Visualizing the Indicators of Diabetic Retinopathy Learnt by Convolutional Neural Networks

Shikhar Srivastava, Srikanth Prabhu, Sidharth Ramesh, Siddarth Pratapneni, Ashwin Abraham, Sulatha V Bhandary

Research output: Chapter in Book/Report/Conference proceedingConference contribution

1 Citation (Scopus)

Abstract

This study proposes a novel application of visualizing features learnt by convolutional neural networks with the aim to further the understanding of Diabetic Retinopathy. A convolutional neural network is first trained to recognize and classify fundus images of diabetic and non-diabetic patients. The network is then visualized, using a technique of pixel optimization, to discover the features that the trained network looks for to classify the image. Through this novel application of network visualization, we show that critical features for diabetic retinopathy can be re-discovered, leaving great scope for its application in scarcely explored diseases using minimal resources.

Original languageEnglish
Title of host publication2017 IEEE International Conference on Computational Intelligence and Computing Research, ICCIC 2017
EditorsN. Krishnan, M. Karthikeyan
PublisherInstitute of Electrical and Electronics Engineers Inc.
ISBN (Electronic)9781509066209
DOIs
Publication statusPublished - 05-11-2018
Event8th IEEE International Conference on Computational Intelligence and Computing Research, ICCIC 2017 - Tamilnadu, India
Duration: 14-12-201716-12-2017

Publication series

Name2017 IEEE International Conference on Computational Intelligence and Computing Research, ICCIC 2017

Conference

Conference8th IEEE International Conference on Computational Intelligence and Computing Research, ICCIC 2017
CountryIndia
CityTamilnadu
Period14-12-1716-12-17

All Science Journal Classification (ASJC) codes

  • Signal Processing
  • Artificial Intelligence
  • Computational Theory and Mathematics
  • Computer Science Applications

Fingerprint Dive into the research topics of 'Visualizing the Indicators of Diabetic Retinopathy Learnt by Convolutional Neural Networks'. Together they form a unique fingerprint.

Cite this