Extraction of left ventricular contours from left ventriculograms by means of a neural edge detector

We propose a method for extracting the left ventricular (LV) contours from left ventriculograms by means of a neural edge detector (NED) in order to extract the contours which accord with those traced by a cardiologist. The NED is a supervised edge detector based on a modified multilayer neural network, and is trained by use of a modified back-propagation algorithm. The NED can acquire the function of a desired edge detector through training with a set of input images and the desired edges obtained from the contours traced by a cardiologist. The proposed contour-extraction method consists of 1) detection of "subjective edges" by use of the NED; 2) extraction of rough contours by use of low-pass filtering and edge enhancement; and 3) a contour-tracing method based on the contour candidates synthesized from the edges detected by the NED and the rough contours. Through experiments, it was shown that the proposed method was able to extract the contours in agreement with those traced by an experienced cardiologist, i.e., we achieved an average contour error of 6.2% for left ventriculograms at end-diastole and an average difference between the ejection fractions obtained from the manually traced contours and those obtained from the computer-extracted contours of 4.1%.

[1]  Ken-ichi Funahashi,et al.  On the approximate realization of continuous mappings by neural networks , 1989, Neural Networks.

[2]  Andrew R. Barron,et al.  Universal approximation bounds for superpositions of a sigmoidal function , 1993, IEEE Trans. Inf. Theory.

[3]  J. Reiber,et al.  Comparison between manual and semiautomated analysis of left ventricular volume parameters from short-axis MR images. , 1997, Journal of computer assisted tomography.

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

[5]  Geoffrey E. Hinton,et al.  Learning representations by back-propagating errors , 1986, Nature.

[6]  Kenji Suzuki,et al.  Recognition of Coronary Arterial Stenosis Using Neural Network on DSA System , 1995, Systems and Computers in Japan.

[7]  Kenji Suzuki,et al.  Neural Edge Enhancer for Supervised Edge Enhancement from Noisy Images , 2003, IEEE Trans. Pattern Anal. Mach. Intell..

[8]  Richard O. Duda,et al.  Pattern classification and scene analysis , 1974, A Wiley-Interscience publication.

[9]  Abdel-Ouahab Boudraa,et al.  Left ventricle automated detection method in gated isotopic ventriculography using fuzzy clustering , 1993, IEEE Trans. Medical Imaging.

[10]  Stephen A. Dyer,et al.  Digital signal processing , 2018, 8th International Multitopic Conference, 2004. Proceedings of INMIC 2004..

[11]  Geoffrey E. Hinton,et al.  Learning internal representations by error propagation , 1986 .

[12]  C. C. Li,et al.  Automated left ventricular border determination in cineangiograms based on a dynamic spider model , 1990, [1990] Proceedings Computers in Cardiology.

[13]  Jun Shen,et al.  Artificial neural networks for boundary extraction , 1996, 1996 IEEE International Conference on Systems, Man and Cybernetics. Information Intelligence and Systems (Cat. No.96CH35929).

[14]  A. Hallstrom,et al.  Reproducibility of ventricular function measurements by contrast angiography. , 1984, Catheterization and cardiovascular diagnosis.

[15]  M Baroni,et al.  Computer evaluation of left ventricular wall motion by means of shape-based tracking and symbolic description. , 1999, Medical engineering & physics.

[16]  Kenji Suzuki,et al.  Simple unit-pruning with gain-changing training , 2001, Neural Networks for Signal Processing XI: Proceedings of the 2001 IEEE Signal Processing Society Workshop (IEEE Cat. No.01TH8584).

[17]  Gosuke Ohashi,et al.  Boundary estimation method for ultrasonic 3D imaging , 1993 .

[18]  Josef Kittler,et al.  Optimal Edge Detectors for Ramp Edges , 1991, IEEE Trans. Pattern Anal. Mach. Intell..

[19]  Kenji Suzuki,et al.  Designing the optimal structure of a neural filter , 1998, Neural Networks for Signal Processing VIII. Proceedings of the 1998 IEEE Signal Processing Society Workshop (Cat. No.98TH8378).

[20]  M Demi.  New approach to automatic contour detection from image sequences: an application to ventriculographic images. , 1994, Computers and biomedical research, an international journal.

[21]  Jaakko Astola,et al.  A new class of nonlinear filters-neural filters , 1993, IEEE Trans. Signal Process..

[22]  Essam A. El-Kwae,et al.  Edge detection in medical images using a genetic algorithm , 1998, IEEE Transactions on Medical Imaging.

[23]  Manfred H. Hueckel.  A Local Visual Operator Which Recognizes Edges and Lines , 1973, JACM.

[24]  Krishnan B. Chandran,et al.  Automatic detection of left ventricular endocardium in cardiac images , 1990, [1990] Proceedings Computers in Cardiology.

[25]  C. Guzelis,et al.  Recurrent perceptron learning algorithm for CNNs with application to edge detection , 1995 .

[26]  Koji Tochinai,et al.  An edge detection by using self-organization , 1998, Proceedings of the 1998 IEEE International Conference on Acoustics, Speech and Signal Processing, ICASSP '98 (Cat. No.98CH36181).

[27]  Constantine Butakoff,et al.  Image processing using cellular neural networks based on multi-valued and universal binary neurons , 2002, J. VLSI Signal Process..

[28]  Kenji Suzuki,et al.  Efficient approximation of neural filters for removing quantum noise from images , 2002, IEEE Trans. Signal Process..

[29]  J. Sau,et al.  Automated detection of the left ventricular region in gated nuclear cardiac imaging , 1996, IEEE Transactions on Biomedical Engineering.

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

[31]  Patrick Clarysse,et al.  Tracking geometrical descriptors on 3-D deformable surfaces: application to the left-ventricular surface of the heart , 1997, IEEE Transactions on Medical Imaging.

[32]  Jaakko Astola,et al.  Adaptive multistage weighted order statistic filters based on the backpropagation algorithm , 1994, IEEE Trans. Signal Process..

[33]  James D. Thomas,et al.  Segmentation and tracking in echocardiographic sequences: active contours guided by optical flow estimates , 1998, IEEE Transactions on Medical Imaging.

[34]  N. Otsu.  A threshold selection method from gray level histograms , 1979 .

[35]  D.L. Parker,et al.  Improving left ventricular border recognition using probability surfaces , 1988, Proceedings. Computers in Cardiology 1988.

[36]  Ken-ichi Suzuki,et al.  Neural Filter with Selection of Input Features and Its Application to Image Quality Improvement of Medical Image Sequences , 2002 .

[37]  S Akselrod,et al.  An automatic contour extraction algorithm for short-axis cardiac magnetic resonance images. , 1996, Medical physics.

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

[39]  Hiroshi Nagahashi,et al.  Boundary Detection of Color Images Using Neural Networks. , 1997 .

[40]  Takao Hinamoto,et al.  Image restoration by Hopfield networks considering the line process , 1995, Proceedings of ICNN'95 - International Conference on Neural Networks.

[41]  Naum N. Aizenberg,et al.  Image processing using cellular neural networks based on multi-valued and universal binary neurons , 2000, Neural Networks for Signal Processing X. Proceedings of the 2000 IEEE Signal Processing Society Workshop (Cat. No.00TH8501).

[42]  M. Y. Siyal,et al.  Edge detection with BP neural networks , 1998, ICSP '98. 1998 Fourth International Conference on Signal Processing (Cat. No.98TH8344).

[43]  Kenji Suzuki,et al.  Training under achievement quotient criterion , 2000, Neural Networks for Signal Processing X. Proceedings of the 2000 IEEE Signal Processing Society Workshop (Cat. No.00TH8501).

[44]  Kenji Suzuki,et al.  Computer-aided diagnosis system for coronary artery stenosis using a neural network , 2001, SPIE Medical Imaging.

[45]  Hideo Fujimoto,et al.  Edge detection by neural network with line process , 1993, Proceedings of 1993 International Conference on Neural Networks (IJCNN-93-Nagoya, Japan).

[46]  W. Lunscher,et al.  Optimal Edge Detector Design I: Parameter Selection and Noise Effects , 1986, IEEE Transactions on Pattern Analysis and Machine Intelligence.

[47]  James S. Duncan,et al.  Estimation of 3-D left ventricular deformation from medical images using biomechanical models , 2002, IEEE Transactions on Medical Imaging.

[48]  Riccardo Poli,et al.  Recovery of the 3-D shape of the left ventricle from echocardiographic images , 1995, IEEE Trans. Medical Imaging.

[49]  G Bashein,et al.  Matched filter identification of left-ventricular endocardial borders in transesophageal echocardiograms. , 1990, IEEE transactions on medical imaging.

[50]  Amir A. Amini,et al.  Fast LV motion estimation using subspace approximation techniques , 2001, IEEE Transactions on Medical Imaging.

[51]  Joos Vandewalle,et al.  Multi-Valued and Universal Binary Neurons: Theory, Learning and Applications , 2012 .

[52]  Demetri Terzopoulos,et al.  Snakes: Active contour models , 2004, International Journal of Computer Vision.

[53]  Elsa D. Angelini,et al.  LV volume quantification via spatiotemporal analysis of real-time 3-D echocardiography , 2001, IEEE Transactions on Medical Imaging.

[54]  Surendra Ranganath,et al.  Contour extraction from cardiac MRI studies using snakes , 1995, IEEE Trans. Medical Imaging.

[55]  Yoshinobu Sato,et al.  Reconstruction of time-varying 3-D left-ventricular shape from multiview X-ray cineangiocardiograms , 2002, IEEE Transactions on Medical Imaging.

[56]  Cullen Schaffer,et al.  Selecting a classification method by cross-validation , 1993, Machine Learning.

[57]  S. Armato,et al.  Massive training artificial neural network (MTANN) for reduction of false positives in computerized detection of lung nodules in low-dose computed tomography. , 2003, Medical physics.

[58]  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.

[59]  Kenji Suzuki,et al.  Linear-time connected-component labeling based on sequential local operations , 2003, Comput. Vis. Image Underst..

[60]  Kenji Suzuki,et al.  A Simple Neural Network Pruning Algorithm with Application to Filter Synthesis , 2001, Neural Processing Letters.

[61]  Joos Vandewalle,et al.  Multi-Valued and Universal Binary Neurons , 2000 .

[62]  James S. Duncan,et al.  Knowledge Directed Left Ventricular Boundary Detection in Equilibrium Radionuclide Angiocardiography , 1987, IEEE Transactions on Medical Imaging.

[63]  P. Cohn,et al.  Reproducibility of the angiographic left ventricular ejection fraction in patients with coronary artery disease. , 1974, American heart journal.

[64]  Nirwan Ansari,et al.  Structure and properties of generalized adaptive neural filters for signal enhancement , 1996, IEEE Trans. Neural Networks.

[65]  Geoffrey E. Hinton,et al.  Learning representations of back-propagation errors , 1986 .

[66]  J. Alison Noble,et al.  A shape-space-based approach to tracking myocardial borders and quantifying regional left-ventricular function applied in echocardiography , 2002, IEEE Transactions on Medical Imaging.

[67]  Pekka J. Toivanen,et al.  Edge Detection of Multispectral Images Using the 1-D Self-Organizing Map , 1998 .

[68]  P. Grattoni,et al.  Contour Detection of the Left Ventricular Cavity from Angiographic Images , 1985, IEEE Transactions on Medical Imaging.

[69]  Ling Guan,et al.  Neural vision system and applications in image processing and analysis , 1998, Proceedings of the 1998 IEEE International Conference on Acoustics, Speech and Signal Processing, ICASSP '98 (Cat. No.98CH36181).

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