Detection of Diabetic Retinopathy Using Extracted 3D Features from OCT Images.
Mahmoud ElgafiAhmed SharafeldeenAhmed ElnakibAhmed ElgarayhiNorah Saleh AlghamdiMohammed SallahAyman S El-BazPublished in: Sensors (Basel, Switzerland) (2022)
Diabetic retinopathy (DR) is a major health problem that can lead to vision loss if not treated early. In this study, a three-step system for DR detection utilizing optical coherence tomography (OCT) is presented. First, the proposed system segments the retinal layers from the input OCT images. Second, 3D features are extracted from each retinal layer that include the first-order reflectivity and the 3D thickness of the individual OCT layers. Finally, backpropagation neural networks are used to classify OCT images. Experimental studies on 188 cases confirm the advantages of the proposed system over related methods, achieving an accuracy of 96.81%, using the leave-one-subject-out (LOSO) cross-validation. These outcomes show the potential of the suggested method for DR detection using OCT images.
Keyphrases
- optical coherence tomography
- diabetic retinopathy
- optic nerve
- loop mediated isothermal amplification
- neural network
- label free
- real time pcr
- editorial comment
- public health
- healthcare
- type diabetes
- metabolic syndrome
- adipose tissue
- machine learning
- risk assessment
- solar cells
- health information
- weight loss
- sensitive detection
- drug induced