Introducing a Novel Layer in Convolutional Neural Network for Automatic Identification of Diabetic Retinopathy

Khojasteh, P, Aliahmad, B, Poosapadi Arjunan, S and Kumar, D 2018, 'Introducing a Novel Layer in Convolutional Neural Network for Automatic Identification of Diabetic Retinopathy', in Proceedings of the 40th Annual International Conference of the IEEE Engineering in Medicine and Biology Society (EMBC 2018), Honolulu, Hawaii, United States, 18-21 July 2018, pp. 5938-5941.


Document type: Conference Paper
Collection: Conference Papers

Title Introducing a Novel Layer in Convolutional Neural Network for Automatic Identification of Diabetic Retinopathy
Author(s) Khojasteh, P
Aliahmad, B
Poosapadi Arjunan, S
Kumar, D
Year 2018
Conference name EMBC 2018: Learning from the Past, Looking to the Future
Conference location Honolulu, Hawaii, United States
Conference dates 18-21 July 2018
Proceedings title Proceedings of the 40th Annual International Conference of the IEEE Engineering in Medicine and Biology Society (EMBC 2018)
Publisher IEEE
Place of publication United States
Start page 5938
End page 5941
Total pages 4
Abstract Convolutional neural networks have been widely used for identifying diabetic retinopathy on color fundus images. For such application, we proposed a novel framework for the convolutional neural network architecture by embedding a preprocessing layer followed by the first convolutional layer to increase the performance of the convolutional neural network classifier. Two image enhancement techniques i.e. 1- Contrast Enhancement 2- Contrast-limited adaptive histogram equalization were separately embedded in the proposed layer and the results were compared. For identification of exudates, hemorrhages and microaneurysms, the proposed framework achieved the total accuracy of 87.6%, and 83.9% for the contrast enhancement and contrast-limited adaptive histogram equalization layers, respectively. However, the total accuracy of the convolutional neural network alone without the preprocessing layer was found to be 81.4%. Consequently, the new convolutional neural network architecture with the proposed preprocessing layer improved the performance of convolutional neural network.
Subjects Biomedical Engineering not elsewhere classified
Signal Processing
DOI - identifier 10.1109/EMBC.2018.8513606
Copyright notice © 2018 IEEE
ISBN 9781538636473
Versions
Version Filter Type
Citation counts: Scopus Citation Count Cited 0 times in Scopus Article
Altmetric details:
Access Statistics: 8 Abstract Views  -  Detailed Statistics
Created: Thu, 31 Jan 2019, 11:26:00 EST by Catalyst Administrator
© 2014 RMIT Research Repository • Powered by Fez SoftwareContact us