An Automated Identification of Muscular Atrophy and Muscular Dystrophy Disease in Fetus using Deep Learning Approach

Muscular Atrophy (MA) and Muscular dystrophy (MD) diseases are genetic diseases. These diseases are commonly diagnosed with the help of techniques such as chorionic villus sampling (CVS) and amniocentesis, vitro fertilization (IVF), Intrauterine insemination (IUI) in fetus level. Among these techniques, chorionic villus sampling (CVS) and amniocentesis recommends the diagnosis of muscular dystrophy and muscular atrophy through identification of the patterns that exist in fetus. However, while there is a dearth of information about disease-specific patterns, there are overlaps among the patterns of different diseases. Therefore, Deep learning techniques can be used in the diagnosis of muscular dystrophies, muscular atrophy which enables us to analyze, learn, and predict for the future. In this scenario, the current research paper an automated muscular dystrophy detection and muscular antropy model using Convolutional neural networks (CNN)method and Restricted Boltzmann machines (RBM). These models have been proposed to act as an automated deep learning (DL) model that examines the chorionic villus sampling (CVS) and amniocentesis data.