Detection of hemorrhage in retinal images using linear classifiers and iterative thresholding approaches based on firefly and particle swarm optimization algorithms

Abstract

We propose a novel iterative thresholding approach based on firefly and particle swarm optimization tobe used for the detection of hemorrhages, one of the signs of diabetic retinopathy disease. This approach consists ofthe enhancement of the image using basic preprocessing methods, the segmentation of vessels with the help of Gaborand Top-hat transformation for the removal of the vessels from the image, the determination of the number of regionswith hemorrhages and pixel counts in these regions using firefly algorithm (FFA) and particle swarm optimizationalgorithm (PSOA)-based iterative thresholding, and the detection of hemorrhages with the help of a support vectormachine (SVM) and linear regression (LR)-based classifier. In the preprocessing step, color space selection, brightnessand contrast adjustment, and adaptive histogram equalization are applied to enhance retinal images, respectively. In thestep of segmentation, blood vessels are detected by using Gabor and Top-hat transformations and are removed from theimage to avoid confusion with hemorrhagic regions in the retinal image. In the iterative thresholding step, the numberof hemorrhagic regions and pixel counts in these regions are determined by using an iterative thresholding approach thatgenerates different thresholding values with the FFA/PSOA. In the classification step, the hemorrhagic regions and pixelcounts obtained by the iterative thresholding are used as inputs in the LR/SVM-based classifier. PSOA-based iterativethresholding and the SVM classifier achieved 96.7% sensitivity, 91.4% specificity, and 94.1% accuracy for hemorrhagedetection. Finally, the experiments show that the correct classification rates and time performances of the PSOA-basediterative thresholding algorithm are better than those of the FFA in hemorrhage detection. In addition, the proposedapproach can be used as a diagnostic decision support system for detecting hemorrhages with high success rate.