Author : Deepak Reddy P.A 1
Date of Publication :7th May 2016
Abstract: The prenatal detection of fetal cardiac structure is difficult because of its small size and rapid movements but is important for the early and effective diagnosis of congenital cardiac defects.. Congenital heart disease (CHD) is related to defects in the blood vessels which are located inside the heart or the one which are connecting to heart, that are present by birth or sometimes before birth also when the fetus is developing in the uterus. It brings about a narrowing or stenosis of the valves, or a complete closure that obstructs or impedes forward blood stream. Hence the objectives of this project are to extract prenatal features from the ultrasound images and from clinical diagnosis of the neonates(physiological parameters like diabetes hypertension etc). An initial pre-processing is done to remove noise and enhance the images. An effective K means clustering algorithm is applied to the images to segment the region of interest and eliminating empty clusters is performed . Finally an active appearance model is proposed to detect the fetal heart .and a suitable classifier (Naive Bayes ) designed for the features according to the statistical characteristics, quantitative or qualitative dataset. Feeding a set of features in the training dataset, use these features to develop the classification algorithm to find CHD .
Reference :
-
[1]Reshmi Mariam Reji Jacob1, S.Prabakar and DR.K.Porkumaran3] Fetal Cardiac Structure Detection From Ultrasound SequencesInternational Journal of Instrumentation, Control and Automation (IJICA), ISSN: 2231-1890, Volume-2, Issue-1, 2013
[2 ] Tarun Gangil1, Ranjan Shetty2 Congenital Heart Disease Prediction by Classification based on the Parameters Obtained from Neonates International Journal of fluids and Heat Transfer
[3]N. Maglaveras, S. Maglavera, I. Lekka, I. Chouvarda, and S. A. Netsmart, “Quality home telemedicine services for chronic cardiac disease patients through the interlife platform, Computers in Cardiology, vol. 1, pp. 245–248, 2006.
[4] P. S. Rao, Dr. P Syamsundar Rao “Atrial septal defect a review,” InTech Publications, vol.1, Ed. 1, pp-3-18, 2012, ISBN: 9789535105312.
[5] D. Crowley, “Two-dimensional and M-mode echocardiographic evaluation of fetal arrhythmia,” Clinical Cardiology Publishing, vol. 10, pp. 1–10, 1985.
[6] ] M. Nakao, K. Maeda, R. Haraguchi, K. Kurosaki, K. Kagisaki et al “Cardiovascular modeling of congenital heart disease based on neonatal echocardiographic images.,” IEEE Transactions on Information Technology in Biomedicine, vol. 16, pp. 70–79, 2012.
[7] M. Qian, Y. Sun, Q. Wu, Y. Ma, and Y. Chen, “ Fetal echocardiography in normal fetuses between 11 and 14 gestational age,” Chin. J. Med. Imaging Technol., vol 23, pp. 268–271, 2007.
[8] T.C. Aysal, K.E. Barner, “Rayleigh-maximumlikelihood filtering for speckle reduction of ultrasound images,” IEEE Trans. Medical Imaging,vol.26, pp. 712– 727, 2007.
[9] Y.Deng, Y. Wang, P. Chen. “Automated Detection of Fetal Cardiac Structure from First-trimester Ultrasound Sequences,” IEEE International Conference on Biomedical Engineering and Informatics,2010, pp.127-131.
[10] B. C.Patel, Dr. G.R.Sinha, “An Adaptive K-means Clustering Algorithm for Breast Image Segmentation,” International Journal of Computer Applications Volume 10, No.4,pp. 35-38, 2010.
[11] T.F. Cootes, G.J Edwards, and C,J. Taylor, “Active Appearance Models,” IEEE Trans. Pattern Analysis and Machine Intelligence, vol.23, pp. 681–685, 2001