Biometric measurement and classification of IUGR using neural networks

The examination of fetal growth is an important cause of perinatal morbidity and mortality. The accurate evaluation of fetal growth during pregnancy is difficult, but recent techniques have improved this important aspect of obstetrics and Gynecology with positive implications for prenatal patients and their babies. Ultrasound measurements play a significant role in obstetrics and Gynecology as an accurate means for the estimation of fetal growth. In this work an automated method is proposed for the Biometric measurement and classification of IUGR, using OpenGL concepts for extracting the feature values and Artificial Neural Network (ANN) model is designed for diagnosis and classification. The features to figure out whether a fetus is normal or abnormal were extracted from the 2D-ultrasound images using OpenGL concepts. The features that are considered for the determination of the IUGR are gestational age (GA), bi-parietal diameter (BPD), abdominal circumference (AC), head circumference (HC), and femur length (FL). These feature values were obtained from 2D-ultrasound image. ANN model designed for the classification is able to distinguish whether fetus is normal or abnormal based on the feature values. Two ANN models, Multilayer Perceptron (MLP) using Back propagation algorithm and Radial Basis Function (RBF) models were studied and used for the diagnosis and classification.