Detection of Anomalies in Fetus using Convolution Neural Network

Full Text (PDF, 831KB), PP.77-86

Views: 0 Downloads: 0


Bindiya H.M 1,* Chethana H.T 1 Pavan Kumar S.P 1

1. Vidyavardhaka College of Engineering, Mysuru, India

* Corresponding author.


Received: 31 Jul. 2018 / Revised: 5 Aug. 2018 / Accepted: 12 Aug. 2018 / Published: 8 Nov. 2018

Index Terms

Fetal Anomalies, Ultrasound Scanning, CNN, KNN


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.

Cite This Paper

Bindiya H.M, Chethana H.T, Pavan Kumar S.P, "Detection of Anomalies in Fetus using Convolution Neural Network", International Journal of Information Technology and Computer Science(IJITCS), Vol.10, No.11, pp.77-86, 2018. DOI:10.5815/ijitcs.2018.11.08


[1]Gustavo Carneiro, Bogdan Georgescu. Detection and Measurement of Fetal Anatomies from Ultrasound Images using a Constrained Probabilistic Boosting Tree: [J].IEEE Transactions on Medical Imaging, 2008, 27(9):1342 - 1355.
[2]Shamya Shetty, Dr. Jose Alex Mathew. Analysis of Fetal Development Using Ultrasound Images: IOSR Journal of VLSI and Signal Processing, 2016, 6(3): 2319 – 4197.
[3]Faezeh Marzbanrad, Yoshitaka Kimura, et al. Application of automated fetal valve motion identification to investigate fetal heart anomalies: [J].IEEE Healthcare Innovation Conference (HIC), 2014.
[4]Ahsan H Khandoker, Yoshitaka Kimura. Identifying fetal heart anomalies using fetal ECG and Doppler cardiogram signals: [J].IEEE Computing in Cardiology, 2010.
[5]D.Escalona-Vargas C.L.Lowery. Recurrence quantification analysis applied to fetal heart rate variability with fetal magnetocardiography: [J].IEEE 22nd International Conference on Digital Signal Processing (DSP), 2017.
[6]Christian F. Baumgartner, Konstantinos Kamnitsas. SonoNet: Real-Time Detection and Localisation of Fetal Standard Scan Planes in Freehand Ultrasound: [J].IEEE Transactions on Medical Imaging, 2017,36(11): 2204– 2215.
[7]AH Khandoker, Y Kimura. Automated identification of abnormal fetuses using fetal ECG and doppler ultrasound signals: [J].IEEE 2009 36th Annual Computers in Cardiology Conference (CinC), 2009.
[8]G. Malathi, V. Shanthi. Wavelet Based Features for Ultrasound Placenta Images Classification: [J].IEEE 2009 Second International Conference on Emerging Trends in Engineering & Technology, 2009.
[9]What can ultrasounds show?
[10]Convolutional Neural Networks
[11]Beginners guide to deep learning
[12]Convolutional Neural Network
[13]Introduction to k-nearest algorithm
[14]Kajal Hedau, Nikita Dhakare. Patient Queue Management System: International Journal of Scientific Research in Computer Science, Engineering and Information Technology, 2018, 3(3): 2456-3307.