Enhancing Medical Image Denoising: A Hybrid Approach Incorporating Adaptive Kalman Filter and Non-Local Means with Latin Square Optimization
Abstract
:1. Introduction
2. Motivation
- Complexity of Image Structures: Images often contain a diverse range of structures, textures, and patterns. Determining the appropriate parameters for non-local means filtering requires considering the scale and characteristics of these structures, which can vary significantly across different images and imaging modalities.
- Trade-off between Denoising and Detail Preservation: Non-local means filtering aims to strike a balance between denoising and preserving important image details. Selecting optimal parameters involves finding the right balance between noise reduction and maintaining image sharpness and clarity.
- Computational Complexity: Non-local means filtering involves comparing patches of pixels across the entire image, which can be computationally intensive, particularly for high-resolution images. Selecting optimal parameters that achieve satisfactory denoising results while minimizing computational overhead is essential for practical applications.
- Impact of Noise Characteristics: The effectiveness of non-local means filtering can vary depending on the characteristics of the noise present in the image. Selecting parameters that are adaptive to different noise profiles and levels is crucial for achieving optimal denoising performance.
3. Proposed Method
3.1. Kalman Filter for Noise Attenuation
3.2. Adaptive Kalman Filter
- Dynamic Nature of Image Noise:
- Optimizing Denoising Performance:
- Robustness to Changing Environments:
- Prediction:
- Update:
3.3. Non-Local Means (NLM) Post-Processing
3.4. Parameter Selection and Optimization
3.5. Median Filter Post-Processing
3.6. Latin Square Optimization
- Each symbol appears exactly once in each row. This can be represented as follows:
- Each symbol appears exactly once in each column. This can be represented as follows:
Algorithm 1: Selection of Optimized Variables Using a Latin Square. |
1: Input: Parameters = {W,S,h} and n levels for parameters , , }, , , }, and , , } 2: Output: Optimal levels for parameters 3: Initialize a Latin Square with n × n matrix Assign the parameters such that each parameter appears exactly once in each row and each column 4: for i in (0..n) do 5: for j in (0..n) do 6: ) 7: for k in (0..n) do derive 8: end for 9: end for 10: end for 11: solve the equations 12: if == MSE then 13: Minimize the Objective Function 14: else if == PSNR then 15: Maximize the Objective Function 16: else 17: Invalid choice 18: end if 19: determine the optimal parameters 20: return optimal parameters |
4. Experimental Results
4.1. Analysis Results Latin Square
4.2. Proposed Method Evaluation Results
- Peak Signal-to-Noise Ratio (PSNR):
- Mean Squared Error (MSE):
- Structural Similarity Index (SSIM):
Algorithm 2: Robustness Analysis. |
Input: - OriginalImage: the original image - MaxNoiseLevel: the maximum noise level to be tested - ProposedMethod: function to apply the proposed denoising method - DesiredOutputPSNR: the desired PSNR value for the denoised image - DesiredOutputMSE: the desired MSE value for the denoised image Output: - MaxNoiseLevel: the maximum noise level at which PSNR and MSE remain consistent Initialize NoiseLevel to image noise level For NoiseLevel from the image noise level to MaxNoiseLevel: Add noise to OriginalImage with NoiseLevel Calculate PSNR of the noisy image Denoise the noisy image using ProposedMethod Calculate PSNR and MSE of the denoised image If PSNR of noisy image > DesiredOutputPSNR or MSE of noisy image < DesiredOutputMSE: Increment NoiseLevel Return MaxNoiseLevel |
5. Conclusions
Author Contributions
Funding
Data Availability Statement
Conflicts of Interest
References
- Chang, S.G.; Yu, B.; Vetterli, M. Adaptive wavelet thresholding for image denoising and compression. IEEE Trans. Image Process. 2000, 9, 1532–1546. [Google Scholar] [CrossRef] [PubMed]
- Starck, J.L.; Candès, E.J.; Donoho, D.L. The curvelet transform for image denoising. IEEE Trans. Image Process. 2002, 11, 670–684. [Google Scholar] [CrossRef] [PubMed]
- Elad, M.; Aharon, M. Image denoising via sparse and redundant representations over learned dictionaries. IEEE Trans. Image Process. 2006, 15, 3736–3745. [Google Scholar] [CrossRef] [PubMed]
- Dong, W.; Zhang, L.; Shi, G.; Li, X. Nonlocally centralized sparse representation for image restoration. IEEE Trans. Image Process. 2012, 22, 1620–1630. [Google Scholar] [CrossRef] [PubMed]
- Zhou, M.; Chen, H.; Paisley, J.; Ren, L.; Li, L.; Xing, Z.; Dunson, D.; Sapiro, G.; Carin, L. Nonparametric Bayesian dictionary learning for analysis of noisy and incomplete images. IEEE Trans. Image Process. 2011, 21, 130–144. [Google Scholar] [CrossRef] [PubMed]
- Portilla, J.; Strela, V.; Wainwright, M.J.; Simoncelli, E.P. Image denoising using scale mixtures of Gaussians in the wavelet domain. IEEE Trans. Image Process. 2003, 12, 1338–1351. [Google Scholar] [CrossRef] [PubMed]
- Luo, E.; Chan, S.H.; Nguyen, T.Q. Adaptive image denoising by targeted databases. IEEE Trans. Image Process. 2015, 24, 2167–2181. [Google Scholar] [CrossRef] [PubMed]
- Zhang, K.; Zuo, W.; Chen, Y.; Meng, D.; Zhang, L. Beyond a gaussian denoiser: Residual learning of deep cnn for image denoising. IEEE Trans. Image Process. 2017, 26, 3142–3155. [Google Scholar] [CrossRef] [PubMed]
- Rabie, T. Robust estimation approach for blind denoising. IEEE Trans. Image Process. 2005, 14, 1755–1765. [Google Scholar] [CrossRef]
- Liu, C.; Szeliski, R.; Kang, S.B.; Zitnick, C.L.; Freeman, W.T. Automatic estimation and removal of noise from a single image. IEEE Trans. Pattern Anal. Mach. Intell. 2007, 30, 299–314. [Google Scholar] [CrossRef]
- Lebrun, M.; Colom, M.; Morel, J.M. Multiscale image blind denoising. IEEE Trans. Image Process. 2015, 24, 3149–3161. [Google Scholar] [CrossRef]
- Zhu, F.; Chen, G.; Hao, J.; Heng, P.A. Blind image denoising via dependent Dirichlet process tree. IEEE Trans. Pattern Anal. Mach. Intell. 2016, 39, 1518–1531. [Google Scholar] [CrossRef] [PubMed]
- Xu, J.; Zhang, L.; Zhang, D. External prior guided internal prior learning for real-world noisy image denoising. IEEE Trans. Image Process. 2018, 27, 2996–3010. [Google Scholar] [CrossRef] [PubMed]
- Khodarahmi, M.; Maihami, V. A review on Kalman filter models. Arch. Comput. Methods Eng. 2023, 30, 727–747. [Google Scholar] [CrossRef]
- Ma, R.; Hu, H.; Xing, S.; Li, Z. Efficient and fast real-world noisy image denoising by combining pyramid neural network and two-pathway unscented Kalman filter. IEEE Trans. Image Process. 2020, 29, 3927–3940. [Google Scholar] [CrossRef]
- Conte, F.; Germani, A.; Iannello, G. A kalman filter approach for denoising and deblurring 3-d microscopy images. IEEE Trans. Image Process. 2013, 22, 5306–5321. [Google Scholar] [CrossRef] [PubMed]
- Roonizi, A.K.; Selesnick, I.W. A Kalman filter framework for simultaneous LTI filtering and total variation denoising. IEEE Trans. Signal Process. 2022, 70, 4543–4554. [Google Scholar] [CrossRef]
- Yang, L.; Parton, R.; Ball, G.; Qiu, Z.; Greenaway, A.H.; Davis, I.; Lu, W. An adaptive non-local means filter for denoising live-cell images and improving particle detection. J. Struct. Biol. 2010, 172, 233–243. [Google Scholar] [CrossRef]
- Zhang, X. Two-step non-local means method for image denoising. Multidimens. Syst. Signal Process. 2022, 33, 341–366. [Google Scholar] [CrossRef]
- Arabi, H.; Zaidi, H. Non-local mean denoising using multiple PET reconstructions. Ann. Nucl. Med. 2021, 35, 176–186. [Google Scholar] [CrossRef]
- Bal, A.; Banerjee, M.; Chaki, R.; Sharma, P. An efficient method for PET image denoising by combining multi-scale transform and non-local means. Multimed. Tools Appl. 2020, 79, 29087–29120. [Google Scholar] [CrossRef]
- Jiang, J.; Yang, K.; Yang, J.; Yang, Z.X.; Chen, Y.; Luo, L. A new nonlocal means based framework for mixed noise removal. Neurocomputing 2021, 431, 57–68. [Google Scholar] [CrossRef]
- Pan, J.; Yang, X.; Cai, H.; Mu, B. Image noise smoothing using a modified Kalman filter. Neurocomputing 2016, 173, 1625–1629. [Google Scholar] [CrossRef]
- Pfleger, S.G.; Plentz, P.D.; Rocha, R.C.; Pereira, A.D.; Castro, M. Real-time video denoising on multicores and gpus with kalman-based and bilateral filters fusion. J. Real-Time Image Process. 2019, 16, 1629–1642. [Google Scholar] [CrossRef]
- Wang, X.; Su, Y.; Xu, M.; Zhang, H.; Zhang, Y. A new image encryption algorithm based on Latin square matrix. Nonlinear Dyn. 2022, 107, 1277–1293. [Google Scholar] [CrossRef]
- Hua, Z.; Zhu, Z.; Chen, Y.; Li, Y. Color image encryption using orthogonal Latin squares and a new 2D chaotic system. Nonlinear Dyn. 2021, 104, 4505–4522. [Google Scholar] [CrossRef]
- Zhou, J.; Zhou, N.R.; Gong, L.H. Fast color image encryption scheme based on 3D orthogonal Latin squares and matching matrix. Opt. Laser Technol. 2020, 131, 106437. [Google Scholar] [CrossRef]
- Reid, I.; Term, H. Estimation ii; Lecture Note; University of Oxford: Oxford, UK, 2001. [Google Scholar]
- Al-Dhabyani, W.; Gomaa, M.; Khaled, H.; Fahmy, A. Dataset of breast ultrasound images. Data Brief 2020, 28, 104863. [Google Scholar] [CrossRef]
h | TemplateWindowSize | SearchWindowSize |
---|---|---|
5 | 3 | 8 |
7 | 5 | 10 |
9 | 7 | 15 |
10 | 9 | 20 |
12 | 12 | 25 |
Parameters | PSNR | MSE |
---|---|---|
µ | 20.766225 | 19.3494 |
3.936885 | 5.42564 | |
3.999685 | 4.95964 | |
4.209085 | 3.46324 | |
4.310885 | 2.74524 | |
4.309685 | 2.75564 | |
4.239685 | 3.26184 | |
4.174685 | 3.72104 | |
4.143685 | 3.93744 | |
4.091085 | 4.30184 | |
4.117085 | 4.12724 | |
4.132285 | 4.01624 | |
4.146885 | 3.90664 | |
4.167085 | 3.77784 | |
4.141085 | 3.95764 | |
4.178885 | 3.69104 |
Gaussian Noise | Image I | Image II | Image III | Image IV | Image V | Image VI | Image VII | Image VIII | Image IX | Image X | |
---|---|---|---|---|---|---|---|---|---|---|---|
Median | PSNR | 27.64 | 27.32 | 27.54 | 27.43 | 27.70 | 27.73 | 27.75 | 27.66 | 28.01 | 27.86 |
MSE | 111.97 | 120.46 | 114.70 | 117.44 | 110.47 | 109.72 | 109.23 | 111.50 | 102.94 | 106.37 | |
SSIM | 0.599 | 0.657 | 0.638 | 0.633 | 0.635 | 0.609 | 0.637 | 0.567 | 0.591 | 0.607 | |
NLM | PSNR | 24.17 | 23.49 | 23.21 | 24.96 | 25.95 | 25.18 | 25.28 | 23.23 | 24.07 | 25.22 |
MSE | 248.74 | 291.18 | 310.72 | 207.53 | 165.06 | 197.35 | 192.87 | 308.95 | 254.70 | 195.67 | |
SSIM | 0.498 | 0.521 | 0.464 | 0.576 | 0.632 | 0.571 | 0.589 | 0.399 | 0.459 | 0.547 | |
Kalman | PSNR | 29.07 | 29.01 | 29.13 | 29.02 | 29.03 | 29.07 | 29.10 | 29.15 | 29.25 | 29.19 |
MSE | 80.49 | 81.51 | 79.41 | 81.42 | 81.20 | 80.52 | 79.83 | 78.94 | 77.16 | 78.19 | |
SSIM | 0.413 | 0.498 | 0.478 | 0.458 | 0.431 | 0.411 | 0.434 | 0.403 | 0.387 | 0.402 | |
Kalman and NLM | PSNR | 27.00 | 26.01 | 26.77 | 26.02 | 26.32 | 27.06 | 26.29 | 28.10 | 27.56 | 26.99 |
MSE | 129.61 | 163.11 | 136.93 | 162.71 | 151.66 | 127.97 | 152.89 | 100.65 | 114.08 | 130.10 | |
SSIM | 0.634 | 0.656 | 0691 | 0.594 | 0.584 | 0.611 | 0.585 | 0.690 | 0.610 | 0.596 | |
Proposed Method | PSNR | 33.52 | 32.22 | 32.66 | 32.36 | 33.31 | 33.45 | 32.65 | 33.30 | 33.16 | 32.93 |
MSE | 28.88 | 38.93 | 35.24 | 37.73 | 30.30 | 29.36 | 35.26 | 30.40 | 31.34 | 33.04 | |
SSIM | 0.842 | 0.821 | 0.834 | 0.816 | 0.853 | 0.843 | 0.814 | 0.811 | 0.807 | 0.807 |
Gaussian Noise | Median | NLM | Kalman | Kalman and NLM | ||||||||
---|---|---|---|---|---|---|---|---|---|---|---|---|
PSNR | MSE | SSIM | PSNR | MSE | SSIM | PSNR | MSE | SSIM | PSNR | MSE | SSIM | |
Improvement % | 19.12 | 70.38 | 33.82 | 34.82 | 85.49 | 59.54 | 13.24 | 58.63 | 92.24 | 22.95 | 75.58 | 20.38 |
Poisson Noise | Image I | Image II | Image III | Image IV | Image V | Image VI | Image VII | Image VIII | Image IX | Image X | |
---|---|---|---|---|---|---|---|---|---|---|---|
Median | PSNR | 32.92 | 32.31 | 32.82 | 31.74 | 32.12 | 32.16 | 32.34 | 32.91 | 33.50 | 32.58 |
MSE | 33.21 | 38.16 | 33.95 | 43.54 | 39.89 | 39.58 | 37.97 | 33.28 | 29.02 | 35.87 | |
SSIM | 0.859 | 0.880 | 0.892 | 0.835 | 0.837 | 0.833 | 0.851 | 0.856 | 0.862 | 0.849 | |
NLM | PSNR | 32.70 | 31.98 | 32.48 | 30.88 | 32.11 | 32.03 | 32.21 | 32.25 | 33.53 | 32.69 |
MSE | 34.96 | 41.20 | 36.70 | 53.10 | 39.97 | 40.74 | 39.08 | 38.77 | 28.86 | 34.98 | |
SSIM | 0.851 | 0.857 | 0.880 | 0.808 | 0.837 | 0.826 | 0.838 | 0.836 | 0.860 | 0.841 | |
Kalman | PSNR | 31.72 | 31.66 | 32.24 | 30.93 | 30.87 | 31.09 | 31.22 | 32.35 | 32.22 | 31.61 |
MSE | 43.69 | 44.35 | 38.77 | 52.40 | 53.17 | 50.53 | 49.00 | 37.85 | 38.98 | 44.81 | |
SSIM | 0.762 | 0.817 | 0.832 | 0.740 | 0.709 | 0.704 | 0.744 | 0.785 | 0.768 | 0.744 | |
Kalman and NLM | PSNR | 34.14 | 33.19 | 33.12 | 32.88 | 34.16 | 33.87 | 33.85 | 33.41 | 34.26 | 34.15 |
MSE | 25.04 | 31.16 | 31.68 | 33.51 | 24.98 | 26.65 | 26.79 | 29.63 | 24.39 | 25.03 | |
SSIM | 0.867 | 0.871 | 0.869 | 0.862 | 0.882 | 0.861 | 0.876 | 0.838 | 0.851 | 0.861 | |
Proposed Method | PSNR | 34.92 | 33.35 | 33.96 | 33.48 | 34.96 | 34.96 | 34.53 | 34.32 | 35.55 | 35.09 |
MSE | 20.93 | 29.99 | 26.07 | 29.13 | 20.72 | 20.73 | 22.89 | 24.00 | 18.08 | 20.12 | |
SSIM | 0.889 | 0.870 | 0.887 | 0.857 | 0.902 | 0.894 | 0.891 | 0.853 | 0.891 | 0.888 |
Poisson Noise | Median | NLM | Kalman | Kalman and NLM | ||||||||
---|---|---|---|---|---|---|---|---|---|---|---|---|
PSNR | MSE | SSIM | PSNR | MSE | SSIM | PSNR | MSE | SSIM | PSNR | MSE | SSIM | |
Improvement % | 6.06 | 35.95 | 3.18 | 6.90 | 39.80 | 4.63 | 9.27 | 48.02 | 16.35 | 2.39 | 16.92 | 2.13 |
Robustness (%) | Gaussian | Poisson |
---|---|---|
Image I | 43.37 | 36.69 |
Image II | 43.96 | 29.49 |
Image III | 38.88 | 27.88 |
Image IV | 47.01 | 35.80 |
Image V | 47.28 | 38.98 |
Disclaimer/Publisher’s Note: The statements, opinions and data contained in all publications are solely those of the individual author(s) and contributor(s) and not of MDPI and/or the editor(s). MDPI and/or the editor(s) disclaim responsibility for any injury to people or property resulting from any ideas, methods, instructions or products referred to in the content. |
© 2024 by the authors. Licensee MDPI, Basel, Switzerland. This article is an open access article distributed under the terms and conditions of the Creative Commons Attribution (CC BY) license (https://creativecommons.org/licenses/by/4.0/).
Share and Cite
Taassori, M.; Vizvári, B. Enhancing Medical Image Denoising: A Hybrid Approach Incorporating Adaptive Kalman Filter and Non-Local Means with Latin Square Optimization. Electronics 2024, 13, 2640. https://doi.org/10.3390/electronics13132640
Taassori M, Vizvári B. Enhancing Medical Image Denoising: A Hybrid Approach Incorporating Adaptive Kalman Filter and Non-Local Means with Latin Square Optimization. Electronics. 2024; 13(13):2640. https://doi.org/10.3390/electronics13132640
Chicago/Turabian StyleTaassori, Mehdi, and Béla Vizvári. 2024. "Enhancing Medical Image Denoising: A Hybrid Approach Incorporating Adaptive Kalman Filter and Non-Local Means with Latin Square Optimization" Electronics 13, no. 13: 2640. https://doi.org/10.3390/electronics13132640