Retinal images are nowadays widely used to diagnose many diseases, for example diabetic retinopathy. In our work, we propose the algorithm for the screening application, which identifies the patients with such severe diabetic complication as diabetic retinopathy is, in early phase. In the application we use the patient’s fundus photography without any additional examination by an ophtalmologist. After this screening identification, other examination methods should be considered and the patient’s follow-up by a doctor is necessary. Our application is composed of three principal modules including fundus image preprocessing, feature extraction and feature classification. Image preprocessing module has the role of luminance normalization, contrast enhancement and optical disk masking. Feature extraction module includes two stages: bright lesions candidates localization and candidates feature extraction. We selected 16 statistical and structural features. For feature classification, we use multilayer perceptron (MLP) with one hidden layer. We classify images into two classes. Feature classification efficiency is about 93 percent.
Keywords
- diabetic retinopathy
- fundus images
- automatic diagnostic and screening
- machine learning
- neural networks
Probabilistic three-phase power flow in a distribution system applying the pseudo-inverse and cumulant method Spectral and energy efficiency trade-off in massive MIMO systems using multi-objective bat algorithm Observability, controllability and stability of a nonlinear RLC circuit in form of a Duffing oscillator by means of theoretical mechanical approach Influence of temperature on detectable minimum rotation rate in i-FOGs using Er-doped SFSs Smart DTC algorithm with automatic torque ripple adjustment Decentralized controlled charging and vehicle-to-grid solution for voltage regulation in low voltage distribution systems A novel principal component-based virtual sensor approach for efficient classification of gases/odors Multi-UAV integrated HetNet for maximum coverage in disaster management Investigation of field free region formed by dual Halbach array for focused magnetic hyperthermia Study of subjective and objective quality assessment of infrared compressed images