A comparative study on preprocessing techniques in diabetic retinopathy retinal images: Illumination correction and contrast enhancement

Abstract

To investigate the effect of preprocessing techniques including contrast enhancement and illumination correction on retinal image quality, a comparative study was carried out. We studied and implemented a few illumination correction and contrast enhancement techniques on color retinal images to find out the best technique for optimum image enhancement. To compare and choose the best illumination correction technique we analyzed the corrected red and green components of color retinal images statistically and visually. The two contrast enhancement techniques were analyzed using a vessel segmentation algorithm by calculating the sensitivity and specificity. The statistical evaluation of the illumination correction techniques were carried out by calculating the coefficients of variation. The dividing method using the median filter to estimate background illumination showed the lowest Coefficients of variations in the red component. The quotient and homomorphic filtering methods after the dividing method presented good results based on their low Coefficients of variations. The contrast limited adaptive histogram equalization increased the sensitivity of the vessel segmentation algorithm up to 5% in the same amount of accuracy. The contrast limited adaptive histogram equalization technique has a higher sensitivity than the polynomial transformation operator as a contrast enhancement technique for vessel segmentation. Three techniques including the dividing method using the median filter to estimate background, quotient based and homomorphic filtering were found as the effective illumination correction techniques based on a statistical evaluation. Applying the local contrast enhancement technique, such as CLAHE, for fundus images presented good potentials in enhancing the vasculature segmentation.

Evolution of optic nerve photography for glaucoma screening: a review

“…Disc edge detection has been further refined by PPA elimination techniques . Image preprocessing techniques such as blood vessel extraction, illumination normalization and contrast improvement have further improved disc segmentation …”

“…62 Image preprocessing techniques such as blood vessel extraction, illumination normalization and contrast improvement have further improved disc segmentation. 63 Optic cup segmentation is significantly more difficult than disc segmentation. This is due to a high density of blood vessels, more subtle colour intensity changes between the cup and the neuroretinal rim and anomalous contours due to glaucomatous damage (i.e.…”

New grading criterion for retinal haemorrhages in term newborns based on deep convolutional neural networks

“…Similar procedures were applied for the BV and OD segmentation networks. We pre‐processed the images by applying a Gaussian filter …”

“…We pre-processed the images by applying a Gaussian filter. [27][28][29] All the three deep neural networks were implemented in Pytorch and evaluated on a graphic processing unit cluster with 10 Nvidia GeForce GTX 1080 Tis. In training the networks, we applied stochastic gradient descent with a momentum of 0.9, weight decay of 5 × 10 −3 , learning rate of 0.005, and decay rate of 0.96.…”

Image processing methods for computer-aided screening for disease

“…In CAD systems with fundus retinal imaging techniques like histogram equalization (Sopharak et al 2008), color remapping (Marrugo and Millán 2011) or contrast enhancement (Rasta et al 2015) have been used to pre-process the images. But when the quality is too low sometimes is better strategy to discard the image because, even with the application of enhancement techniques, an accurate classification is not possible.…”