CNN‐based spatio‐temporal nonlinear filtering and endocardial boundary detection in echocardiography

In this paper, a CNN based spatio-temporal approach is introduced for finding the endocardial (inner) boundary of the left ventricle from a sequence of echocardiographic images. The discussed analogic1 CNN algorithm combines optimal nonlinear filtering and constrained wave propagation in order to estimate the continuous contour of a moving object in a medium where the edges are ill-defined. In the preprocessing phase, nonlinear filtering is employed to remove the coherent speckle noise that corrupts the images. It is verified that an optimal filtering strategy should estimate the mode of the local intensity histogram. Three different approximations of the mode filter were implemented, derived from robust statistics2 and geometry-driven diffusion3, that give an output consistent with the maximum likelihood estimate of the noisy sequence. The kernel of the left ventricle is located and the boundary is found using a fuzzy-adaptive technique that embodies constrained wave propagation. Boundary dislocation, area and smoothness constraints are transformed into the transient length of the CNN while the a priori knowledge about the heart morphology is built into the spatial template parameters (weight values). Special emphasis is given to VLSI implementation complexity. It is shown that the core of the algorithm can be realized using the already available CNN chips. Furthermore, it is argued that all templates of the complete solution belong to the implementation frame that is considered for the next generation of CNN Universal Chips. This study demonstrates that the discussed novel approach allows a reliable endocardial boundary tracking of the left ventricle in real-time using a spatio-temporal CNN visual microprocessor.

[1]  Frank S. Werblin,et al.  The computational eye , 1996 .

[2]  J Jenkins,et al.  Automatic Contour Definition on Left Ventriculograms By Image Evidence and a Multiple Template-Based Model (Cardiology) , 1989, IEEE transactions on medical imaging.

[3]  Frank S. Werblin,et al.  Techniques for constructing physiologically motivated neuromorphic models in CNN , 1994, Proceedings of the Third IEEE International Workshop on Cellular Neural Networks and their Applications (CNNA-94).

[4]  Leon O. Chua,et al.  Design of linear cellular neural networks for motion sensitive filtering , 1993 .

[5]  Tamás Roska,et al.  CNN based adaptive smoothing and some novel types of nonlinear operators for grey-scale image processing , 1995 .

[6]  S. J. Perantonis,et al.  Tracking endocardial border motion in ultrasonic images by using neural networks and ARIMA modelling techniques , 1996, Proceedings of International Conference on Neural Networks (ICNN'96).

[7]  Bing J. Sheu,et al.  Neural information processing and VLSI , 1995 .

[8]  A. Zarandy,et al.  Design of analogic CNN algorithms for mammogram analysis , 1994, Proceedings of the Third IEEE International Workshop on Cellular Neural Networks and their Applications (CNNA-94).

[9]  Mark S. Nixon,et al.  Biased motion-adaptive temporal filtering for speckle reduction in echocardiography , 1996, IEEE Trans. Medical Imaging.

[10]  Michel Bertrand,et al.  Ultrasonic texture motion analysis: theory and simulation , 1995, IEEE Trans. Medical Imaging.

[11]  José M. N. Leitão,et al.  Wall position and thickness estimation from sequences of echocardiographic images , 1996, IEEE Trans. Medical Imaging.

[12]  Niklas Nordström,et al.  Biased anisotropic diffusion: a unified regularization and diffusion approach to edge detection , 1990, Image Vis. Comput..

[13]  Marco Gilli,et al.  Stability of cellular neural networks and delayed cellular neural networks with nonpositive templates and nonmonotonic output functions , 1994 .

[14]  Lin-Bao Yang,et al.  Cellular neural networks: theory , 1988 .

[15]  Ángel Rodríguez-Vázquez,et al.  A 0.8 micrometer CMOS 2-D Programmable Mixed-Signal Focal-Plane Array Processor with On-Chip Binary Imaging and Instructions Storage , 1997 .

[16]  C T Chen,et al.  Epicardial boundary detection using fuzzy reasoning. , 1991, IEEE transactions on medical imaging.

[17]  Ákos Zarándy,et al.  Intelligent image resolution enhancement by the CNN universal machine and its relevance to TV picture enhancement , 1995 .

[18]  Bertram E. Shi,et al.  Order statistic filtering with cellular neural networks , 1994, Proceedings of the Third IEEE International Workshop on Cellular Neural Networks and their Applications (CNNA-94).

[19]  Akio Ushida,et al.  CNN based self-adjusting nonlinear filters , 1996, 1996 Fourth IEEE International Workshop on Cellular Neural Networks and their Applications Proceedings (CNNA-96).

[20]  Á. Rodríguez-Vázquez,et al.  Current-mode techniques for the implementation of continuous- and discrete-time cellular neural networks , 1993 .

[21]  Alexander A. Sawchuk,et al.  Adaptive Noise Smoothing Filter for Images with Signal-Dependent Noise , 1985, IEEE Transactions on Pattern Analysis and Machine Intelligence.

[22]  T. Loupas,et al.  An adaptive weighted median filter for speckle suppression in medical ultrasonic images , 1989 .

[23]  Leon O. Chua,et al.  Cellular neural networks: applications , 1988 .

[24]  Tamás Roska,et al.  CNN-based difference-controlled adaptive non-linear image filters , 1998, Int. J. Circuit Theory Appl..

[25]  P. Simard,et al.  Restoration of the velocity field of the heart from two-dimensional echocardiograms. , 1989, IEEE transactions on medical imaging.

[26]  Carver Mead,et al.  Analog VLSI and neural systems , 1989 .

[27]  Michael G. Strintzis,et al.  Nonlinear ultrasonic image processing based on signal-adaptive filters and self-organizing neural networks , 1994, IEEE Trans. Image Process..

[28]  Andrew P. Witkin,et al.  Scale-Space Filtering , 1983, IJCAI.

[29]  Bart M. ter Haar Romeny,et al.  Geometry-Driven Diffusion in Computer Vision , 1994, Computational Imaging and Vision.

[30]  A. Dawidziuk,et al.  Minimum size 0.5 micron CMOS programmable 48 by 48 CNN test chip , 1997 .

[31]  P. Lions,et al.  Image selective smoothing and edge detection by nonlinear diffusion. II , 1992 .

[32]  J C Bamber,et al.  Real-time implementation of coherent speckle suppression in B-scan images. , 1991, Ultrasonics.

[33]  Leon O. Chua,et al.  Fuzzy cellular neural networks: theory , 1996, 1996 Fourth IEEE International Workshop on Cellular Neural Networks and their Applications Proceedings (CNNA-96).

[34]  T Loupas,et al.  Clinical evaluation of a digital signal-processing device for real-time speckle suppression in medical ultrasonics. , 1989, The British journal of radiology.

[35]  D. Adam,et al.  Automatic ventricular cavity boundary detection from sequential ultrasound images using simulated annealing. , 1989, IEEE transactions on medical imaging.

[36]  Tamás Roska,et al.  Analogic CNN algorithms for 3D interpolation-approximation and object rotation using controlled switched templates , 1996, Int. J. Circuit Theory Appl..

[37]  E. R. Davies,et al.  On the noise suppression and image enhancement characteristics of the median, truncated median and mode filters , 1988, Pattern Recognit. Lett..

[38]  A. Jacobs,et al.  Some cortical spiking neuron models using CNN , 1994, Proceedings of the Third IEEE International Workshop on Cellular Neural Networks and their Applications (CNNA-94).

[39]  Leon O. Chua,et al.  Resistive grid image filtering: input/output analysis via the CNN framework , 1992 .

[40]  Frank S. Werblin,et al.  Using CNN to unravel space-time processing in the vertebrate retina , 1994, Proceedings of the Third IEEE International Workshop on Cellular Neural Networks and their Applications (CNNA-94).

[41]  Josiane Zerubia,et al.  Markov random field image segmentation using cellular neural network , 1997 .

[42]  Guido Gerig,et al.  Nonlinear anisotropic filtering of MRI data , 1992, IEEE Trans. Medical Imaging.

[43]  Tamás Roska,et al.  Smart image scanning algorithms for the CNN universal machine , 1995 .

[44]  L. T. Andrews,et al.  Segmentation of echocardiographic images using mathematical morphology , 1988, IEEE Transactions on Biomedical Engineering.

[45]  John F. Canny,et al.  A Computational Approach to Edge Detection , 1986, IEEE Transactions on Pattern Analysis and Machine Intelligence.

[46]  Leon O. Chua,et al.  Image processing techniques for cellular neural network hardware , 1997 .

[47]  Leon O. Chua,et al.  The CNN paradigm , 1993 .

[48]  Bertram E. Shi,et al.  Spatio-temporal image filtering with cellular neural networks , 1996, Proceedings of International Conference on Neural Networks (ICNN'96).

[49]  Ricardo Carmona-Galán,et al.  A CNN Universal Chip in CMOS Technology , 1996, Int. J. Circuit Theory Appl..

[50]  Anastasios N. Venetsanopoulos,et al.  Adaptive schemes for noise filtering and edge detection by use of local statistics , 1988 .

[51]  Cs. Rekeczky,et al.  The Use of CNN Technology in Echocardiography: Spatio-temporal Nonlinear Filtering and Contour Detec , 1997 .

[52]  C. Burckhardt Speckle in ultrasound B-mode scans , 1978, IEEE Transactions on Sonics and Ultrasonics.

[53]  Tamás Roska,et al.  A fast, complex and efficient test implementation of the CNN Universal Machine , 1994, Proceedings of the Third IEEE International Workshop on Cellular Neural Networks and their Applications (CNNA-94).

[54]  Tamás Roska,et al.  Rotation invariant detection of moving and standing objects using analogic cellular neural network algorithms based on ring codes , 1995 .

[55]  Leon O. Chua,et al.  Estimating optical flow with cellular neural networks , 1998 .

[56]  Edgar Sanchez-Sinencio,et al.  Operational transconductance amplifier-based nonlinear function syntheses , 1989 .

[57]  E J Delp,et al.  Detecting left ventricular endocardial and epicardial boundaries by digital two-dimensional echocardiography. , 1988, IEEE transactions on medical imaging.

[58]  P. Shankar Speckle Reduction in Ultrasound B-Scans Using Weighted Averaging in Spatial Compounding , 1986, IEEE Transactions on Ultrasonics, Ferroelectrics and Frequency Control.

[59]  D Marr,et al.  Theory of edge detection , 1979, Proceedings of the Royal Society of London. Series B. Biological Sciences.

[60]  Jitendra Malik,et al.  Scale-Space and Edge Detection Using Anisotropic Diffusion , 1990, IEEE Trans. Pattern Anal. Mach. Intell..

[61]  R. F. Wagner,et al.  Statistics of Speckle in Ultrasound B-Scans , 1983, IEEE Transactions on Sonics and Ultrasonics.

[62]  Gozde Bozdagi Akar,et al.  An adaptive speckle suppression filter for medical ultrasonic imaging , 1995, IEEE Trans. Medical Imaging.

[63]  J C Bamber,et al.  Adaptive filtering for reduction of speckle in ultrasonic pulse-echo images. , 1986, Ultrasonics.

[64]  Tamás Roska,et al.  The use of CNN models in the subcortical visual pathway. (Reseach report of the Dual and Neural Computing Systems Laboratory DNS-16-1992) , 1993 .

[65]  Akio Ushida,et al.  Image Segmentation by Soft Computing on the CNN Universal Machine , 1996 .

[66]  Yongmin Kim,et al.  A multiple active contour model for cardiac boundary detection on echocardiographic sequences , 1996, IEEE Trans. Medical Imaging.

[67]  Tamás Roska,et al.  The CNN universal machine: an analogic array computer , 1993 .

[68]  Tamás Roska,et al.  CNN chip set architectures and the visual mouse , 1996, 1996 Fourth IEEE International Workshop on Cellular Neural Networks and their Applications Proceedings (CNNA-96).

[69]  I. Pitas,et al.  Optimum nonlinear signal detection and estimation in the presence of ultrasonic speckle. , 1992, Ultrasonic imaging.

[70]  S Rocchi,et al.  An adaptive Kalman filter for speckle reduction in ultrasound images. , 1988, The Journal of nuclear medicine and allied sciences.

[71]  Song B. Park,et al.  Speckle Reduction with Edge Preservation in Medical Ultrasonic Images Using a Homogeneous Region Growing Mean Filter (HRGMF) , 1991, Ultrasonic imaging.

[72]  J. M. Cruz,et al.  A 16 × 16 Cellular Neural Network Universal Chip: The First Complete Single-Chip Dynamic Computer Array with Distributed Memory and with Gray-Scale Input-Output , 1998 .

[73]  A. Zarandy,et al.  Novel types of analogic CNN algorithms for recognizing bank-notes , 1994, Proceedings of the Third IEEE International Workshop on Cellular Neural Networks and their Applications (CNNA-94).