International Journal of Computer Applications (0975 – 8887) Volume 77 – No.12, September 2013 33 Automatic Border Detection of the Left Ventricle in Parasternal Short Axis View of Echocardiogram G.N.Balaji T.S.Subashini, Ph.D Ph.D. Research Scholar Associate professor Department of Computer Science and Engineering Department of Computer Science and Engineering Annamalai University, Annamalai Nagar Annamalai University, Annamalai Nagar ABSTRACT Echocardiogram is one of the easiest ad widely employed methods that uses ultrasound to evaluate heart muscle, heart valves, and risk for heart disease. Heart failure (HF) can result from any structural or functional cardiac disorder that impairs the ability of the ventricle to fill with or eject blood. Echocardiography represents “the gold standard" in the assessment of left ventricle LV systolic and diastolic dysfunction. Left ventricular dimensions, volumes and wall thicknesses are echocardiographic measurements that are widely used in clinical practice and research. To obtain accurate linear measurements from the echocardiography accurate segmentation of the LV is essential. This paper proposes a method to segment the left ventricular border automatically on the 3-dimensional (2D+t) echocardiogram, where ‘t’ is the time. The 2D image is obtained by extracting the frames from the video of echocardiogram which is further processed to detect the edges of the left ventricle and finally the edge detected frames are converted back into video which will help the cardiologist to visualize the left ventricle in motion. The obtained results are efficient and can be utilized for the purpose of detecting various medical parameters. Keywords Echocardiogram, Left ventricular, automatic detection, segmentation. 1. INTRODUCTION Echocardiography images the heart using standard 2D, 3D and Doppler ultrasound [1]. The human heart is an organ that provides continuous blood circulation to the entire body through the cardiac cycle and is one of the most vital organs in the human body [2]. The heart is divided into four main chambers: the two upper chambers are called the left and right atria and two lower chambers are called the right and left ventricles [3]. The left ventricle [LV] receives oxygenated blood from the left atrium via the mitral valve, and pumps it into the aorta via the aortic valve [4]. For healthy functioning of the heart the LV should relax very rapidly after each contraction so as to fill rapidly with oxygenated blood owing from the lung veins. The echocardiogram allows doctors to diagnose, evaluate, and monitor heart related problems. An echocardiogram is a test that uses sound waves to create a moving picture of the heart [5, 6]. The picture is much more detailed than a plain x-ray image and involves no radiation exposure. An echocardiogram allows doctors to see the heart beating, and to see the heart valves and other structures of the heart. Clinical parameters such as ejection fraction (EF), left ventricle myocardium mass (MM), and stroke volume (SV) are required by the cardiologist for accurate diagnosis of heart related problems. Calculations of these parameters depend upon accurate delineation of endocardial and epicardial contours of the left ventricle (LV). Manual delineation is time consuming and tedious and has high inter-observer variability. Thus, fully automatic LV segmentation in echocardiogram is desirable. The automatic segmentation of the LV in echocardiogram typically faces four challenges: 1)the overlap between the intensity distributions within the cardiac regions; 2)the lack of edge information. 3) The shape variability of the endocardial and epicardial contours and 4) the inter-subject variability of these factors. In this paper it is proposed to automatically segment the LV in parasternal short-axis view of the echocardiogram video without any manual intervention. 2. RELATED WORK Accurate LV segmentation is quite difficult due to the presence of noise and due to the low contrast of echocardiograph image. Hence preprocessing of echocardiograph images is very important before the actual segmentation of LV. The work in [7] presented a wavelet- based thresholding scheme for noise suppression in ultrasound images. In [8] the image is filtered by convolving with a 3X3 Gaussian low pass filter followed by thresholding and to eliminate the noise morphological dilation and erosion have been applied. Adaptive weighted median filter (AWMF) for reducing speckle noise in ultrasound images is presented in [9] which is based on the weighted median. By adjusting the weight coefficients and consequently the smoothing characteristics of the filter according to the local statistics around each point of the image, it is possible to suppress noise while edges and other important features are preserved. The work in [10] combines image processing techniques with radial search to detect the left ventricular borders from echocardiograph images. The fuzzy reasoning employed in [11] defines edges by local image characteristics computed based on local statistics of the image. In this work to reduce the noise and to enhance the contrast of the image high boost filtering followed by LoG filter is carried out. The literature shows different methods for segmentation of LV in short axis views. The work in [12] uses the gray level information along with user defined initial contours to extract the boundary in the images. The method in [13] implements a probabilistic deformable model considering the boundary as two- dimensional deformable object using maximum posteriori estimate. The work in [14] reports an interesting approach to detect LV boundary of short axis echocardiographic