A Novel Method for Echocardiogram Boundary Detection Using Adaptive Neuro -Fuzzy Systems

Echocardiogram is one of the effective diagnostics tool for cardiac investigations. Artifacts such as speckle, grating lobes, and shadowing in ultrasound images can hamper experts interpretation and impede automated analysis. This is because noise and artifacts cause edges to manifest themselves in different ways from the typical definition; hence they pose challenge to conventional edge detection and noise suppression methods. Thus, a method is proposed to resolve the ambiguous edge definitions in noisy echocardiogram by applying the adaptive neuro-fuzzy inference system (ANFIS) to determine edgeness based on local image characteristics that are defined by operators using local statistics. The performance of the proposed method is compared to that of a conventional edge detector and another similar method but without learning capability.

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

[2]  K. Miller.  Least Squares Methods for Ill-Posed Problems with a Prescribed Bound , 1970 .

[3]  Joseph Yadegar,et al.  Regularized Speckle Reducing Anisotropic Diffusion for Feature Characterization , 2006, 2006 International Conference on Image Processing.

[4]  Nikolas P. Galatsanos,et al.  Regularized reconstruction to reduce blocking artifacts of block discrete cosine transform compressed images , 1993, IEEE Trans. Circuits Syst. Video Technol..

[5]  S Chan,et al.  Boundary Enhancement using ANFIS Based on Local Image Characteristics for Echocardiograms , 2006 .

[6]  Jae Lim,et al.  Reduction Of Blocking Effects In Image Coding , 1984 .

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

[8]  K. R. Rao,et al.  Discrete cosine transform filtering , 1990, International Conference on Acoustics, Speech, and Signal Processing.

[9]  Wataru Ohyama,et al.  Automatic left ventricular endocardium detection in echocardiograms based on ternary thresholding method , 2000, Proceedings 15th International Conference on Pattern Recognition. ICPR-2000.

[10]  J. Soraghan,et al.  Automatic cardiac LV boundary detection and tracking using hybrid fuzzy temporal and fuzzy multiscale edge detection , 1999, IEEE Transactions on Biomedical Engineering.

[11]  Scott T. Acton,et al.  Speckle reducing anisotropic diffusion , 2002, IEEE Trans. Image Process..

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

[13]  Rémy Prost,et al.  Iterative constrained restoration of DCT-compressed images , 1989 .

[14]  Anil K. Jain.  Fundamentals of Digital Image Processing , 2018, Control of Color Imaging Systems.

[15]  Jyh-Shing Roger Jang,et al.  ANFIS: adaptive-network-based fuzzy inference system , 1993, IEEE Trans. Syst. Man Cybern..

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