Diabetic retinopathy early detection based on OCT and OCTA feature fusion

Nabila Eladawi, Ahmed Eltanboly, Mohammed Elmogy, Mohammed Ghazal, Luay Fraiwan, Ahmed Aboelfetouh, Alaa Riad, Robert Keynton, Magdi El-Azab, Shlomit Schaal, Ayman El-Baz

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

5 Scopus citations

Abstract

Diabetic retinopathy (DR) is one of the major causes of blindness worldwide. It is a diabetes complication that occurs after the damage of the blood vessels in the light-sensitive tissue in the retina. So, early detection of DR could reduce the severity of the disease and help ophthalmologists in treating and investigating it more efficiently. In this paper, we developed a computer-aided diagnosis (CAD) system that can detect early signs of DR using both optical coherence tomography (OCT) and optical coherence tomography angiography (OCTA) images. Our system is able to segment the blood vessels from two retinal plexuses using OCTA images. Also, it segments twelve different retinal layers from OCT scans. Then, seven different features are extracted from both segmented OCTA plexuses and OCT layers. Finally, these features are fused to generate a comprehensive diagnostic non-invasive tool for detecting early signs of DR. A total number of 76 cases (23 normal and 53 DR) were used in evaluating the performance of the proposed systems. Using 4-fold cross-validation, our proposed system achieved an average accuracy of 100%. These results show the potential of the proposed system.

Original languageEnglish (US)
Title of host publicationISBI 2019 - 2019 IEEE International Symposium on Biomedical Imaging
PublisherInstitute of Electrical and Electronics Engineers Inc.
Pages587-591
Number of pages5
ISBN (Electronic)9781538636411
DOIs
StatePublished - Apr 2019
Event16th IEEE International Symposium on Biomedical Imaging, ISBI 2019 - Venice, Italy
Duration: Apr 8 2019Apr 11 2019

Publication series

NameProceedings - International Symposium on Biomedical Imaging
Volume2019-April
ISSN (Print)1945-7928
ISSN (Electronic)1945-8452

Conference

Conference16th IEEE International Symposium on Biomedical Imaging, ISBI 2019
Country/TerritoryItaly
CityVenice
Period4/8/194/11/19

Keywords

  • CAD
  • DR
  • Feature fusion
  • OCT
  • OCTA

ASJC Scopus subject areas

  • Biomedical Engineering
  • Radiology Nuclear Medicine and imaging

Fingerprint

Dive into the research topics of 'Diabetic retinopathy early detection based on OCT and OCTA feature fusion'. Together they form a unique fingerprint.

Cite this