncirl.ie/id/eprint/4469

Actions (login required)

View Item View Item