Improved graph cut model with features of superpixels and neighborhood patches for myocardium segmentation from ultrasound image.

Ultrasound (US) imaging has the technical advantages for the functional evaluation of myocardium compared with other imaging modalities. However, it is a challenge of extracting the myocardial tissues from the background due to low quality of US imaging. To better extract the myocardial tissues, this study proposes a semi-supervised segmentation method of fast Superpixels and Neighborhood Patches based Continuous Min-Cut (fSP-CMC). The US image is represented by a graph, which is constructed depending on the features of superpixels and neighborhood patches. A novel similarity measure is defined to capture and enhance the features correlation using Pearson correlation coefficient and Pearson distance. Interactive labels provided by user play a subsidiary role in the semi-supervised segmentation. The continuous graph cut model is solved via a fast minimization algorithm based on augmented Lagrangian and operator splitting. Additionally, Non-Uniform Rational B-Spline (NURBS) curve fitting is used as post-processing to solve the low resolution problem caused by the graph-based method. 200 B-mode US images of left ventricle of the rats were collected in this study. The myocardial tissues were segmented using the proposed fSP-CMC method compared with the method of fast Neighborhood Patches based Continuous Min-Cut (fP-CMC). The results show that the fSP-CMC segmented the myocardial tissues with a higher agreement with the ground truth (GT) provided by medical experts. The mean absolute distance (MAD) and Hausdorff distance (HD) were significantly lower than those values of fP-CMC (p < 0.05), while the Dice was significantly higher (p < 0.05). In conclusion, the proposed fSP-CMC method accurately and effectively segments the myocardiumn in US images. This method has potentials to be a reliable segmentation method and useful for the functional evaluation of myocardium in the future study.

[1]  Jean-Michel Morel,et al.  A Review of Image Denoising Algorithms, with a New One , 2005, Multiscale Model. Simul..

[2]  Marie-Pierre Jolly,et al.  Interactive Graph Cuts for Optimal Boundary and Region Segmentation of Objects in N-D Images , 2001, ICCV.

[3]  Xiaoming Yuan,et al.  An augmented Lagrangian based parallel splitting method for separable convex minimization with applications to image processing , 2014, Math. Comput..

[4]  Pascal Fua,et al.  SLIC Superpixels Compared to State-of-the-Art Superpixel Methods , 2012, IEEE Transactions on Pattern Analysis and Machine Intelligence.

[5]  R. Glowinski,et al.  Augmented Lagrangian and Operator-Splitting Methods in Nonlinear Mechanics , 1987 .

[6]  Xuejing Wang,et al.  Improved graph-cut segmentation for ultrasound liver cyst image , 2018, Multimedia Tools and Applications.

[7]  Alexei A. Efros,et al.  Image quilting for texture synthesis and transfer , 2001, SIGGRAPH.

[8]  Sung Yong Shin,et al.  On pixel-based texture synthesis by non-parametric sampling , 2006, Comput. Graph..

[9]  Huijing Hu,et al.  Ultrasonography Monitoring of Trauma-Induced Heterotopic Ossification: Guidance for Rehabilitation Procedures , 2018, Front. Neurol..

[10]  Olivier Bernard,et al.  A fully automatic and multi-structural segmentation of the left ventricle and the myocardium on highly heterogeneous 2D echocardiographic data , 2017, 2017 IEEE International Ultrasonics Symposium (IUS).

[11]  Jinhui Lan,et al.  Image segmentation based on gray stretch and threshold algorithm , 2015 .

[12]  Moustafa M. Fahmy,et al.  Optimal merging of sorted data under the mean absolute error criterion , 1992 .

[13]  Huicheng Zhou,et al.  Implementation of CL points preprocessing methodology with NURBS curve fitting technique for high-speed machining , 2015, Comput. Ind. Eng..

[14]  Andrew Blake,et al.  "GrabCut" , 2004, ACM Trans. Graph..

[15]  Kim Steenstrup Pedersen,et al.  The Nonlinear Statistics of High-Contrast Patches in Natural Images , 2003, International Journal of Computer Vision.

[16]  Qinghua Huang,et al.  Breast ultrasound image segmentation: a survey , 2017, International Journal of Computer Assisted Radiology and Surgery.

[17]  Stephen Ashcroft,et al.  One-way Analysis of Variance (ANOVA) , 2003 .

[18]  Mahmoud R. El-Sakka,et al.  Optical Flow Active Contours with Primitive Shape Priors for Echocardiography , 2010, EURASIP J. Adv. Signal Process..

[19]  Les A. Piegl,et al.  On NURBS: A Survey , 2004 .

[20]  Baining Guo,et al.  Real-time texture synthesis by patch-based sampling , 2001, TOGS.

[21]  Jitendra Malik,et al.  Learning a classification model for segmentation , 2003, Proceedings Ninth IEEE International Conference on Computer Vision.

[22]  Vladimir Kolmogorov,et al.  What metrics can be approximated by geo-cuts, or global optimization of length/area and flux , 2005, Tenth IEEE International Conference on Computer Vision (ICCV'05) Volume 1.

[23]  Qinghua Huang,et al.  A Superpixel-Classification-Based Method for Breast Ultrasound Images , 2018, 2018 5th International Conference on Systems and Informatics (ICSAI).

[24]  Xavier Bresson,et al.  An efficient segmentation method for ultrasound images based on a semi-supervised approach and patch-based features , 2011, 2011 IEEE International Symposium on Biomedical Imaging: From Nano to Macro.

[25]  Marie-Pierre Jolly,et al.  Interactive graph cuts for optimal boundary & region segmentation of objects in N-D images , 2001, Proceedings Eighth IEEE International Conference on Computer Vision. ICCV 2001.

[26]  B LeeAnn,et al.  The Nonlinear Statistics of High-Contrast Patches in Natural Images , 2003 .

[27]  Ghassan Hamarneh,et al.  Multi-Region Probabilistic Dice Similarity Coefficient using the Aitchison Distance and Bipartite Graph Matching , 2015, ArXiv.

[28]  Vladimir Kolmogorov,et al.  Computing geodesics and minimal surfaces via graph cuts , 2003, Proceedings Ninth IEEE International Conference on Computer Vision.

[29]  Yanhui Guo,et al.  A novel myocardium segmentation approach based on neutrosophic active contour model , 2017, Comput. Methods Programs Biomed..

[30]  James S. Duncan,et al.  A coupled deformable model for tracking myocardial borders from real-time echocardiography using an incompressibility constraint , 2010, Medical Image Anal..

[31]  Qinghua Huang,et al.  Machine Learning in Ultrasound Computer-Aided Diagnostic Systems: A Survey , 2018, BioMed research international.

[32]  Marcin Kozak,et al.  Including the Tukey Mean‐Difference (Bland–Altman) Plot in a Statistics Course , 2014 .

[33]  Guy Gilboa,et al.  Nonlocal Operators with Applications to Image Processing , 2008, Multiscale Model. Simul..

[34]  Olga Veksler,et al.  Fast Approximate Energy Minimization via Graph Cuts , 2001, IEEE Trans. Pattern Anal. Mach. Intell..

[35]  Xavier Bresson,et al.  Semi-Supervised Segmentation of Ultrasound Images Based on Patch Representation and Continuous Min Cut , 2014, PloS one.

[36]  Hemant D. Tagare,et al.  Tunneling descent for m.a.p. active contours in ultrasound segmentation , 2007, Medical Image Anal..

[37]  Rumin Yang,et al.  Segmentation of breast ultrasound image using graph cuts and level set , 2015 .

[38]  L. Rudin,et al.  Nonlinear total variation based noise removal algorithms , 1992 .

[39]  Jingan Zhou,et al.  Thyroid Tumor Ultrasound Image Segmentation Based on Improved Graph Cut , 2016, 2016 International Conference on Intelligent Transportation, Big Data & Smart City (ICITBS).

[40]  Hao Chen,et al.  Iterative Multi-domain Regularized Deep Learning for Anatomical Structure Detection and Segmentation from Ultrasound Images , 2016, MICCAI.

[41]  K. Przyklenk,et al.  Reduction of Myocardial Infarct Size with Ischemic “Conditioning”: Physiologic and Technical Considerations , 2013, Anesthesia and analgesia.

[42]  Xuelong Li,et al.  Optimized graph-based segmentation for ultrasound images , 2014, Neurocomputing.

[43]  Daniel Cremers,et al.  An Experimental Comparison of Discrete and Continuous Shape Optimization Methods , 2008, ECCV.

[44]  Qianjin Feng,et al.  Segmentation of ultrasonic breast tumors based on homogeneous patch. , 2012, Medical physics.

[45]  Xavier Bresson,et al.  Semi-supervised Segmentation Based on Non-local Continuous Min-Cut , 2009, SSVM.

[46]  Pierrick Coupé,et al.  Nonlocal Means-Based Speckle Filtering for Ultrasound Images , 2009, IEEE Transactions on Image Processing.