A homomorphic non-subsampled contourlet transform based ultrasound image despeckling by novel thresholding function and self-organizing map

• Autorzy: Singh Prabhishek , Diwakar Manoj , Singh Shilpi , Kumar Sarvesh , Tripathi Amrendra , Shankar Achyut

Identyfikatory

DOI

10.1016/j.bbe.2022.03.003

• Języki publikacji: EN

Abstrakty

EN

The speckle noise leaves an adverse effect on ultrasound images due to which loss of information occurs. Hence this paper proposes a homomorphic Non-Subsampled Contourlet Transform (NSCT) based ultrasound image despeckling technique using a novel thresholding function, bilateral filter, and self-organizing map (SOM). The bilateral filter is utilized over the low-pass NSCT sub-band for speckle component removal and sharp features. To get better noise suppression and edge preservation, a novel thresholding function is proposed and performed over the high-pass NSCT sub-band. In the proposed method, Kohonen’s SOM is implemented as a post-processing step for deblurring purposes. The significance of the proposed scheme is also tested where it was found that using Kohonen’s SOM as post-processing works better than without post-processing. Experimental outcomes were also evaluated on real speckled ultrasound images and synthetic added speckled noisy images. The results are evaluated and compared using visual analysis and performance metrics using with and without reference images. For more critical analysis, intensity profile along a line and experts observation were also evaluated to find the performance analysis of the proposed methodology. From all experimental and comparative evaluations, it was found that the proposed approach gives better outcomes compared to similar and recent methods.

Słowa kluczowe

EN

nonsubsampled contourlet transform; Kohonen’s SOM; bilateral filter

PL

transformacja konturowa; mapa samoorganizująca; filtr dwustronny

• Wydawca: Nałęcz Institute of Biocybernetics and Biomedical Engineering of the Polish Academy of Sciences ; Elsevier
• Czasopismo: Biocybernetics and Biomedical Engineering
• Rocznik: 2022
• Tom: Vol. 42, no. 2
• Strony: 512--528
• Opis fizyczny: Bibliogr. 82 poz., rys., tab., wykr.

Twórcy

autor

Singh Prabhishek

• Amity School of Engineering and Technology, Amity University Uttar Pradesh Noida, India

autor

Diwakar Manoj

• Department of CSE, Graphic Era Deemed to be University, Dehradun, Uttarakhand 248001, India

autor

Singh Shilpi

• Department of Computer Science and Engineering, ASET, Amity University Patna, India

autor

Kumar Sarvesh

• Department of Computer Science & Engineering, Babu Banarasi Das University, Lucknow, India

autor

Tripathi Amrendra

• Department of CSE, UPES, Dehradun, India

autor

Shankar Achyut

• Amity School of Engineering and Technology, Amity University Uttar Pradesh Noida, India

Bibliografia

• [1] Michailovich OV, Tannenbaum A. Despeckling of medical ultrasound images. IEEE Trans Ultrason Ferroelectr Freq Control 2006;53(1):64–78.
• [2] Jensen JA. Medical ultrasound imaging. Prog Biophys Mol Biol 2007;93(1–3):153–65.
• [3] Ragesh NK, Anil AR, Rajesh R. Digital image denoising in medical ultrasound images: a survey. InIcgst Aiml-11 Conference, Dubai, UAE 2011 Apr 12 (Vol. 12, p. 14).
• [4] Khare A, Khare M, Jeong Y, Kim H, Jeon M. Despeckling of medical ultrasound images using Daubechies complex wavelet transform. Signal Process 2010;90(2):428–39.
• [5] Shams R, Hartley R, Navab N. Real-time simulation of medical ultrasound from CT images. InInternational Conference on Medical Image Computing and ComputerAssisted Intervention 2008 Sep 6 (pp. 734-741). Springer, Berlin, Heidelberg.
• [6] Hiremath PS, Akkasaligar PT, Badiger S, Gunarathne G. Speckle noise reduction in medical ultrasound images. Advancements and breakthroughs in ultrasound imaging. 2013 Jun 5;1(8):1-8.
• [7] Narayanan SK, Wahidabanu RS. A view on despeckling in ultrasound imaging. Int J Signal Process Image Process Pattern Recog 2009;2(3):85–98.
• [8] Singh P, Diwakar M, Shankar A, Shree R, Kumar M. A review on SAR image and its despeckling. Arch Comput Methods Eng 2021;28(7):4633–53.
• [9] Lee JS, Wen JH, Ainsworth TL, Chen KS, Chen AJ. Improved sigma filter for speckle filtering of SAR imagery. IEEE Trans Geosci Remote Sens 2008;47(1):202–13.
• [10] Yommy AS, Liu R, Wu S. SAR image despeckling using refined Lee filter. In2015 7th International Conference on Intelligent Human-Machine Systems and Cybernetics 2015 Aug 26 (Vol. 2, pp. 260-265). IEEE.
• [11] Marin A, Pothier J, Zimmermann K, Gibrat JF. FROST: a filter-based fold recognition method. Proteins Struct Funct Bioinf 2002;49(4):493–509.
• [12] Akl A, Tabbara K, Yaacoub C. An enhanced Kuan filter for suboptimal speckle reduction. In2012 2nd International Conference on Advances in Computational Tools for Engineering Applications (ACTEA) 2012 Dec 12 (pp. 91-95). IEEE.
• [13] Bartyzel K. Adaptive kuwahara filter. SIViP 2016;10(4):663–70.
• [14] Baraldi A, Parmiggiani F. A refined gamma MAP SAR speckle filter with improved geometrical adaptivity. IEEE Trans Geosci Remote Sens 1995;33(5):1245–57.
• [15] Meer P, Park RH, Cho KJ. Multiresolution adaptive image smoothing. CVGIP: Graphical Models and Image Processing 1994;56(2):140–8.
• [16] Aiazzi B, Alparone L, Baronti S. Multiresolution localstatistics speckle filtering based on a ratio Laplacian pyramid. IEEE Trans Geosci Remote Sens 1998;36(5):1466–76.
• [17] Jirik R, Taxt T. High-resolution ultrasonic imaging using two-dimensional homomorphic filtering. IEEE Trans Ultrason Ferroelectr Freq Control 2006;53(8):1440–8.
• [18] Dhinagar NJ, Celenk M. Ultrasound medical image enhancement and segmentation using adaptive homomorphic filtering and histogram thresholding. In2012 IEEE-EMBS Conference on Biomedical Engineering and Sciences 2012 Dec 17 (pp. 349-353). IEEE.
• [19] Benameur S, Mignotte M, Lavoie F. An homomorphic filtering and expectation maximization approach for the point spread function estimation in ultrasound imaging. InImage Processing: Algorithms and Systems X; and Parallel Processing for Imaging Applications II 2012 Feb 2 (Vol. 8295, pp. 245-252). SPIE.
• [20] Taxt T. Restoration of medical ultrasound images using two-dimensional homomorphic deconvolution. IEEE Trans Ultrason Ferroelectr Freq Control 1995;42(4):543–54.
• [21] Santos CA, Martins DL, Mascarenhas ND. Ultrasound image despeckling using stochastic distance-based BM3D. IEEE Trans Image Process 2017;26(6):2632–43.
• [22] Sagheer SV, George SN. Ultrasound image despeckling using low rank matrix approximation approach. Biomed Signal Process Control 2017;1(38):236–49.
• [23] Cui W, Li M, Gong G, Lu K, Sun S, Dong F. Guided trilateral filter and its application to ultrasound image despeckling. Biomed Signal Process Control 2020;1(55) 101625.
• [24] Baselice F. Ultrasound image despeckling based on statistical similarity. Ultrasound Med Biol 2017;43(9):2065–78.
• [25] Astola J, Koskinen L, Neuvo Y. Statistical properties of discrete morphological filters. InMathematical Morphology in Image Processing 2018 Oct 3 (pp. 93-120). CRC Press.
• [26] Nakashizuka M, Kobayashi KI, Ishikawa T, Itoi K. Convex filter networks based on morphological filters and their application to image noise and mask removal. IEICE Trans Fundamentals Electron Commun Comput Sci 2017;100 (11):2238–47.
• [27] Ruchay A, Kober V. Removal of impulse noise clusters from color images with local order statistics. InApplications of Digital Image Processing XL 2017 Sep 19 (Vol. 10396, p. 1039626). International Society for Optics and Photonics.
• [28] Wan X, Zhao C, Wang Y, Liu W. Stacked sparse autoencoder in hyperspectral data classification using spectral-spatial, higher order statistics and multifractal spectrum features. Infrared Phys Technol 2017;1(86):77–89.
• [29] Singh P, Shree R. A new homomorphic and method noise thresholding based despeckling of SAR image using anisotropic diffusion. J King Saud Univ-Comput Inform Sci 2020;32(1):137–48.
• [30] Mei K, Hu B, Fei B, Qin B. Phase asymmetry ultrasound despeckling with fractional anisotropic diffusion and total variation. IEEE Trans Image Process 2019;19(29):2845–59.
• [31] Schou J, Skriver H. Restoration of polarimetric SAR images using simulated annealing. IEEE Trans Geosci Remote Sens 2001;39(9):2005–16.
• [32] Fatnassi S, Yahia M, Ali T, Mortula MM. SAR Speckle Filtering Using Hybrid NonLocal Sigma Filter. In2021 18th International Multi-Conference on Systems, Signals & Devices (SSD) 2021 Mar 22 (pp. 463-467). IEEE.
• [33] Sharma R, Panigrahi RK. Stokes based sigma filter for despeckling of compact PolSAR data. IET Radar Sonar Navig 2018;12(4):475–83.
• [34] Joel T, Sivakumar R. Nonsubsampled contourlet transform with cross-guided bilateral filter for despeckling of medical ultrasound images. Int J Imaging Syst Technol 2021;31 (2):763–77.
• [35] Liu L, Zhou F, Chen J, Yang X, Jia L, Dong Z, et al. Despeckling PolSAR images with an adaptive bilateral filter. J Appl Remote Sens 2017;11(2) 020501.
• [36] Garg A, Khandelwal V. Despeckling of medical ultrasound images using fast bilateral filter and NeighShrinkSure filter in wavelet domain. InAdvances in Signal Processing and Communication 2019 (pp. 271-280). Springer, Singapore.
• [37] Song P, Trzasko JD, Manduca A, Huang R, Kadirvel R, Kallmes DF, et al. Improved super-resolution ultrasound microvessel imaging with spatiotemporal nonlocal means filtering and bipartite graph-based microbubble tracking. IEEE Trans Ultrason Ferroelectr Freq Control 2017;65(2):149–67.
• [38] Zhu L, Fu CW, Brown MS, Heng PA. A non-local low-rank framework for ultrasound speckle reduction. InProceedings of the IEEE conference on computer vision and pattern recognition 2017 (pp. 5650-5658).
• [39] Zhou Y, Zang H, Xu S, He H, Lu J, Fang H. An iterative speckle filtering algorithm for ultrasound images based on bayesian nonlocal means filter model. Biomed Signal Process Control 2019;1(48):104–17.
• [40] Wang S, Huang TZ, Zhao XL, Mei JJ, Huang J. Speckle noise removal in ultrasound images by first-and second-order total variation. Numerical Algorithms 2018;78(2):513–33.
• [41] Hacini M, Hachouf F, Djemal K. A new speckle filtering method for ultrasound images based on a weighted multiplicative total variation. Signal Process 2014;1 (103):214–29.
• [42] Rawat N, Singh M, Singh B. Wavelet and total variation based method using adaptive regularization for speckle noise reduction in ultrasound images. Wireless Pers Commun 2019;106(3):1547–72.
• [43] Shafiei A, Beheshti M, Yazdian E. Distributed compressed sensing for despeckling of SAR images. Digital Signal Process 2018;1(81):138–54.
• [44] Sahu S, Singh HV, Kumar B, Singh AK. De-noising of ultrasound image using Bayesian approached heavy-tailed Cauchy distribution. Multimedia Tools and Applications 2019;78(4):4089–106.
• [45] Shahdoosti HR, Rahemi Z. Edge-preserving image denoising using a deep convolutional neural network. Signal Process 2019;1(159):20–32.
• [46] Joel T, Sivakumar R. An extensive review on Despeckling of medical ultrasound images using various transformation techniques. Appl Acoust 2018;1(138):18–27.
• [47] Jubairahmed L, Satheeskumaran S, Venkatesan C. Contourlet transform based adaptive nonlinear diffusion filtering for speckle noise removal in ultrasound images. Cluster Computing 2019;22(5):11237–46.
• [48] Joel T, Yogapriya J. Contrast enhancementusing non-subsampled contourlet transform with histogram equalization for ultrasound images. Eur J Mol Clin Med;7 (03):2020.
• [49] Shahdoosti HR, Rahemi Z. A maximum likelihood filter using non-local information for despeckling of ultrasound images. Mach Vis Appl 2018;29(4):689–702.
• [50] Dey J, Hasan M. Multiframe-based Adaptive Despeckling Algorithm for Ultrasound B-mode Imaging with Superior Edge and Texture. arXiv preprint arXiv:1912.00815. 2019 Dec 2.
• [51] Wang C, Xu L, Clausi DA, Wong A. A Bayesian joint decorrelation and despeckling of SAR imagery. IEEE Geosci Remote Sens Lett 2019;16(9):1393–7.
• [52] Paul A, Mukherjee DP, Acton ST. Speckle removal using diffusion potential for optical coherence tomography images. IEEE J Biomed Health Inf 2018;23(1):264–72.
• [53] Yu Y, Acton ST. Speckle reducing anisotropic diffusion. IEEE Trans Image Process 2002;11(11):1260–70.
• [54] Feng W, Lei H, Gao Y. Speckle reduction via higher order total variation approach. IEEE Trans Image Process 2014;23 (4):1831–43.
• [55] Randhawa SK, Sunkaria RK, Puthooran E. Despeckling of ultrasound images using novel adaptive wavelet thresholding function. Multidimension Syst Signal Process 2019;30(3):1545–61.
• [56] Huang S, Zhou P, Shi H, Sun Y, Wan S. Image speckle noise denoising by a multi-layer fusion enhancement method based on block matching and 3D filtering. The Imaging Science Journal 2019;67(4):224–35.
• [57] Abazari R, Lakestani M. Non-subsampled shearlet transform and log-transform methods for despeckling of medical ultrasound images. Informatica 2019;30(1):1–9.
• [58] Diwakar M, Singh P. CT image denoising using multivariate model and its method noise thresholding in non-subsampled shearlet domain. Biomed Signal Process Control 2020;1(57) 101754.
• [59] Mastriani M. Denoising based on wavelets and deblurring via self-organizing map for Synthetic Aperture Radar images. International Journal of Signal Processing 2005;2(4):226–35.
• [60] Candes EJ, Donoho DL. Curvelets: A surprisingly effective nonadaptive representation for objects with edges. Stanford Univ Ca Dept of Statistics; 2000 Jan 1.
• [61] Do MN. Directional multiresolution image representations. EPFL 2002.
• [62] Do MN, Vetterli M. The contourlet transform: an efficient directional multiresolution image representation. IEEE Trans Image Process 2005;14(12):2091–106.
• [63] Da Cunha AL, Zhou J, Do MN. The nonsubsampled contourlet transform: theory, design, and applications. IEEE Trans Image Process 2006;15(10):3089–101.
• [64] Ni W, Guo B, Yan Y, Yang L. Speckle suppression for sar images based on adaptive shrinkage in contourlet domain. In2006 6th World Congress on Intelligent Control and Automation 2006 Jun 21 (Vol. 2, pp. 10017-10021). IEEE.
• [65] Chen BH, Tseng YS, Yin JL. Gaussian-adaptive bilateral filter. IEEE Signal Process Lett 2020;18(27):1670–4.
• [66] Bedi AK, Sunkaria RK, Mittal D. Ultrasound image despeckling and enhancement using modified multiscale anisotropic diffusion model in non-subsampled shearlet domain. Computer J 2021;64(12):1785–800.
• [67] Hadj Fredj A, Malek J. FPGA-accelerated anisotropic diffusion filter based on SW/HW-codesign for medical images. J Real-Time Image Proc 2021;18(6):2429–40.
• [68] Zhu L, Wang W, Qin J, Wong KH, Choi KS, Heng PA. Fast feature-preserving speckle reduction for ultrasound images via phase congruency. Signal Process 2017;1(134):275–84.
• [69] Zhu L, Wang W, Li X, Wang Q, Qin J, Wong KH, et al. Featurepreserving ultrasound speckle reduction via L0 minimization. Neurocomputing 2018;14(294):48–60.
• [70] Ambrosanio M, Baselice F, Ferraioli G, Pascazio V. Ultrasound despeckling based on non local means. InEMBEC & NBC 2017 2017 Jun 11 (pp. 109-112). Springer, Singapore.
• [71] Ambrosanio M, Kanoun B, Baselice F. wksr-nlm: an ultrasound despeckling filter based on patch ratio and statistical similarity. IEEE Access 2020;7(8):150773–83.
• [72] Ma X, Wang C, Yin Z, Wu P. SAR image despeckling by noisy reference-based deep learning method. IEEE Trans Geosci Remote Sens 2020;58(12):8807–18.
• [73] Vitale S, Ferraioli G, Pascazio V. Multi-objective cnn-based algorithm for sar despeckling. IEEE Trans Geosci Remote Sens 2020;59(11):9336–49.
• [74] https://www.ultrasoundcases.info/cases/musculo-skeletalbone-muscle-nerves-and-other-soft-tissues/soft-tissues/ miscellaneous-benign-soft-tissues-lesions/.
• [75] https://www.aylward.org/notes/open-access-medical-imagerepositories.
• [76] https://www.kaggle.com/aryashah2k/breast-ultrasoundimages-dataset.
• [77] Singh P, Mukundan R, de Ryke R. Synthetic models of ultrasound image formation for speckle noise simulation and analysis. In 2017 International Conference on Signals and Systems (ICSigSys) 2017 May 16 (pp. 278-284). IEEE.
• [78] Hiremath PS, Akkasaligar PT, Badiger S. Speckle reducing contourlet transform for medical ultrasound images. Int J Compt Inf Engg 2010;4(4):284–91.
• [79] Zhang Q, Wang Y, Wang W, Ma J, Qian J, Ge J. Automatic segmentation of calcifications in intravascular ultrasound images using snakes and the contourlet transform. Ultrasound Med Biol 2010;36(1):111–29.
• [80] Hiremath PS, Akkasaligar PT, Badiger S. Performance comparison of wavelet transform and contourlet transform based methods for despeckling medical ultrasound images. Int J Comput Applications 2011;26(9):34–41.
• [81] Sun Q, Jiao L, Hou B. Synthetic aperture radar image despeckling via spatially adaptive shrinkage in the nonsubsampled contourlet transform domain. J Electron Imaging 2008;17(1) 013013.
• [82] Zhang Q, Han H, Ji C, Yu J, Wang Y, Wang W. Gabor-based anisotropic diffusion for speckle noise reduction in medical ultrasonography. JOSA A 2014;31(6):1273–83.