Fundus images analysis using deep features for detection of exudates, hemorrhages and microaneurysms

Khojasteh, P, Aliahmad, B and Kumar, D 2018, 'Fundus images analysis using deep features for detection of exudates, hemorrhages and microaneurysms', BMC Ophthalmology, vol. 18, no. 1, pp. 1-13.

Document type: Journal Article
Collection: Journal Articles

Attached Files
Name Description MIMEType Size
n2006088801.pdf Published Version application/pdf 4.24MB
Title Fundus images analysis using deep features for detection of exudates, hemorrhages and microaneurysms
Author(s) Khojasteh, P
Aliahmad, B
Kumar, D
Year 2018
Journal name BMC Ophthalmology
Volume number 18
Issue number 1
Start page 1
End page 13
Total pages 13
Publisher BioMed Central
Abstract Background: Convolution neural networks have been considered for automatic analysis of fundus images to detect signs of diabetic retinopathy but suffer from low sensitivity. Methods: This study has proposed an alternate method using probabilistic output from Convolution neural network to automatically and simultaneously detect exudates, hemorrhages and microaneurysms. The method was evaluated using two approaches: patch and image-based analysis of the fundus images on two public databases: DIARETDB1 and e-Ophtha. The novelty of the proposed method is that the images were analyzed using probability maps generated by score values of the softmax layer instead of the use of the binary output. Results: The sensitivity of the proposed approach was 0.96, 0.84 and 0.85 for detection of exudates, hemorrhages and microaneurysms, respectively when considering patch-based analysis. The results show overall accuracy for DIARETDB1 was 97.3% and 86.6% for e-Ophtha. The error rate for image-based analysis was also significantly reduced when compared with other works. Conclusion: The proposed method provides the framework for convolution neural network-based analysis of fundus images to identify exudates, hemorrhages, and microaneurysms. It obtained accuracy and sensitivity which were significantly better than the reported studies and makes it suitable for automatic diabetic retinopathy signs detection.
Subject Biomedical Engineering not elsewhere classified
Signal Processing
Keyword(s) Convolutional neural networks
Deep learning
Diabetic retinopathy
Fundus image analysis
Image processing
DOI - identifier 10.1186/s12886-018-0954-4
Copyright notice © The Author(s). 2018 Open Access This article is distributed under the terms of the Creative Commons Attribution 4.0 International License (
ISSN 1471-2415
Version Filter Type
Citation counts: TR Web of Science Citation Count  Cited 11 times in Thomson Reuters Web of Science Article | Citations
Scopus Citation Count Cited 0 times in Scopus Article
Altmetric details:
Access Statistics: 29 Abstract Views, 49 File Downloads  -  Detailed Statistics
Created: Thu, 31 Jan 2019, 11:26:00 EST by Catalyst Administrator
© 2014 RMIT Research Repository • Powered by Fez SoftwareContact us