Implementation of Stochastic Approach for Vessel and Ridge Studies in Retinopathy of Prematurity Screening

Abstract

The retinopathy of prematurity (ROP) is an ocular pathological disorder of retinal blood vessels in premature infants and low birth weight infants. The medical professional who is taking care of premature infants should know who is at the risk of this disease and its exact severity stage. It is also important to decide when screening must begin and how often these infants need to be examined as disease progression leads to a more severe stage causing blindness. The contrast stretching method has been utilized to enhance the ROP colour image. Then an automatic isotropic undecimated wavelet transform (IUWT) scheme has been proposed to extract the abnormal retinal blood vessel and measure its width and tortuosity. The ridge formation of this pathological disorder has also been extracted by IUWT. The quantitative measurements of mean diameter, standard deviation, tortuosity, length of retinal blood vessel and ridge have been considered and computed to find the exact severity stage of ROP. The proposed methods for ROP stage screening system have been validated through machine vision techniques. This proposed system improves the optimum time utilization for ophthalmologists; ophthalmic technicians can provide exact ROP stage and deliver better accuracy and sensitivity in diagnosis.