Investigation on chromosomal anomaly detection and syndrome classification in fetal images using novel neural network computing techniques

Abstract

Common terminology can sometimes be confusing when used to describe fetal infections in ultrasound images. In the modern era of medical technology, improved diagnosis and decision making has been focused on by many researchers. The prenatal diagnostic rate was changing from country to country with the available equipment and differences in monitoring. Besides, most of the research works were focused to diagnose fetal abnormalities in the ultrasound image. One of the ultimate goals of an imaging modality is to improve accuracy and reduce the time of diagnosis. This research work presents a computerized method of the syndrome and chromosomal anomaly detection parameters such as Nuchal Translucency thickness, Nasal bone measurement and Crown ramp length estimation by using Conditionally Rooted Neural Network (CRNN) with Wavelet filter and Reverse Folded Deep Neural Network (RFDNN). The proposed solution for a computerized scheme of Chromosomal anomaly recognition and classification of Chromosomal abnormality such as Trisomy (T) T-13, T-18 and T-21(Patau, Edwards and Down syndrome) is Conditionally Rooted Neural Network (CRNN) with Wavelet Filter. CRNN is used to estimate the chromosomal anomaly features separation from fetal provisions. The clear template of feature estimation from the first-trimester fetus of ultrasound images will be used to train the CRNN. The software has successfully identified and classified the region of the chromosomal anomaly. The evaluations show that CRNN technique can attain good denoising and classification performance in comparison with existing methods. In this experiment, the results indicate that our proposed method can detect and classify the trisomy factors measurement from the ultrasound image regions precisely and robustly against speckle noise. The classification of fetus ultrasound image datasets was done using CRNN classifier, and the accuracy of classification was found to be a highly efficient resolution for Chromosomal anomaly detection. The Reverse folded deep learning technique has turned into the absolute, most well-known strategy to train systems. This technique is rehashed for all the training designs toward the finish of every cycle. Test examples are exhibited to Deep Neural Network (DNN) and the characterization execution of DNN is assessed. There are various stages of classification of fetus image as pre-processing, feature extraction, similarity measure and RFDNN classification. newline