Statistical modeling and processing of high frequency ultrasound images: application to dermatologic oncology

This thesis studies statistical image processing of high frequency ultrasound imaging, with application to in-vivo exploration of human skin and noninvasive lesion assessment. More precisely, Bayesian methods are considered in order to perform tissue segmentation in ultrasound images of skin. It is established that ultrasound signals backscattered from skin tissues converge to a complex Levy Flight random process with non-Gaussian _-stable statistics. The envelope signal follows a generalized (heavy-tailed) Rayleigh distribution. Based on these results, it is proposed to model the distribution of multiple-tissue ultrasound images as a spatially coherent finite mixture of heavy-tailed Rayleigh distributions. Spatial coherence inherent to biological tissues is modeled by a Potts Markov random field. An original Bayesian algorithm combined with a Markov chain Monte Carlo method is then proposed to jointly estimate the mixture parameters and a label-vector associating each voxel to a tissue. The proposed method is successfully applied to the segmentation of in-vivo skin tumors in high frequency 2D and 3D ultrasound images. This method is subsequently extended by including the estimation of the Potts regularization parameter B within the Markov chain Monte Carlo (MCMC) algorithm. Standard MCMC methods cannot be applied to this problem because the likelihood of B is intractable. This difficulty is addressed by using a likelihood-free Metropolis-Hastings algorithm based on the sufficient statistic of the Potts model. The resulting unsupervised segmentation method is successfully applied to tridimensional ultrasound images. Finally, the problem of computing the Cramer-Rao bound (CRB) of B is studied. The CRB depends on the derivatives of the intractable normalizing constant of the Potts model. This is resolved by proposing an original Monte Carlo algorithm, which is successfully applied to compute the CRB of the Ising and Potts models.

[1]  B. Gnedenko,et al.  Limit Distributions for Sums of Independent Random Variables , 1955 .

[2]  L. A. Goodman.  On the Exact Variance of Products , 1960 .

[3]  J. Besag.  Spatial Interaction and the Statistical Analysis of Lattice Systems , 1974 .

[4]  J. Besag.  Statistical Analysis of Non-Lattice Data , 1975 .

[5]  D. Rubin,et al.  Maximum likelihood from incomplete data via the EM - algorithm plus discussions on the paper , 1977 .

[6]  A. Cohen.  An Introduction to Probability Theory and Mathematical Statistics , 1979 .

[7]  J. Laurie Snell,et al.  Markov Random Fields and Their Applications , 1980 .

[8]  F. Y. Wu.  The Potts model , 1982 .

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

[10]  Donald Geman,et al.  Stochastic Relaxation, Gibbs Distributions, and the Bayesian Restoration of Images , 1984, IEEE Transactions on Pattern Analysis and Machine Intelligence.

[11]  J. McCulloch,et al.  Simple consistent estimators of stable distribution parameters , 1986 .

[12]  Joseph W. Goodman.  A random walk through the field of speckle , 1986 .

[13]  R. F. Wagner,et al.  Statistical properties of radio-frequency and envelope-detected signals with applications to medical ultrasound. , 1987, Journal of the Optical Society of America. A, Optics and image science.

[14]  李幼升,et al.  Ph , 1989 .

[15]  A. Perretti,et al.  Diagnostic ultrasound imaging. , 1990, Rays.

[16]  M. Fink,et al.  The influence of multiple scattering in incoherent ultrasonic inspection of coarse grain stainless steel , 1991, IEEE 1991 Ultrasonics Symposium,.

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

[18]  D. Rubin,et al.  Inference from Iterative Simulation Using Multiple Sequences , 1992 .

[19]  C. Geyer,et al.  Constrained Monte Carlo Maximum Likelihood for Dependent Data , 1992 .

[20]  J. Jensen,et al.  Calculation of pressure fields from arbitrarily shaped, apodized, and excited ultrasound transducers , 1992, IEEE Transactions on Ultrasonics, Ferroelectrics and Frequency Control.

[21]  J.M. Reid,et al.  Use of non-Rayleigh statistics for the identification of tumors in ultrasonic B-scans of the breast , 1993, IEEE Trans. Medical Imaging.

[22]  D. Applebaum.  Stable non-Gaussian random processes , 1995, The Mathematical Gazette.

[23]  Stanley,et al.  Stochastic process with ultraslow convergence to a Gaussian: The truncated Lévy flight. , 1994, Physical review letters.

[24]  J. Greenleaf,et al.  Ultrasound echo envelope analysis using a homodyned K distribution signal model. , 1994, Ultrasonic imaging.

[25]  C. L. Nikias,et al.  Signal processing with alpha-stable distributions and applications , 1995 .

[26]  Sylvia Richardson,et al.  Markov chain concepts related to sampling algorithms , 1995 .

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

[28]  Chrysostomos L. Nikias,et al.  Fast estimation of the parameters of alpha-stable impulsive interference , 1996, IEEE Trans. Signal Process..

[29]  David Bruce Wilson,et al.  Exact sampling with coupled Markov chains and applications to statistical mechanics , 1996, Random Struct. Algorithms.

[30]  J. Arendt.  Paper presented at the 10th Nordic-Baltic Conference on Biomedical Imaging: Field: A Program for Simulating Ultrasound Systems , 1996 .

[31]  Edward H. Ip,et al.  Stochastic EM: method and application , 1996 .

[32]  J. L. Nolan,et al.  Numerical calculation of stable densities and distribution functions: Heavy tails and highly volatil , 1997 .

[33]  Zhenyu Zhou,et al.  Approximate maximum likelihood hyperparameter estimation for Gibbs priors , 1997, IEEE Trans. Image Process..

[34]  P. Green,et al.  Corrigendum: On Bayesian analysis of mixtures with an unknown number of components , 1997 .

[35]  L. C. Gilman,et al.  First-order statistics of pulsed-sinusoid backscatter from random media: basic elements of an exact treatment , 1997, IEEE Transactions on Ultrasonics, Ferroelectrics and Frequency Control.

[36]  Simon J. Godsill,et al.  Statistical reconstruction and analysis of autoregressive signals in impulsive noise using the Gibbs sampler , 1998, IEEE Trans. Speech Audio Process..

[37]  Xiao-Li Meng,et al.  Simulating Normalizing Constants: From Importance Sampling to Bridge Sampling to Path Sampling , 1998 .

[38]  Josiane Zerubia,et al.  Estimation of Markov random field prior parameters using Markov chain Monte Carlo maximum likelihood , 1999, IEEE Trans. Image Process..

[39]  Chrysostomos L. Nikias,et al.  Maximum-likelihood symmetric α-stable parameter estimation , 1999, IEEE Trans. Signal Process..

[40]  Christophe Chesnaud,et al.  Statistical Region Snake-Based Segmentation Adapted to Different Physical Noise Models , 1999, IEEE Trans. Pattern Anal. Mach. Intell..

[41]  P. Mohana Shankar,et al.  A general statistical model for ultrasonic backscattering from tissues , 2000, IEEE Transactions on Ultrasonics, Ferroelectrics and Frequency Control.

[42]  Athina P. Petropulu,et al.  Power-Law Shot Noise and Its Relationship To Long-Memory �-Stable Processes , 2000 .

[43]  Lei Wang,et al.  MRF parameter estimation by MCMC method , 2000, Pattern Recognit..

[44]  M. A. Kutay,et al.  On modeling biomedical ultrasound RF echoes using a power-law shot-noise model , 2001, IEEE Transactions on Ultrasonics, Ferroelectrics and Frequency Control.

[45]  J. Nolan,et al.  Maximum likelihood estimation and diagnostics for stable distributions , 2001 .

[46]  Matthias Lebertre,et al.  Echographie quantitative haute-fréquence : propriétés du derme humain et potentiel diagnostique , 2001 .

[47]  A. Childs,et al.  Exact sampling from nonattractive distributions using summary states. , 2000, Physical review. E, Statistical, nonlinear, and soft matter physics.

[48]  P. Shankar.  Ultrasonic tissue characterization using a generalized Nakagami model , 2001, IEEE Transactions on Ultrasonics, Ferroelectrics and Frequency Control.

[49]  B. Goldberg,et al.  Classification of ultrasonic B-mode images of breast masses using Nakagami distribution , 2001, IEEE Transactions on Ultrasonics, Ferroelectrics and Frequency Control.

[50]  Stan Z. Li,et al.  Markov Random Field Modeling in Image Analysis , 2001, Computer Science Workbench.

[51]  Tony F. Chan,et al.  Active contours without edges , 2001, IEEE Trans. Image Process..

[52]  M. Giger,et al.  Automatic segmentation of breast lesions on ultrasound. , 2001, Medical physics.

[53]  M. Srinivasan,et al.  Statistics of envelope of high-frequency ultrasonic backscatter from human skin in vivo , 2002, IEEE Transactions on Ultrasonics, Ferroelectrics and Frequency Control.

[54]  Balasundara I. Raju,et al.  High frequency ultrasonic characterization of human skin In vivo , 2002 .

[55]  Michael Brady,et al.  Segmentation of ultrasound B-mode images with intensity inhomogeneity correction , 2002, IEEE Transactions on Medical Imaging.

[56]  D. Balding,et al.  Approximate Bayesian computation in population genetics. , 2002, Genetics.

[57]  P. Moral,et al.  Sequential Monte Carlo samplers , 2002, cond-mat/0212648.

[58]  Edgar Arce Santana,et al.  Hidden Markov Measure Field Models for Image Segmentation , 2003, IEEE Trans. Pattern Anal. Mach. Intell..

[59]  Paul Marjoram,et al.  Markov chain Monte Carlo without likelihoods , 2003, Proceedings of the National Academy of Sciences of the United States of America.

[60]  Dimitris N. Metaxas,et al.  Combining low-, high-level and empirical domain knowledge for automated segmentation of ultrasonic breast lesions , 2003, IEEE Transactions on Medical Imaging.

[61]  Yihua Yu,et al.  MRF parameter estimation by an accelerated method , 2003, Pattern Recognit. Lett..

[62]  J. Sethian,et al.  FRONTS PROPAGATING WITH CURVATURE DEPENDENT SPEED: ALGORITHMS BASED ON HAMILTON-JACOB1 FORMULATIONS , 2003 .

[63]  P.M. Shankar,et al.  A compound scattering pdf for the ultrasonic echo envelope and its relationship to K and Nakagami distributions , 2003, IEEE Transactions on Ultrasonics, Ferroelectrics and Frequency Control.

[64]  Olivier Basset,et al.  Segmentation of ultrasound images--multiresolution 2D and 3D algorithm based on global and local statistics , 2003, Pattern Recognit. Lett..

[65]  A.P. Petropulu,et al.  Benign versus malignant classification of breast tumors based on the the PLSN model for the ultrasound RF echo and homomorphic filtering , 2004, The 26th Annual International Conference of the IEEE Engineering in Medicine and Biology Society.

[66]  Josiane Zerubia,et al.  Modeling SAR images with a generalization of the Rayleigh distribution , 2004, IEEE Transactions on Image Processing.

[67]  Frits Mastik,et al.  Fully automatic luminal contour segmentation in intracoronary ultrasound imaging-a statistical approach , 2004, IEEE Transactions on Medical Imaging.

[68]  Anthony N. Pettitt,et al.  Efficient recursions for general factorisable models , 2004 .

[69]  Henri Maître,et al.  A new statistical model for Markovian classification of urban areas in high-resolution SAR images , 2004, IEEE Transactions on Geoscience and Remote Sensing.

[70]  Dar-Ren Chen,et al.  Watershed segmentation for breast tumor in 2-D sonography. , 2004, Ultrasound in medicine & biology.

[71]  Zoubin Ghahramani,et al.  Bayesian Learning in Undirected Graphical Models: Approximate MCMC Algorithms , 2004, UAI.

[72]  David A. Clausi,et al.  Unsupervised segmentation of synthetic aperture Radar sea ice imagery using a novel Markov random field model , 2005, IEEE Transactions on Geoscience and Remote Sensing.

[73]  Mark W. Woolrich,et al.  Mixture models with adaptive spatial regularization for segmentation with an application to FMRI data , 2005, IEEE Transactions on Medical Imaging.

[74]  Torbjørn Eltoft,et al.  The Rician inverse Gaussian distribution: a new model for non-Rayleigh signal amplitude statistics , 2005, IEEE Transactions on Image Processing.

[75]  Hong Sun,et al.  An unsupervised segmentation method based on MPM for SAR images , 2005, IEEE Geoscience and Remote Sensing Letters.

[76]  B. Goldberg,et al.  Application of the compound probability density function for characterization of breast masses in ultrasound B scans , 2005, Physics in medicine and biology.

[77]  C. Lamberti,et al.  Maximum likelihood segmentation of ultrasound images with Rayleigh distribution , 2005, IEEE Transactions on Ultrasonics, Ferroelectrics and Frequency Control.

[78]  Devinder Thapa,et al.  Automatic Segmentation and Diagnosis of Breast Lesions Using Morphology Method Based on Ultrasound , 2005, FSKD.

[79]  J. Møller,et al.  An efficient Markov chain Monte Carlo method for distributions with intractable normalising constants , 2006 .

[80]  J. Rosenthal,et al.  Markov Chain Monte Carlo Methods , 2006 .

[81]  Hong Sun,et al.  Supervised SAR Image MPM Segmentation Based on Region-Based Hierarchical Model , 2006, IEEE Geoscience and Remote Sensing Letters.

[82]  Claus Skaanning,et al.  Markov Chain Monte Carlo Methods , 2006 .

[83]  Mohamed-Jalal Fadili,et al.  Region-Based Active Contours with Exponential Family Observations , 2009, Journal of Mathematical Imaging and Vision.

[84]  Josiane Zerubia,et al.  SAR image filtering based on the heavy-tailed Rayleigh model , 2006, IEEE Transactions on Image Processing.

[85]  Max Mignotte,et al.  Fusion of Hidden Markov Random Field Models and Its Bayesian Estimation , 2006, IEEE Transactions on Image Processing.

[86]  J. Alison Noble,et al.  Ultrasound image segmentation: a survey , 2006, IEEE Transactions on Medical Imaging.

[87]  K. Boone,et al.  Effect of skin impedance on image quality and variability in electrical impedance tomography: a model study , 1996, Medical and Biological Engineering and Computing.

[88]  Zoubin Ghahramani,et al.  MCMC for Doubly-intractable Distributions , 2006, UAI.

[89]  Jean Meunier,et al.  Intravascular ultrasound image segmentation: a three-dimensional fast-marching method based on gray level distributions , 2006, IEEE Transactions on Medical Imaging.

[90]  Sheila MacNeil,et al.  Progress and opportunities for tissue-engineered skin , 2007, Nature.

[91]  Jean-Michel Marin,et al.  Bayesian Core: A Practical Approach to Computational Bayesian Statistics , 2010 .

[92]  José M. Bioucas-Dias,et al.  Oil spill segmentation of SAR images via graph cuts , 2006, 2007 IEEE International Geoscience and Remote Sensing Symposium.

[93]  Max Mignotte,et al.  Image Denoising by Averaging of Piecewise Constant Simulations of Image Partitions , 2007, IEEE Transactions on Image Processing.

[94]  Rajeev Agrawal,et al.  Ultrasonic backscattering in tissue: characterization through Nakagami-generalized inverse Gaussian distribution , 2007, Comput. Biol. Medicine.

[95]  C. Robert,et al.  ABC likelihood-free methods for model choice in Gibbs random fields , 2008, 0807.2767.

[96]  Gustavo Carneiro,et al.  Detection and Measurement of Fetal Anatomies from Ultrasound Images using a Constrained Probabilistic Boosting Tree , 2008, IEEE Transactions on Medical Imaging.

[97]  Dominique Van de Sompel,et al.  Simultaneous reconstruction and segmentation algorithm for positron emission tomography and transmission tomography , 2008, 2008 5th IEEE International Symposium on Biomedical Imaging: From Nano to Macro.

[98]  Milind Rajadhyaksha,et al.  Skin imaging with reflectance confocal microscopy. , 2008, Seminars in cutaneous medicine and surgery.

[99]  Tong Fang,et al.  Shape-Driven Segmentation of the Arterial Wall in Intravascular Ultrasound Images , 2008, IEEE Transactions on Information Technology in Biomedicine.

[100]  Chongzhao Han,et al.  Heavy-Tailed Rayleigh Distribution: A New Tool for the Modeling of SAR Amplitude Images , 2008, IGARSS 2008 - 2008 IEEE International Geoscience and Remote Sensing Symposium.

[101]  Denis Friboulet,et al.  Prostate segmentation in echographic images: A variational approach using deformable super-ellipse and rayleigh distribution , 2008, 2008 5th IEEE International Symposium on Biomedical Imaging: From Nano to Macro.

[102]  Anthony N. Pettitt,et al.  Variational Bayes for estimating the parameters of a hidden Potts model , 2009, Stat. Comput..

[103]  Alfred O. Hero,et al.  Hierarchical Bayesian Sparse Image Reconstruction With Application to MRFM , 2008, IEEE Transactions on Image Processing.

[104]  Benoit Scherrer,et al.  Distributed Local MRF Models for Tissue and Structure Brain Segmentation , 2009, IEEE Transactions on Medical Imaging.

[105]  Bülent Sankur,et al.  Bayesian Separation of Images Modeled With MRFs Using MCMC , 2009, IEEE Transactions on Image Processing.

[106]  Ahror Belaid,et al.  Phase based level set segmentation of ultrasound images , 2009, 2009 9th International Conference on Information Technology and Applications in Biomedicine.

[107]  Alex R Cook,et al.  The International Journal of Biostatistics Inference in Epidemic Models without Likelihoods , 2011 .

[108]  Jean Meunier,et al.  Segmentation in Ultrasonic B-Mode Images of Healthy Carotid Arteries Using Mixtures of Nakagami Distributions and Stochastic Optimization , 2009, IEEE Transactions on Medical Imaging.

[109]  T. Hergum,et al.  Fast ultrasound imaging simulation in K-space , 2009, IEEE Transactions on Ultrasonics, Ferroelectrics and Frequency Control.

[110]  Laurent Risser,et al.  Fast bilinear extrapolation of 3D ising field partition function. application to fMRI image analysis. , 2009, 2009 16th IEEE International Conference on Image Processing (ICIP).

[111]  Bülent Sankur,et al.  Adaptive Langevin Sampler for Separation of $t$-Distribution Modelled Astrophysical Maps , 2010, IEEE Transactions on Image Processing.

[112]  B T Cox,et al.  k-Wave: MATLAB toolbox for the simulation and reconstruction of photoacoustic wave fields. , 2010, Journal of biomedical optics.

[113]  Jean-Yves Tourneret,et al.  Bayesian Orthogonal Component Analysis for Sparse Representation , 2009, IEEE Transactions on Signal Processing.

[114]  Robert D. Howe,et al.  Mitral Annulus Segmentation From 3D Ultrasound Using Graph Cuts , 2010, IEEE Transactions on Medical Imaging.

[115]  Laurent Risser,et al.  Spatially adaptive mixture modeling for analysis of fMRI time series , 2009, NeuroImage.

[116]  Alin Achim,et al.  Compressive sensing for ultrasound RF echoes using a-Stable Distributions , 2010, 2010 Annual International Conference of the IEEE Engineering in Medicine and Biology.

[117]  Hadj Batatia,et al.  A levy flight model for ultrasound in skin tissues , 2010, 2010 IEEE International Ultrasonics Symposium.

[118]  G. Cloutier,et al.  A critical review and uniformized representation of statistical distributions modeling the ultrasound echo envelope. , 2010, Ultrasound in medicine & biology.

[119]  Yu Li,et al.  Segmentation of SAR Intensity Imagery With a Voronoi Tessellation, Bayesian Inference, and Reversible Jump MCMC Algorithm , 2010, IEEE Transactions on Geoscience and Remote Sensing.

[120]  Hadj Batatia,et al.  An alpha-stable model for ultrasound speckle statistics in skin , 2010, 2010 Annual International Conference of the IEEE Engineering in Medicine and Biology.

[121]  A. Doucet,et al.  Particle Markov chain Monte Carlo methods , 2010 .

[122]  S. Sisson,et al.  Reversible jump Markov chain Monte Carlo , 2010, 1001.2055.

[123]  Nikolas P. Galatsanos,et al.  A Bayesian Framework for Image Segmentation With Spatially Varying Mixtures , 2010, IEEE Transactions on Image Processing.

[124]  Ali Mcheik.  Modélisation statistique du Speckle en OCT: application à la segmentation d'images de la peau. (Statistical modelization of Speckle in Optical Coherence Tomography (OCT) : application of skin images segmentation) , 2010 .

[125]  Max Mignotte,et al.  A Label Field Fusion Bayesian Model and Its Penalized Maximum Rand Estimator for Image Segmentation , 2010, IEEE Transactions on Image Processing.

[126]  Faming Liang,et al.  A double Metropolis–Hastings sampler for spatial models with intractable normalizing constants , 2010 .

[127]  Jean-Yves Tourneret,et al.  Labeling skin tissues in ultrasound images using a generalized Rayleigh mixture model , 2011, 2011 IEEE International Conference on Acoustics, Speech and Signal Processing (ICASSP).

[128]  Jean-François Giovannelli.  Ising field parameter estimation from incomplete and noisy data , 2011, 2011 18th IEEE International Conference on Image Processing.

[129]  P. Paramanathan,et al.  Tumor Growth in the Fractal Space-Time with Temporal Density , 2011 .

[130]  Jean-Yves Tourneret,et al.  Enhancing Hyperspectral Image Unmixing With Spatial Correlations , 2010, IEEE Transactions on Geoscience and Remote Sensing.

[131]  Arthur Gretton,et al.  Parallel Gibbs Sampling: From Colored Fields to Thin Junction Trees , 2011, AISTATS.

[132]  Laurent Risser,et al.  Min-max Extrapolation Scheme for Fast Estimation of 3D Potts Field Partition Functions. Application to the Joint Detection-Estimation of Brain Activity in fMRI , 2011, J. Signal Process. Syst..

[133]  Jean-Yves Tourneret,et al.  Segmentation of ultrasound images using a spatially coherent generalized Rayleigh mixture model , 2011, 2011 19th European Signal Processing Conference.

[134]  Gabriela Palacio,et al.  Unsupervised Classification of SAR Images Using Markov Random Fields and ${\cal G}_{I}^{0}$ Model , 2011, IEEE Geoscience and Remote Sensing Letters.

[135]  Sheng Xu,et al.  Adaptively Learning Local Shape Statistics for Prostate Segmentation in Ultrasound , 2011, IEEE Transactions on Biomedical Engineering.

[136]  Hadj Batatia,et al.  Modeling ultrasound echoes in skin tissues using symmetric α-stable processes , 2012, IEEE Transactions on Ultrasonics, Ferroelectrics and Frequency Control.

[137]  Dwarikanath Mahapatra,et al.  Integrating Segmentation Information for Improved MRF-Based Elastic Image Registration , 2012, IEEE Transactions on Image Processing.

[138]  Jiwen Lu,et al.  Abrupt Motion Tracking Via Intensively Adaptive Markov-Chain Monte Carlo Sampling , 2012, IEEE Transactions on Image Processing.

[139]  Jean-Michel Marin,et al.  Approximate Bayesian computational methods , 2011, Statistics and Computing.

[140]  Robert Azencott,et al.  Rigid-Motion-Invariant Classification of 3-D Textures , 2012, IEEE Transactions on Image Processing.

[141]  Jean-Yves Tourneret,et al.  Segmentation of Skin Lesions in 2-D and 3-D Ultrasound Images Using a Spatially Coherent Generalized Rayleigh Mixture Model , 2012, IEEE Transactions on Medical Imaging.

[142]  Masato Inoue,et al.  Posterior-Mean Super-Resolution With a Causal Gaussian Markov Random Field Prior , 2011, IEEE Transactions on Image Processing.

[143]  Carlos Alberola-López,et al.  A Markov Random Field Approach for Topology-Preserving Registration: Application to Object-Based Tomographic Image Interpolation , 2012, IEEE Transactions on Image Processing.

[144]  Vincent Loriette,et al.  Bayesian Estimation for Optimized Structured Illumination Microscopy , 2012, IEEE Transactions on Image Processing.

[145]  Richard G. Everitt,et al.  Bayesian Parameter Estimation for Latent Markov Random Fields and Social Networks , 2012, ArXiv.