Improved Optic Disc and Cup Segmentation in Glaucomatic Images Using Deep Learning Architecture

HARI MOHAN PANDEY*, Partha Sarathi Mangipudi, Ankur Choudhary

*Corresponding author for this work

Research output: Contribution to journalArticlepeer-review

5 Downloads (Pure)

Abstract

Glaucoma is an ailment causing permanent vision loss but can be prevented through the early detection. Optic disc to cup ratio is one of the key factors for glaucoma diagnosis. But accurate segmentation of disc and cup is still a challenge. To mitigate this challenge, an effective system for optic disc and cup segmentation using deep learning architecture is presented in this paper. Modified Groundtruth is utilized to train the proposed model. It works as fused segmentation marking by multiple experts that helps in improving the performance of the system. Extensive computer simulations are conducted to test the efficiency of the proposed system. For the implementation three standard benchmark datasets such as DRISHTI-GS, DRIONS-DB and RIM-ONE v3 are used. The performance of the proposed system is validated against the state-of-the-art methods. Results indicate an average overlapping score of 96.62%, 96.15% and 98.42% respectively for optic disc segmentation and an average overlapping score of 94.41% is achieved on DRISHTI-GS which is significant for optic cup segmentation.
Original languageEnglish
Article numberMTAP-D-19-04016R5
JournalMultimedia Tools and Applications
Early online date2 Feb 2021
DOIs
Publication statusE-pub ahead of print - 2 Feb 2021

Keywords

  • Glaucoma
  • Fundus Image
  • Convolution Filters
  • Overfitting
  • Optic Disc
  • Optic Cup
  • Deep Learning
  • Machine learning

Fingerprint

Dive into the research topics of 'Improved Optic Disc and Cup Segmentation in Glaucomatic Images Using Deep Learning Architecture'. Together they form a unique fingerprint.

Cite this