Relevance Vector Machine Image Reconstruction Algorithm for Electrical Capacitance Tomography With Explicit Uncertainty Estimates

We present a Relevance Vector Machine (RVM) based algorithm for electrical capacitance tomography (ECT) applications that can concurrently provide image reconstruction results and uncertainty estimates about the reconstruction. To illustrate the RVM operation in ECT, we simulate typical ECT scenarios, making explicit the connection between the reconstructed pixel values and the corresponding uncertainty estimates in each case. We compare the RVM reconstruction performance with that of the Iterative Landweber Method (ILM) and the least absolute shrinkage and selection operator (LASSO) in all the considered scenarios. The results show that, in addition to the key advantage of providing uncertainty measures, RVM can achieve similar reconstruction results with either lower or similar computational complexity.

[1]  William R B Lionheart.  EIT reconstruction algorithms: pitfalls, challenges and recent developments. , 2004, Physiological measurement.

[2]  M. Neumayer,et al.  Electrical Capacitance Tomography: Current sensors/algorithms and future advances , 2012, 2012 IEEE International Instrumentation and Measurement Technology Conference Proceedings.

[3]  M. Neumayer,et al.  Current Reconstruction Algorithms in Electrical Capacitance Tomography , 2011 .

[4]  A. Massa,et al.  Microwave Imaging Within the First-Order Born Approximation by Means of the Contrast-Field Bayesian Compressive Sensing , 2012, IEEE Transactions on Antennas and Propagation.

[5]  F. Schmitt,et al.  Linear inverse problems in imaging , 2008, IEEE Signal Processing Magazine.

[6]  Robert G. Aykroyd,et al.  Statistical image reconstruction , 2015 .

[7]  Trevor Hastie,et al.  Statistical Learning with Sparsity: The Lasso and Generalizations , 2015 .

[8]  Wuqiang Yang,et al.  An image-reconstruction algorithm based on Landweber's iteration method for electrical-capacitance tomography , 1999 .

[9]  Paolo Rocca,et al.  A Bayesian-Compressive-Sampling-Based Inversion for Imaging Sparse Scatterers , 2011, IEEE Transactions on Geoscience and Remote Sensing.

[10]  Zhang Cao,et al.  An image reconstruction algorithm based on total variation with adaptive mesh refinement for ECT , 2007 .

[11]  Karl J. Friston,et al.  Multiple sparse priors for the M/EEG inverse problem , 2008, NeuroImage.

[12]  Daniel Watzenig,et al.  A review of statistical modelling and inference for electrical capacitance tomography , 2009 .

[13]  Geoff K. Nicholls,et al.  Prior modeling and posterior sampling in impedance imaging , 1998, Optics & Photonics.

[14]  Mário A. T. Figueiredo,et al.  Gradient Projection for Sparse Reconstruction: Application to Compressed Sensing and Other Inverse Problems , 2007, IEEE Journal of Selected Topics in Signal Processing.

[15]  Liang-Shih Fan,et al.  Electrical Capacitance Volume Tomography , 2007, IEEE Sensors Journal.

[16]  Radford M. Neal.  Pattern Recognition and Machine Learning , 2007, Technometrics.

[17]  Weifu Fang.  Reconstruction of permittivity profile from boundary capacitance data , 2006, Appl. Math. Comput..

[18]  Weifu Fang,et al.  A nonlinear image reconstruction algorithm for electrical capacitance tomography , 2004 .

[19]  Albert Tarantola,et al.  Inverse problem theory - and methods for model parameter estimation , 2004 .

[20]  Paolo Rocca,et al.  Bayesian Compressive Sensing Approaches for the Reconstruction of Two-Dimensional Sparse Scatterers Under TE Illuminations , 2013, IEEE Transactions on Geoscience and Remote Sensing.

[21]  Fernando L. Teixeira,et al.  Adaptive Electrical Capacitance Volume Tomography , 2014, IEEE Sensors Journal.

[22]  Manuchehr Soleimani,et al.  Nonlinear image reconstruction for electrical capacitance tomography using experimental data , 2005 .

[23]  A Massa,et al.  Bayesian compressive optical imaging within the Rytov approximation. , 2012, Optics letters.

[24]  Artur J. Jaworski,et al.  The design of an electrical capacitance tomography sensor for use with media of high dielectric permittivity , 2000 .

[25]  Q. Marashdeh,et al.  Nonlinear forward problem solution for electrical capacitance tomography using feed-forward neural network , 2006, IEEE Sensors Journal.

[26]  Wuqiang Yang,et al.  Design of electrical capacitance tomography sensors , 2010 .

[27]  F. L. Teixeira,et al.  Bayesian compressive sensing for ultrawideband inverse scattering in random media , 2013, 1401.1092.

[28]  R. Tibshirani.  Regression Shrinkage and Selection via the Lasso , 1996 .

[29]  Y. Pi,et al.  Bayesian compressive sensing in synthetic aperture radar imaging , 2012 .

[30]  Mario Bertero,et al.  Introduction to Inverse Problems in Imaging , 1998 .

[31]  Fernando L. Teixeira,et al.  Acceleration of Electrical Capacitance Volume Tomography Imaging by Fourier-Based Sparse Representations , 2018, IEEE Sensors Journal.

[32]  Thomas Bretterklieber,et al.  Statistical solution of inverse problems using a state reduction , 2019, COMPEL - The international journal for computation and mathematics in electrical and electronic engineering.

[33]  Leslie M. Collins,et al.  Texture Features for Antitank Landmine Detection Using Ground Penetrating Radar , 2007, IEEE Transactions on Geoscience and Remote Sensing.

[34]  Trevor A. York.  Status of electrical tomography in industrial applications , 2001, J. Electronic Imaging.

[35]  Michael E. Tipping,et al.  Fast Marginal Likelihood Maximisation for Sparse Bayesian Models , 2003 .

[36]  Martin Burger,et al.  Inverse problems in imaging , 2013 .

[37]  L. Carin,et al.  Inverse scattering with sparse Bayesian vector regression , 2004 .

[38]  Lihui Peng,et al.  Image reconstruction algorithms for electrical capacitance tomography , 2003 .

[39]  I. Netuka,et al.  Mean Value Property and Harmonic Functions , 1994 .

[40]  E. Somersalo,et al.  Statistical inversion and Monte Carlo sampling methods in electrical impedance tomography , 2000 .

[41]  Daniel Watzenig.  Bayesian inference for inverse problems – statistical inversion , 2007, Elektrotech. Informationstechnik.

[42]  A. E. Foudaa,et al.  Ultra-wideband microwave imaging of breast cancer tumors via Bayesian inverse scattering , 2014 .

[43]  Stephen P. Boyd,et al.  Distributed Optimization and Statistical Learning via the Alternating Direction Method of Multipliers , 2011, Found. Trends Mach. Learn..

[44]  Fernando L. Teixeira,et al.  Enhancing Resolution of Electrical Capacitive Sensors for Multiphase Flows by Fine-Stepped Electronic Scanning of Synthetic Electrodes , 2019, IEEE Transactions on Instrumentation and Measurement.

[45]  Colin Fox,et al.  Fast Sampling in a Linear-Gaussian Inverse Problem , 2015, SIAM/ASA J. Uncertain. Quantification.

[46]  P. Stark.  Inverse problems as statistics , 2002 .

[47]  A. Mohammad-Djafari,et al.  Inverse scattering in a Bayesian framework: application to microwave imaging for breast cancer detection , 2014 .

[48]  A. Stuart,et al.  The Bayesian Approach to Inverse Problems , 2013, 1302.6989.

[49]  Rainer Goebel,et al.  Predicting EEG single trial responses with simultaneous fMRI and Relevance Vector Machine regression , 2011, NeuroImage.

[50]  Fei Wang,et al.  Electrical Capacitance Volume Tomography: Design and Applications , 2010, Sensors.

[51]  Thomas Bretterklieber,et al.  PCA Based State Reduction for Inverse Problems Using Prior Information , 2017 .

[52]  George Eastman House,et al.  Sparse Bayesian Learning and the Relevan e Ve tor Ma hine , 2001 .

[53]  Daniel Watzenig,et al.  Reconstruction of inhomogeneities in fluids by means of capacitance tomography , 2003 .

[54]  S. Mylvaganam,et al.  Electrical Capacitance Tomography—Sensor Models, Design, Simulations, and Experimental Verification , 2006, IEEE Sensors Journal.

[55]  Hubert Zangl,et al.  Artefact reduction in fast Bayesian inversion in electrical tomography , 2015 .

[56]  Lawrence Carin,et al.  Bayesian Compressive Sensing , 2008, IEEE Transactions on Signal Processing.

[57]  Johnathan M. Bardsley,et al.  MCMC-Based Image Reconstruction with Uncertainty Quantification , 2012, SIAM J. Sci. Comput..

[58]  Federico Viani,et al.  Sparse scatterers imaging through approximated multitask compressive sensing strategies , 2013 .

[59]  L. Flatto.  The converse of Gauss's theorem for harmonic functions , 1965 .

[60]  Liang-Shih Fan,et al.  Electrical capacitance tomography , 2015 .

[61]  C. Fox,et al.  Accelerated Markov chain Monte Carlo sampling in electrical capacitance tomography , 2011 .