Abstract
In the current era of technological advancements where convergence of social mobility analytics and clouds enabled the end users in capturing precise medical images on the go but also had lead incorporation of unusual noises too. One such scenario is the combination of both Additive White Gaussian Noise (AWGN) along with impulse noise that are added during acquisition and post-processing of medical images which hampers the overall medical image processing where identification of region of interest is pretty important. The noises not only affect the textures but also could plays at the pixelate level. In this work, a patch transformation technique for mixed noise removal and the bilateral filtering approach for edge preservation have been associated with the cognitive neural network model to remove the noise from medical images. The self adaptation of the network identifies the presence of mixed noise and generate the training dataset with the noisy patches along with the denoised patches. The proposed two stage self adaptive cognitive neural network model (SACNN) successfully retains the edge information along with denoising of the images. The performance of SACNN model is compared with other state-of-the-art techniques through various performance matrices. Statistical analysis such as, Signed test, Wilcoxon Signed rank test and Friedman test are also carried out to investigate the dominance of proposed approach over others.
Similar content being viewed by others
References
Al-Sbou YA (2012) Artificial neural networks evaluation as an image denoising tool. World Appl Sci J 17(2):218–227
Brox T, Van Den Boomgaard R, Lauze F, Van De Weijer J, Weickert J, Mrázek P, Kornprobst P (2006) Adaptive structure tensors and their applications. In: Visualization and processing of tensor fields (pp 17–47). Springer, Berlin, Heidelberg
Buades A, Coll B, Morel JM (2005) A non-local algorithm for image denoising. In: 2005 IEEE Computer Society Conference on Computer Vision and Pattern Recognition (CVPR’05) (Vol 2, pp 60–65). IEEE
Chen P, Qian H, Zhu M (2008) Fast Gaussian particle filtering algorithm. 36. 291–294
Crammer K, Singer Y (2001) On the algorithmic implementation of multiclass kernel-based vector machines. J Mach Learn Res 2(Dec):265–292
Fan L, Zhang F, Fan H, Zhang C (2019) Brief review of image denoising techniques. Vis Comput Ind Biomed Art 2(1):1–12
Fu B, Xiong X, Sun G (2011) An efficient mean filter algorithm. In: The 2011 IEEE/ICME International conference on complex medical engineering (pp 466–470). IEEE
Garnett R, Huegerich T, Chui C, He W (2005) A universal noise removal algorithm with an impulse detector. IEEE Trans Image Process 14(11):1747–1754
Goyal B, Agrawal S, Sohi BS (2018) Noise issues prevailing in various types of medical images. Biomed Pharmacol J 11(3):1227
Goyal B, Dogra A, Agrawal S, Sohi BS (2017) Significance of noise reduction in medical datasets for accurate diagnosis. Int J Comput Appl 64(14):1–12
Guo F, Zhang C (2019) Edge preserving mixed noise removal. Multimed Tools Appl 78(12):16601–16613
Hu H, Li B, Liu Q (2016) Removing mixture of gaussian and impulse noise by patch-based weighted means. J Sci Comput 67(1):103–129
Huang T, Yang GJTGY, Tang G (1979) A fast two-dimensional median filtering algorithm. IEEE Trans Acoust Speech Signal Process 27(1):13–18
Javed SG, Majid A, Mirza AM, Khan A (2016) Multi-denoising based impulse noise removal from images using robust statistical features and genetic programming. Multimed Tools Appl 75(10):5887–5916
Kumar M, Mishra SK (2018) Jaya based functional link multilayer perceptron adaptive filter for Poisson noise suppression from X-ray images. Multimed Tools Appl 77(18):24405–24425
Kumar M, Mishra SK (2020) A comprehensive review on nature inspired neural network based adaptive filter for eliminating noise in medical images. Curr med imaging 16(4):278–287
Li Y, Li C (2020) A mixed model with multi-fidelity terms and nonlocal low rank regularization for natural image noise removal. Multimed Tools Appl 79(43):33043–33069
Li C, Li Y, Zhao Z, Yu L, Luo Z (2019) A mixed noise removal algorithm based on multi-fidelity modeling with nonsmooth and nonconvex regularization. Multimed Tools Appl 78(16):23117–23140
Li B, Liu Q, Xu J, Luo X (2011) A new method for removing mixed noises. Sci China Inf Sci 54(1):51–59
Lin CH, Tsai JS, Chiu CT (2010) Switching bilateral filter with a texture/noise detector for universal noise removal. IEEE Trans Image Process 19 (9):2307–2320
Liu B, Liu J (2018) Non-local mean filtering algorithm based on deep learning. In: MATEC Web of Conferences (Vol 232, p 03025). EDP Sciences
Liu B, Liu J (2019) Overview of image denoising based on deep learning. In: Journal of physics: conference series (Vol 1176, No 2, p 022010). IOP Publishing
Ma H, Nie Y (2018) Mixed noise removal algorithm combining adaptive directional weighted mean filter and improved adaptive anisotropic diffusion model. Mathematical Problems in Engineering, 2018
Mafi M, Izquierdo W, Cabrerizo M, Barreto A, Andrian J, Rishe ND, Adjouadi M (2020) Survey on mixed impulse and Gaussian denoising filters. IET Image Process 14(16):4027–4038
Naga Srinivasu P, Balas VE (2021) Performance measurement of various hybridized kernels for noise normalization and enhancement in high-resolution MR images. In: Bio-inspired Neurocomputing (pp 1–24). Springer, Singapore
Nair MS, Shankar V (2013) Predictive-based adaptive switching median filter for impulse noise removal using neural network-based noise detector. SIViP 7 (6):1041–1070
O’Shea K, Nash R (2015) An introduction to convolutional neural networks. arXiv:http://arxiv.org/abs/1511.08458
Radlak K, Malinski L, Smolka B (2020) Deep learning based switching filter for impulsive noise removal in color images. Sensors 20(10):2782
Rahman MA, Wang Y (2016) Learning neural networks with ranking-based losses for action retrieval. In: 2016 13th Conference on Computer and Robot Vision (CRV) (pp 1–7). IEEE
Razlighi QR, Kehtarnavaz N (2009) A comparison study of image spatial entropy. In: Visual communications and image processing 2009 (Vol 7257, p 72571X). International society for optics and photonics
Shi Z, Xu Z, Pang K, Cao Q, Luo T (2018) Dissimilar pixel counting based impulse detector for two-phase mixed noise removal. Multimed Tools Appl 77(6):6933–6953
Singh Chaplot D, MacLellan C, Salakhutdinov R, Koedinger K (2018) Learning Cognitive Models using Neural Networks. arXiv:http://arxiv.org/abs/1806
Siva Sai JG, Srinivasu PN, Sindhuri MN, Rohitha K, Deepika S (2021) An Automated segmentation of brain MR image through fuzzy recurrent neural network. In: Bio-inspired neurocomputing (pp 163–179). Springer, Singapore
Turkmen I (2014) Removing random-valued impulse noise in images using a neural network detector. Turk J Electr Eng Comput Sci 22(3):637–649
Turkmen I (2016) The ANN based detector to remove random-valued impulse noise in images. J Vis Commun Image Represent 34:28–36
Wang Y, Scott CD (2020) Weston-Watkins Hinge Loss and Ordered Partitions. arXiv:http://arxiv.org/abs/2006.07346
Wang SS, Wu CH (2009) A new impulse detection and filtering method for removal of wide range impulse noises. Pattern Recogn 42(9):2194–2202
Xiong B, Yin Z (2011) A universal denoising framework with a new impulse detector and nonlocal means. IEEE Trans Image Process 21(4):1663–1675
Zhang B, Allebach JP (2008) Adaptive bilateral filter for sharpness enhancement and noise removal. IEEE Trans Image Process 17(5):664–678
Zhang M, Gunturk B (2008) A new image denoising method based on the bilateral filter. In: 2008 IEEE International conference on acoustics, speech and signal processing (pp 929–932). IEEE
Zhang L, Zhang X (2003) Global Linear and Quadratic One-step Smoothing Newton Method for P0 -LCP. J Glob Optim 25(4):363–376
Zhang K, Zuo W, Chen Y, Meng D, Zhang L (2017) Beyond a gaussian denoiser: Residual learning of deep CNN for image denoising. IEEE Trans Image Process 26(7):3142–3155
Zhang K, Zuo W, Gu S, Zhang L (2017) Learning deep CNN denoiser prior for image restoration. In: Proceedings of the IEEE conference on computer vision and pattern recognition, pp 3929–3938
Author information
Authors and Affiliations
Corresponding author
Ethics declarations
Medical Images for the study in this research have been obtained from Om Hospital, Raipur and patients’ identity have not been disclosed. The authors declare that there are no conflicts of interest.
Additional information
Publisher’s note
Springer Nature remains neutral with regard to jurisdictional claims in published maps and institutional affiliations.
Prajna Parimita Dash has contributed equally to this work
Rights and permissions
Springer Nature or its licensor (e.g. a society or other partner) holds exclusive rights to this article under a publishing agreement with the author(s) or other rightsholder(s); author self-archiving of the accepted manuscript version of this article is solely governed by the terms of such publishing agreement and applicable law.
About this article
Cite this article
Shah, V.H., Dash, P.P. Two stage self-adaptive cognitive neural network for mixed noise removal from medical images. Multimed Tools Appl 83, 6497–6519 (2024). https://doi.org/10.1007/s11042-023-15423-9
Received:
Revised:
Accepted:
Published:
Issue Date:
DOI: https://doi.org/10.1007/s11042-023-15423-9