Model-based retinal vasculature enhancement in digital fundus image using independent component analysis

Early detection of several diseases related to the retina can be analyzed from fundus images. However, in fundus images the contrast between retinal vasculature and the background is very low. Therefore, analyzing these tiny retinal blood vessels is difficult. Fluorescein angiogram overcomes this imaging problem; however, it is an invasive procedure that leads to other physiological problems. In this work, we develop a fundus image model based on probability distribution function of melanin, haemoglobin and macular pigment to represent melanin, retinal vasculature and macular region, respectively. Enhancement of the low contrast of retinal vasculature in the retinal fundus image is performed by separating the retinal pigments makeup, namely macular pigment, haemoglobin and melanin, using independent component analysis. Independent component image due to haemoglobin obtained exhibits higher contrast retinal blood vessels. Results show that this approach outperforms other non-invasive enhancement methods and can be beneficial for retinal vasculature segmentation. Contrast enhancement factor of 2.62 for a digital retinal fundus image model is achieved. This improvement in contrast reduces the need of applying contrasting agent on patients.