Abstract
MRI imaging is one of the most widespread techniques in biomedical applications. Impulse noise is frequently a problem affecting the diagnosis of the disease, and it's a challenging task to denoise. However, the standard linear filter cannot detect the distribution of noise accurately due to the extremely nonlinear characteristic of the impulse noise with the one-dimensional measures to describe the behavior of pixels. The paper proposes to find out the relationship between multiple measures by Cartesian Genetic Programming to comprehensively describe the behavior of pixels from multiple dimensions to increase the robustness of detection results, and more complementary feature detectors are constructed by using the multi-gene output characteristics of the model. In the recovery stage, an adaptive median filter and edge-preserving filter (AMEPF) will be proposed which consists of three-layer filters to enhance the image and reduces the traditional over-dependence on the result of the detection phase, the filter can eliminate noise and protect the integrity of the structure. Different experimental results show that the recovery effect under different impulse noise intensity is better than the previous methods.
Access this chapter
Tax calculation will be finalised at checkout
Purchases are for personal use only
Similar content being viewed by others
References
Kaur, M., Kaur, P., Kaur, M.: Comparative analysis of image denoising techniques. Int. J. Emerg. Technol. Adv. Eng. 2(6), 296–298 (2012)
Sprawls.org. http://www.sprawls.org/ppmi2/NOISE/. Accessed 21 Aug 2020
Alruwaili, M., Javed, A., Javed, M.S.: Hybrid genetic filter for restoration of brain MRI images corrupted with impulse noise. Int. J. Comput. Sci. Network Secur. (IJCSNS) 17(2), 255 (2017)
Ng, P.-E., Ma, K.-K.: A switching median filter with boundary discriminative noise detection for extremely corrupted images. IEEE Trans. Image Proc. 15(6), 1506–1516 (2006)
Rajeshwari, S., Sharmila, T. S.: Efficient quality analysis of MRI image using preprocessing techniques. In: IEEE Conference on Information & Communication Technologies, pp. 391–396 (2013)
Sivasundari, M.K.S., Kumar, R.S., Karnan, M.: Performance analysis of image filtering algorithms for MRI images. Int. J. Res. Eng. Technol 3(35), 438–440 (2014)
Huang, T.S.: A fast two-dimensional median filtering algorithm. IEEE Trans. Acoustic. Speech. Sign. Proc. 27(1), 13–18 (1979)
Hwang, H., Haddad, R.A.: Adaptive median filters: new algorithms and results. Image Proc. IEEE Trans. 4(4), 499–502 (1995)
Majid, A., et al.: Impulse noise filtering based on noise-free pixels using genetic programming. Knowl. Inf. Syst. 32(3), 505–526 (2012)
Madallah, A., Arshad, J., et al.: Hybrid genetic filter for restoration of brain MRI images corrupted with impulse noise. Int. J. Comput. Sci. Network Secur. (IJCSNS) 17(2), 252 (2017)
Julian, F. M.: Cartesian genetic programming: its status and future. Genet. Program. Evolv. Mach. 1–40(2019)
Nemanja, I.P., Vladimir, C.: Universal impulse noise filter based on genetic programming. IEEE Trans. Image Process. 17(7), 1109–1120 (2008)
Javed, S.G., Majid, A., Ali, S., et al.: A bio-inspired parallel-framework based multi-gene genetic programming approach to denoise biomedical images. Cogn. Comput. 8(4), 776–793 (2016)
Miller, J.F., Thomson, P.: Cartesian genetic programming. In: Poli, R., Banzhaf, W., Langdon, W.B., Miller, J., Nordin, P., Fogarty, T.C. (eds.) EuroGP 2000. LNCS, vol. 1802, pp. 121–132. Springer, Heidelberg (2000). https://doi.org/10.1007/978-3-540-46239-2_9
Huber, P.J.: Robust statistics. J. Am. Stat. Assoc. 78(381), 354 (2009)
Garnett, R., Huegerich, T., Chui, C., He, W.: A universal noise removal algorithm with an impulse detector. IEEE Trans. Image Proc. 14(11), 1747–1754 (2005). https://doi.org/10.1109/TIP.2005.857261
Dong, Y., Chan, R.H., Shufang, X.: A detection statistic for random-valued impulse noise. IEEE Trans. Image Proc. 16(4), 1112–1120 (2007)
Xiong, B., Yin, Z.: A universal denoising framework with a new impulse detector and nonlocal means. IEEE Trans. Image Proc. 21(4), 1663–1675 (2012)
Crnojevic, V., Senk, V., Trpovski, Z.: Advanced impulse detection based on pixel-wise mad. IEEE Sign. Proc. Lett. 11(7), 589–592 (2004)
Mehdi, M., Harold, M., Malek A.: High impulse noise intensity removal in MRI images. In: 2017 IEEE Signal Processing in Medicine and Biology Symposium (SPMB), pp. 1–6 (2017)
Chen, P.-Y., Lien, C.-Y.: An efficient edge-preserving algorithm for removal of salt-and-pepper noise. IEEE Sign. Proc. Lett. 15, 833–836 (2008)
CVG-UGR Image Database Vision Group. http://decsai.ugr.es/cvg/dbimagenes/. Accessed 21 Nov 2020
IXI Database. http://brain-development.org/ixi-dataset/. Accessed 15 Mar 2021
Acknowledgements
This work was supported in part by the National Natural Science Foundation of China (Grant No. 61977018), and the Natural Science Foundation of Guangdong Province, China (Grant No. 2015A030313501).
Author information
Authors and Affiliations
Editor information
Editors and Affiliations
Rights and permissions
Copyright information
© 2022 The Author(s), under exclusive license to Springer Nature Switzerland AG
About this paper
Cite this paper
Huang, W., He, P., Yan, Z., Wu, H. (2022). An Efficient MRI Impulse Noise Multi-stage Hybrid Filter Based on Cartesian Genetic Programming. In: Xie, Q., Zhao, L., Li, K., Yadav, A., Wang, L. (eds) Advances in Natural Computation, Fuzzy Systems and Knowledge Discovery. ICNC-FSKD 2021. Lecture Notes on Data Engineering and Communications Technologies, vol 89. Springer, Cham. https://doi.org/10.1007/978-3-030-89698-0_11
Download citation
DOI: https://doi.org/10.1007/978-3-030-89698-0_11
Published:
Publisher Name: Springer, Cham
Print ISBN: 978-3-030-89697-3
Online ISBN: 978-3-030-89698-0
eBook Packages: Intelligent Technologies and RoboticsIntelligent Technologies and Robotics (R0)