Segmenting Ultrasound B-Mode Images Using RiIG Distributions and Stochastic Optimization

Authors: N. Mpofu, M. Sears

Abstract:

In this paper, we propose a novel algorithm for delineating the endocardial wall from a human heart ultrasound scan. We assume that the gray levels in the ultrasound images are independent and identically distributed random variables with different Rician Inverse Gaussian (RiIG) distributions. Both synthetic and real clinical data will be used for testing the algorithm. Algorithm performance will be evaluated using the expert radiologist evaluation of a soft copy of an ultrasound scan during the scanning process and secondly, doctor’s conclusion after going through a printed copy of the same scan. Successful implementation of this algorithm should make it possible to differentiate normal from abnormal soft tissue and help disease identification, what stage the disease is in and how best to treat the patient. We hope that an automated system that uses this algorithm will be useful in public hospitals especially in Third World countries where problems such as shortage of skilled radiologists and shortage of ultrasound machines are common. These public hospitals are usually the first and last stop for most patients in these countries.

Keywords: Endorcardial Wall, Rician Inverse Distributions, Segmentation, Ultrasound Images.

Digital Object Identifier (DOI): doi.org/10.5281/zenodo.1086797

References:

[1] T. McInerney and D. Terzopoulos, “Deformable models in medical image analysis in mathematical methods,” pp 171– 180. IEEE,1996.
[2]
[H. C. Inyiama Engr. V. C. Chijindu and Engr. G.Uzedhe, “Medcal imagesegmentation methodologies: A classified overview,”African Journal of Computing and ICT, 2006.
[3] T.F. Cootes, A. Hill, C.J. Taylor, and J. Haslam.“Use of active shape models for locating structures in medical images,”Image and vision computing.vol. 12, no. 6, pp..355–365, 1994.
[4] R.F. Wagner, S.W. Smith, J.M. Sandrik, and H. Lopez,. “Statistics of speckle in ultrasound b-scans,”IEEE Trans. SonisUltrasonics.,vol. 30, no. 3, pp. 156–163, 1983.
[5] P. Atkinson and MV Berry,. “Random noise in ultrasonic echoes diffracted by blood,”Journal of Physics A: Mathematical, Nuclear and General,vol.7, no. 11, pp. 1293, 2001.
[6] C.B. Burckhardt, “Speckle in ultrasound b-modescans. Sonics and Ultrasonics,”IEEETransactions, vol. 25, no. 1, pp.1–6, 1978.
[7] S.W. Flax, G.H. Glover, and N.J. Pelc, “Textural variations in b-mode ultrasonography: a stochastic model,” Ultrasonic Imaging,vol. 3, no. 3, pp.235–257, 1981.
[8] G. Kossoff, WJ Garrett, DA Carpenter, J. Jellins,and MJ Dadd,, “Principles and classification of soft tissues by grey scale echography,” Ultrasound in Medicine & Biology, vol. 2, no. 2, pp. 89–105, 1976.
[9] F.G Sommer, L.F Joynt, BA Carroll, and A. Macovski, “Ultrasonic characterization of abdominal tissues via digital analysis of backscattered waveforms,”Radiology,vol. 141, no. 3, pp. 811–817, 1981.
[10] L.F. Joynt, “A stochastic approach to ultrasonic tissue characterization,”PhD thesis, Stanford University, Carlifornia, USA, 1979.
[11] T. Eltoft. “The rician inverse Gaussian distribution: a new model for non-rayleigh signal amplitude statistics.”Image Processing,IEEE Transactions on, vol..14, no. 11, pp. 1722– 1735, 2005.
[12] O.Francois. “Global optimization with exploration/selection algorithms and simulated annealing,”The Annals of Applied Probability, vol. 12,no. 1, pp. 248–271, 2002.
[13] E. Brusseau, C.L. de Korte, F. Mastik, J. Schaar, and A.F.W. van derSteen, “Fully automated luminal contour segmentation in intracoronary ultrasound imaging-a statistical approach,” Medical Imaging, IEEE Transactionson,vol. 23, no. 5, pp. 554–566, 2004.
[14] M. Mignotte, J. Meunier, and J.C. Tardif, “Endocardial boundary estimation and tracking in echocardiographic images using deformable template and markov random fields,”Pattern Analysis & Applications,vol. 4, no. 4, pp. 256–271, 2001.
[15] J. Richy, “Compressive Sensing in Medical Ultrasonography”. PhD thesis, KTH, 2012.
[16] M. Kohli, Youtube.(2012, June 20), “Ultrasound Physics 2 – Interactions with tissue”,
[Video File], http://www.youtube.com/watch?v=Q1YPZ-04dag
[17] T.F. Cootes and C.J. Taylor, “Active shape models - smart snakes,” in Proc. British Machine Vision Conference,vol. 266275, Citeseer, 1992.
[18] T.F. Cootes, C.J. Taylor, D.H. Cooper, J. Graham, et al, “Active shape models-their training and application,” Computer vision and image understanding,vol. 61, no. 1, pp. 38– 59, 1995.
[19] T. Cootes.,“An introduction to active shape models,” Image Processing and Analysis, pp. 223–248, 2000.
[20] M.B. Stegmann and D.D. Gomez, “A brief introduction to statistical shape analysis,”Informatics and Mathematical Modelling, Technical University of Denmark, DTU, pp.15, 2002.
[21] K.W. Wan, K.M. Lam, and K.C. Ng, “An accurate active shape model for facial feature extraction,”Pattern Recognition Letters, vol. 26, no. 15, pp. 2409–2423, 2005.
[22] F. Destrempes, J. Meunier, M.F. Giroux, G. Soulez, and G. Cloutier, “Segmentation in ultrasonic¡ emphasis,” MedicalImaging, IEEE Transactions on, vol. 28, no. 2, pp. 215–229, 2009
[23] B.S. Garra D.G. Brown M.F. Insana, R.F. Wagner and T.H. Shawker, “Analysis of ultrasound image texture via generalized ricianstatistics,”Optical Engineering, vol. 25, no. 6, pp. 743–748,1986.
[24] P.M.Shankar. “A compound scattering pdf for the ultrasonic echo envelope and its relationship to k and nakagami distribution,”IEEETransactions,Ferroelect., Freq. Contol
[25] P.M. Shankar,“A general statistical model for ultrasonic scattering from tissues,”IEEE Trans. Ultrasonic.Ferroelect., Freq. Contol
[26] Y.Meiry, YouTube, (2012, Jan 13), “Lecture 13 (Basics of MRI, Ultrasound,”,
[Video File] http://www.youtube.com/watch?v=w3Ybm4A2GhI
[27] D.Kroon, University of Twente, Febuary2010.,
[Code]
[28] R. Werner, Allianz, Group Risk Controlling, (2006, May 1)
[Code], Germany
[29] J. L. Romeu, “The Chi-Square: a large Sample Goodness of Fit Test,” Reliability Analysis Center, vol. 10, no. 4, pp. 1-6, START 2003-2004.