Ultrasonic Detection of Down Syndrome Using Multiscale Quantiser with Convolutional Neural Network

Abstract

Down Syndrome is a genetic condition that occurs when there is an extra copy of a chromosome 21 in the newly formed fetus. EIF is observed as one of the possible symptoms of DS. But in comparison to the other symptoms like nasal bone hypoplasia, increased thickness in the nuchal fold, EIF is very much less prone to DS. Hence, recommending the pregnant women with EIF to undergo the diagnostic process like amniocentesis, CVS and PUBS is not always a right choice as these diagnostic processes suffer serious drawbacks like miscarriage, uterine infections. This chapter “Ultrasonic Detection of Down Syndrome Using Multiscale Quantiser With Convolutional Neural Network” presents a new ultrasonic method to detect EIF that can cause DS. Ultrasonic Detection of Down Syndrome Using Multiscale Quantiser with Convolutional Neural Network entails two stages namely i) training phase and ii) testing phase. Training phase aims at learning the features of EIF that can cause DS whereas testing phase classifies the EIF into DS positive or DS negative based on the knowledge cluster formed during the training phase. A new algorithm Multiscale Quantiser with the convolutional neural network is used in the training phase. Enhanced Learning Vector Classifier is used in the testing phase to differentiate the normal EIF from EIF causing DS. The performance of the proposed system is analysed in terms of sensitivity, accuracy and specificity.