Real Time GPU-Based Segmentation and Tracking of the Left Ventricle on 2D Echocardiography

Left ventricle segmentation and tracking in ultrasound images present necessary tasks for cardiac diagnostic. These tasks are difficult due to the inherent problems of ultrasound images (i.e. low contrast, speckle noise, signal dropout, presence of shadows, etc.). In this paper, we propose an accurate and automatic method for left ventricle segmentation and tracking. The method is based on optical flow estimation for detecting the left ventricle center. Then, the contour is defined and tracked using convex hull and spline interpolation algorithms. In order to provide a real time processing of videos, we propose also an effective and adapted exploitation of new parallel and heterogeneous architectures, that consist of both central (CPU) and graphic (GPU) processing units. The latter can exploit both NVIDIA and ATI graphic cards since we propose CUDA and OpenCL implementations. This allowed to improve the performance of our method thanks to the parallel exploitation of the high number of computing units within GPU. Our experiments are conducted using a set of 11 normal and 17 disease hearts ultrasound video sequences. The related results achieved automatic and real-time left ventricle detection and tracking with a rate of 92 % of success.

[1]  David G. Lowe,et al.  Distinctive Image Features from Scale-Invariant Keypoints , 2004, International Journal of Computer Vision.

[2]  Sidi Ahmed Mahmoudi,et al.  A Multi-Resolution FPGA-Based Architecture for Real-Time Edge and Corner Detection , 2014, IEEE Transactions on Computers.

[3]  Michael Unser,et al.  Myocardial motion analysis from B-mode echocardiograms , 2005, IEEE Transactions on Image Processing.

[4]  Andrew W. Fitzgibbon,et al.  A Buyer's Guide to Conic Fitting , 1995, BMVC.

[5]  Yakup Genc,et al.  GPU-based Video Feature Tracking And Matching , 2006 .

[6]  Sidi Ahmed Mahmoudi,et al.  A new self-adapting architecture for feature detection , 2012, 22nd International Conference on Field Programmable Logic and Applications (FPL).

[7]  Yoshiki Mizukami,et al.  Optical Flow Computation on Compute Unified Device Architecture , 2007, 14th International Conference on Image Analysis and Processing (ICIAP 2007).

[8]  Wei Chen,et al.  High performance median filtering using commodity graphics hardware , 2009, 2009 IEEE Nuclear Science Symposium Conference Record (NSS/MIC).

[9]  Zhiyi Yang,et al.  Parallel Image Processing Based on CUDA , 2008, 2008 International Conference on Computer Science and Software Engineering.

[10]  James S. Duncan,et al.  Estimation of 3D left ventricular deformation from echocardiography , 2001, Medical Image Anal..

[11]  Raphaël Couturier,et al.  Fine-tuned High-speed Implementation of a GPU-based Median Filter , 2014, J. Signal Process. Syst..

[12]  Scott B. Baden,et al.  Source-to-Source Optimization of CUDA C for GPU Accelerated Cardiac Cell Modeling , 2010, Euro-Par.

[13]  Sidi Ahmed Mahmoudi,et al.  Real-time motion tracking using optical flow on multiple GPUs , 2014 .

[14]  Sidi Ahmed Mahmoudi,et al.  Efficient exploitation of heterogeneous platforms for images features extraction , 2012, 2012 3rd International Conference on Image Processing Theory, Tools and Applications (IPTA).

[15]  Clark Taylor,et al.  GPU Acceleration of Real-time Feature Based Algorithms , 2007, 2007 IEEE Workshop on Motion and Video Computing (WMVC'07).

[16]  Sidi Ahmed Mahmoudi,et al.  Multi-CPU/Multi-GPU Based Framework for Multimedia Processing , 2015, CIIA.

[17]  Kohji Masuda,et al.  Elucidation of intersection distribution in motion vectors from successive echocardiograms and its application for heart disease recognition , 2011 .

[18]  S. Takeshima,et al.  Development of automatic recognition software of left ventricle by time series processing echocardiograms and application to disease heart , 2012, The 4th 2011 Biomedical Engineering International Conference.

[19]  Julien Marzat,et al.  Real-Time Dense and Accurate Parallel Optical Flow using CUDA , 2009 .