High-performance optic disc segmentation using convolutional Neural networks

Mohan, Dhruv and Kumar, Harish J R and Seelamantula, Chandra Sekhar (2018) High-performance optic disc segmentation using convolutional Neural networks. In: IEEE International Conference on Image Processing - 2018, 07/10/2018, Athens, Greece.

[img] PDF
1115.pdf - Published Version
Restricted to Registered users only

Download (2MB) | Request a copy

Abstract

We present a framework for robust optic disc segmentation using convolutional neural networks. Optic disc is an important anatomical landmark in the fundus image used for the diagnosis of ophthalmological pathologies. Our objective is to develop a system for unsupervised, early and robust detection of diseases such as glaucoma. We introduce the Fine- Net, which generates a high-resolution optic disc segmentation map (1024�1024) from retinal fundus images. The network is trained on three publicly available datasets, MESSIDOR, DRIONS-DB, and DRISHTI-GS. The proposed framework generalizes well as it performs reliably even on test images that have a significant variability. For experimental evaluation, we perform a five-fold cross-validation and achieve accurate optic disc localization in 99.4% of cases. Moreover, for optic disc segmentation we achieve an average Dice coefficient and Jaccard coefficient of 0.958 and 0.921, respectively.

Item Type: Conference or Workshop Item (Paper)
Uncontrolled Keywords: Convolutional neural networks, fundus image, optic disc, glaucoma, Jaccard coefficient
Subjects: Engineering > MIT Manipal > Electrical and Electronics
Depositing User: MIT Library
Date Deposited: 14 Jul 2018 10:32
Last Modified: 14 Jul 2018 10:32
URI: http://eprints.manipal.edu/id/eprint/151581

Actions (login required)

View Item View Item