Detection of anomalies in fetus using convolution neural network

Parental diagnosis is required during mid-pregnancy period from 18-22 weeks in order to know the well-being of the fetus. This diagnosis is usually done through ultrasound scanning. Ultrasound scanning which is also called as sonogram, is an ultrasound based medical imagining technique used to envision the fetus and its development during the gestation period. If there is an abnormality in the diagnosed fetus then the parents and the doctors can do emergency parental care. Anomalies in Fetus occur before birth. Detecting fetal anomalies is a difficult task since it needs expertise and also requires a considerable amount of time, which will not be convenient at an emergency situation. In order to improve the diagnosis accuracy and to reduce the diagnosis time, it has become a demanding issue to develop an efficient and reliable medical decision support system. In this paper we present machine learning approach, such as convolution neural network which is most commonly applied to examine visual pretense. The main motive behind using CNN is due to their accuracy, fewer memory requirements and better training of images. This approach have shown great potential to be applied in the development of medical decision support system for Fetal anomalies which need immediate care.