Automatic localization of optic disc based on deep learning in fundus images

Di Niu, Peiyuan Xu, Cheng Wan, Jun Cheng, Jiang Liu

Research output: Chapter in Book/Conference proceedingConference contributionpeer-review

19 Citations (Scopus)

Abstract

The optic disc (OD) contains lots of important information in retinal image analysis. Detecting the region of OD correctly is important for subsequent analysis of retinal images. It is challenging to locate the OD precisely due to the various reasons including low image quality or lesions around the OD. In this paper, we propose a cascading localization method based on deep learning with feedback to improve the accuracy of OD localization. The method employs the model of saliency-based visual attention to find the most salient region and implements deep convolution neural network (CNN) to determine whether it contains OD. If a region is classified as non-OD region, we find the next salient region and input it into the CNN to classify. The algorithm ends when the CNN finds a region with OD. The proposed method is evaluated on the ORIGA and MESSIDOR datasets. Our experimental results show that the proposed method achieved significant improvement in detection of OD compared with previous methods.

Original languageEnglish
Title of host publication2017 IEEE 2nd International Conference on Signal and Image Processing, ICSIP 2017
PublisherInstitute of Electrical and Electronics Engineers Inc.
Pages208-212
Number of pages5
ISBN (Electronic)9781538609682
DOIs
Publication statusPublished - 29 Nov 2017
Externally publishedYes
Event2nd IEEE International Conference on Signal and Image Processing, ICSIP 2017 - Singapore, Singapore
Duration: 4 Aug 20176 Aug 2017

Publication series

Name2017 IEEE 2nd International Conference on Signal and Image Processing, ICSIP 2017
Volume2017-January

Conference

Conference2nd IEEE International Conference on Signal and Image Processing, ICSIP 2017
Country/TerritorySingapore
CitySingapore
Period4/08/176/08/17

Keywords

  • Convolution neural network
  • Deep learning
  • Optic disc localization
  • Saliency map

ASJC Scopus subject areas

  • Signal Processing

Fingerprint

Dive into the research topics of 'Automatic localization of optic disc based on deep learning in fundus images'. Together they form a unique fingerprint.

Cite this