TY - GEN
T1 - High-Performance Optic Disc Segmentation Using Convolutional Neural Networks
AU - Mohan, Dhruv
AU - Harish Kumar, J. R.
AU - Sekhar Seelamantula, Chandra
N1 - Publisher Copyright:
© 2018 IEEE.
Copyright:
Copyright 2019 Elsevier B.V., All rights reserved.
PY - 2018/8/29
Y1 - 2018/8/29
N2 - 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, MESSI-DOR, 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.
AB - 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, MESSI-DOR, 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.
UR - http://www.scopus.com/inward/record.url?scp=85062902115&partnerID=8YFLogxK
UR - http://www.scopus.com/inward/citedby.url?scp=85062902115&partnerID=8YFLogxK
U2 - 10.1109/ICIP.2018.8451543
DO - 10.1109/ICIP.2018.8451543
M3 - Conference contribution
AN - SCOPUS:85062902115
T3 - Proceedings - International Conference on Image Processing, ICIP
SP - 4038
EP - 4042
BT - 2018 IEEE International Conference on Image Processing, ICIP 2018 - Proceedings
PB - IEEE Computer Society
T2 - 25th IEEE International Conference on Image Processing, ICIP 2018
Y2 - 7 October 2018 through 10 October 2018
ER -