Deep-GlaucomaNet: A Deep Learning based Approach for Glaucoma Detection in Fundus Images

Santosh Kumar Sharma, Debendra Muduli

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

Abstract

Glaucoma is a chronic eye disease that is a leading cause of irreversible vision loss worldwide. Early and accurate classification of glaucoma is crucial for timely intervention and effective management. In this study, we propose a novel glaucoma classification model named as Deep-GlaucomaNet based on advanced deep learning techniques to achieve high accuracy and reliability. Here, the GoogLeNet model has been employed as a base model. The last four layers of the GoogLeNet were replaced with the customized 15 layers. The augmentation technique has been applied for avoiding overfitting is-sues. The performance of the model is evaluated with two activation functions ReLU and Swish. The proposed model earns better classification accuracy 94.39% on the G1020 dataset and represents its perfection over other existing models.

Original languageEnglish
Title of host publication2023 14th International Conference on Computing Communication and Networking Technologies, ICCCNT 2023
PublisherInstitute of Electrical and Electronics Engineers Inc.
ISBN (Electronic)9798350335095
DOIs
Publication statusPublished - 2023
Externally publishedYes
Event14th International Conference on Computing Communication and Networking Technologies, ICCCNT 2023 - Delhi, India
Duration: 6 Jul 20238 Jul 2023

Publication series

Name2023 14th International Conference on Computing Communication and Networking Technologies, ICCCNT 2023

Conference

Conference14th International Conference on Computing Communication and Networking Technologies, ICCCNT 2023
Country/TerritoryIndia
CityDelhi
Period6/07/238/07/23

Keywords

  • Batch normalization (BN)
  • CNN
  • Computer aided diagnosis (CAD)
  • Deep learning (DL)
  • Deep neural network (DNN)
  • Glaucomatous optic disc changes (GON)
  • Machine learning (ML)
  • Optical coherence tomography (OCT)

Fingerprint

Dive into the research topics of 'Deep-GlaucomaNet: A Deep Learning based Approach for Glaucoma Detection in Fundus Images'. Together they form a unique fingerprint.

Cite this