Abstract
This work presents a new ultrasound image despeckling method based on the maximum likelihood principle that effectively exploits non-local information for estimating noise-free pixels. First, a new maximum likelihood filter is proposed which uses neighborhood information to despeckle images. For this purpose, the general speckle model is used in the log-likelihood function and despeckled pixels are obtained by maximizing this function. Second, the proposed filter is developed to use non-local information such that the distribution of each noisy pixel is weighted according to the statistical distance between the patch of the noisy pixel and that of the target pixel. Because it is optimally designed for ultrasound images, the Pearson distance is used to measure the statistical distance between the patches. A series of experiments are conducted on three different ultrasound images and one synthetic image. Subjective evaluations show that the proposed method is able to preserve edges and structural details of the image and objective evaluations using equivalent number of looks, natural image quality evaluator, peak signal-to-noise ratio, mean preservation, and structural similarity confirm that the proposed method can achieve superior performance.
Similar content being viewed by others
References
Mittal, D., Kumar, V., Saxena, S.C., Khandelwal, N., Kalra, N.: Enhancement of the ultrasound images by modified anisotropic diffusion method. Med. Biol. Eng. Comput. 48(12), 1281–1291 (2010)
Gupta, D., Anand, R.S., Tyagi, B.: Ripplet domain non-linear filtering for speckle reduction in ultrasound medical images. Biomed. Signal Process. Control 10, 79–91 (2014)
Sudeep, P.V., Palanisamy, P., Rajan, J., Baradaran, H., Saba, L., Gupta, A., Suri, J.S.: Speckle reduction in medical ultrasound images using an unbiased non-local means method. Biomed. Signal Process. Control 28, 1–8 (2016)
Buades, A., Coll, B., Morel, J.M.: A review of image denoising algorithms, with a new one. Multiscale Model. Simul. 4(2), 490–530 (2005)
Shahdoosti, H.R., Hazavei, S.M.: Image denoising in dual contourlet domain using hidden Markov tree models. Digit. Signal Proc. 67, 17–29 (2017)
Coupé, P., Hellier, P., Kervrann, C., Barillot, C.: Nonlocal means-based speckle filtering for ultrasound images. IEEE Trans. Image Process. 18(10), 2221–2229 (2009)
Lee, J.S.: Digital image enhancement and noise filtering by use of local statistics. IEEE Trans. Pattern Anal. Mach. Intell. 2, 165–168 (1980)
Frost, V.S., Stiles, J.A., Shanmugan, K.S., Holtzman, J.C.: A model for radar images and its application to adaptive digital filtering of multiplicative noise. IEEE Trans. Pattern Anal. Mach. Intell. 2, 157–166 (1982)
Kuan, D.T., Sawchuk, A.A., Strand, T.C., Chavel, P.: Adaptive noise smoothing filter for images with signal-dependent noise. IEEE Trans. Pattern Anal. Mach. Intell. 2, 165–177 (1985)
Lopes, A., Touzi, R., Nezry, E.: Adaptive speckle filters and scene heterogeneity. IEEE Trans. Geosci. Remote Sens. 28(6), 992–1000 (1990)
Qiu, F., Berglund, J., Jensen, J.R., Thakkar, P., Ren, D.: Speckle noise reduction in SAR imagery using a local adaptive median filter. GISci. Remote Sens. 41(3), 244–266 (2004)
Vanithamani, R., Umamaheswari, G., Ezhilarasi, M.: Modified hybrid median filter for effective speckle reduction in ultrasound images. In: Recent Advances in Networking, VLSI and Signal Processing, pp. 166–171 (2010)
Yu, Y., Acton, S.T.: Speckle reducing anisotropic diffusion. IEEE Trans. Image Process. 11(11), 1260–1270 (2002)
Aja-Fernández, S., Alberola-López, C.: On the estimation of the coefficient of variation for anisotropic diffusion speckle filtering. IEEE Trans. Image Process. 15(9), 2694–2701 (2006)
Vegas-Sánchez-Ferrero, G., Aja-Fernández, S., Martín-Fernández, M., Frangi, A.F., Palencia, C.: Probabilistic-driven oriented speckle reducing anisotropic diffusion with application to cardiac ultrasonic images. In: International Conference on Medical Image Computing and Computer-Assisted Intervention, pp. 518–525. Springer, Berlin (2010)
Bini, A.A., Bhat, M.S.: Despeckling low SNR, low contrast ultrasound images via anisotropic level set diffusion. Multidimens. Syst. Signal Process. 25(1), 41–65 (2014)
Shao, D., Zhou, T., Liu, F., Yi, S., Xiang, Y., Ma, L., Xiong, X., He, J.: Ultrasound speckle reduction based on fractional order differentiation. J. Med. Ultrason. 44(3), 227–237 (2017)
Wang, S., Huang, T.Z., Zhao, X.L., Mei, J.J., Huang, J.: Speckle noise removal in ultrasound images by first-and second-order total variation. Numer. Algorithms 1–21 (2017)
Singh, C., Ranade, S.K., Singh, K.: Invariant moments and transform-based unbiased nonlocal means for denoising of MR images. Biomed. Signal Process. Control 30, 13–24 (2016)
Coupé, P., Hellier, P., Kervrann, C., Barillot, C.: May. Bayesian non local means-based speckle filtering. In: 5th IEEE International Symposium on Biomedical Imaging: From Nano to Macro, 2008. ISBI 2008, pp. 1291–1294. IEEE (2008)
Baselice, F.: Ultrasound image despeckling based on statistical similarity. Ultrasound Med. Biol. 43(9), 2065–2078 (2017)
Ni, W., Gao, X.: Despeckling of SAR image using generalized guided filter with Bayesian nonlocal means. IEEE Trans. Geosci. Remote Sens. 54(1), 567–579 (2016)
Mingliang, X., Pei, L., Mingyuan, L., Hao, F., Hongling, Z., Bing, Z., Yusong, L., Liwei, Z.: Medical image denoising by parallel non-local means. Neurocomputing 195, 117–122 (2016)
Wang, G., Xu, J., Pan, Z., Diao, Z.: Ultrasound image denoising using backward diffusion and framelet regularization. Biomed. Signal Process. Control 13, 212–217 (2014)
Gupta, D., Anand, R.S., Tyagi, B.: Despeckling of ultrasound medical images using nonlinear adaptive anisotropic diffusion in nonsubsampled shearlet domain. Biomed. Signal Process. Control 14, 55–65 (2014)
Fu, X., Wang, Y., Chen, L., Tian, J.: An image despeckling approach using quantum-inspired statistics in dual-tree complex wavelet domain. Biomed. Signal Process. Control 18, 30–35 (2015)
Singh, K., Ranade, S.K., Singh, C.: A hybrid algorithm for speckle noise reduction of ultrasound images. Comput. Methods Programs Biomed. 148, 55–69 (2017)
Loupas, T., McDicken, W.N., Allan, P.L.: An adaptive weighted median filter for speckle suppression in medical ultrasonic images. IEEE Trans. Circuits Syst. 36(1), 129–135 (1989)
Wagner, R.F., Smith, S.W., Sandrik, J.M., Lopez, H.: Statistics of speckle in ultrasound B-scans. IEEE Trans. Sonics Ultrasonics 30(3), 156–163 (1983)
Kumar, B.S.: Image denoising based on non-local means filter and its method noise thresholding. SIViP 7(6), 1211–1227 (2013)
Shahdoosti, H.R., Hazavei, S.M.: Combined ripplet and total variation image denoising methods using twin support vector machines. Multimed. Tools Appl. 77(6), 7013–7031 (2018)
Shahdoosti, H.R.: Two-stage image denoising considering interscale and intrascale dependencies. J. Electron. Imaging 26(6), 063029 (2017)
Mittal, A., Soundararajan, R., Bovik, A.C.: Making a “completely blind” image quality analyzer. IEEE Signal Process. Lett. 20(3), 209–212 (2013)
Bhuiyan, M.I.H., Ahmad, M.O., Swamy, M.N.S.: Spatially adaptive thresholding in wavelet domain for despeckling of ultrasound images. IET Image Proc. 3(3), 147–162 (2009)
Author information
Authors and Affiliations
Corresponding author
Appendix
Appendix
Firstly, the derivation of equation (14) is described. Substituting Eq. (12) into (13) and setting the derivative of Eq. (13) equal to zero yield:
As already mentioned, the parameter \(\gamma \) should be set to 0.5. After some manipulations, we obtain:
which is a quadratic function of \(\sigma _u^2 \). Equation (A.2) has two solutions:
Note that \(\hat{{\sigma }}_u^2 \) is always a negative (positive) value for the minus (plus) sign. For the plus sign, Eq. (A.3) is equal to Eq. (14).
Secondly, the derivation of equation (17) is explained. Considering Eq. (16), we should maximize the log-likelihood function:
Substituting \(p_{u(r)} (u(x))\) yields (the parameter \(\gamma \) is set to 0.5):
Setting the derivative of Eq. (A.5) equal to zero yields:
Equation (A.6) has two solutions:
To obtain a positive value for \(\hat{{\sigma }}_{u(r)}^2 \), the plus sign is selected [see Eq. (17)].
Rights and permissions
About this article
Cite this article
Shahdoosti, H.R., Rahemi, Z. A maximum likelihood filter using non-local information for despeckling of ultrasound images. Machine Vision and Applications 29, 689–702 (2018). https://doi.org/10.1007/s00138-018-0929-8
Received:
Revised:
Accepted:
Published:
Issue Date:
DOI: https://doi.org/10.1007/s00138-018-0929-8