10.57647/j.fomj.2025.0602.10

A hybrid method for medical image denoising and segmentation using optimized fuzzy clustering and autoencoder

PDF
  • Omid Darvishi Ghaleh1,
  • Vafa Maihami*2,
  • Keyhan Khamforoosh1,
  1. Department of Computer Engineering, Sa.C., Islamic Azad University, Sanandaj, Iran.
  2. Department of Computer Engineering, Islamic Azad University, Sanandaj Branch, Sanandaj, Iran

Received: 2025-02-08

Revised: 2025-05-14

Accepted: 2025-06-27

Published in Issue 2025-08-23

Copyright (c) 2025 Omid Darvishi, Vafa Maihami, keyhan Khamfroosh (Author)

Creative Commons License

This work is licensed under a Creative Commons Attribution 4.0 International License.

How to Cite

Darvishi Ghaleh, O., Maihami, V., & Khamforoosh, K. (2025). A hybrid method for medical image denoising and segmentation using optimized fuzzy clustering and autoencoder. Fuzzy Optimization and Modeling Journal (FOMJ), 6(2). https://doi.org/10.57647/j.fomj.2025.0602.10
Crossref
Scopus
Google Scholar
Europe PMC

PDF views: 136

Abstract

Frequently, medical images contain noise, which has the potential to obscure important diagnostic features and complicate accurate segmentation. The proposed framework integrates adaptive  autoencoder-based  enhancement, optimized fuzzy clustering, and fast bilateral filtering to achieve robust denoising and segmentation. In the preprocessing phase, fast bilateral filtering preserves edge details while reducing noise, thereby creating a reliable basis for subsequent clustering. In order to surmount the limitations of standard fuzzy C-means (FCM) in noisy conditions, the method employs the computation of the absolute difference between the original and filtered images. This process serves to accentuate structural information and suppress residual noise. Subsequently, an adaptive autoencoder is employed to reconstruct sharp, noise-free images by enhancing fine details. The efficacy of the clustering process is augmented by a refined FCM objective function that expedites convergence through a logarithmic accumulation of membership values from prior iterations. Finally, post-processing steps—including sharpening and median filtering-enhance the clarity and accuracy of segmentation results. The experimental findings, derived from the analysis of benchmark MRI and low-dose CT datasets, demonstrate the efficacy of the proposed method in surpassing classical FCM and other contemporary denoising techniques. The employment of this method engenders several key advantages, including enhanced noise reduction, expedited convergence, and refined segmentation accuracy. Furthermore, it guarantees the maintenance of essential diagnostic characteristics, thereby enhancing the reliability and utility of the resulting data.

Keywords

  • Adaptive autoencode,
  • Fuzzy C-means,
  • Medical image denoising,
  • Segmentation,
  • Fast bilateral filtering,
  • Machine learning
PDF

References

  1. P. F. Feruglio, C. Vinegoni, J. Gros, A. Sbarbati, and R. Weissleder. Block matching 3d random noise filtering for absorption optical projection tomography. Physics in Medicine & Biology, 55(18): 5401–5415, 2010.
  2. M. Diwakar, P. Kumar, P. Singh, A. Tripathi, and L. Singh. An efficient reversible data hiding using svd over a novel weighted iterative anisotropic total variation based denoised medical images. Biomedical Signal Processing and Control, 82:104563, 2023.
  3. H. Barrah, A. Cherkaoui, and D. Sarsri. Robust fcm algorithm with local and gray information for image segmentation. Advances in Fuzzy Systems, pages 1–10, 2016.
  4. H. Aetesam and S. K. Maji. Deep variational magnetic resonance image denoising via network conditioning. Biomedical Signal Processing and Control, 95:106452, 2024.
  5. V. Srivastava. An optimization for adaptive multi-filter estimation in medical images and eeg based signal denoising. Biomedical Signal Processing and Control, 82:104513, 2023.
  6. A. A. Laghari, Y. Sun, M. Alhussein, K. Aurangzeb, M. S. Anwar, and M. Rashid. Deep residual-dense network based on bidirectional recurrent neural network for atrial fibrillation detection. Scientific Reports, 13(1):15109, 2023.
  7. S. Das, A. Adhikary, A. A. Laghari, G. A. Sampedro, and S. Mitra. Eldo-care: Eeg with kinect sensor based telehealthcare for the disabled and the elderly. Neuroscience Informatics, page 100130, 2023.
  8. U. Saeed, K. Kumar, M. A. Khuhro, A. A. Laghari, A. A. Shaikh, and A. Rai. Deepleuknet–a cnn based microscopy adaptation model for acute lymphoblastic leukemia classification. Multimedia Tools and Applications, pages 1–25, 2023.
  9. S. Krinidis and V. Chatzis. A robust fuzzy local information c-means clustering algorithm. IEEE Transactions on Image Processing, 19 (5):1328–1337, 2010.
  10. V. Maihami and F. Yaghmaee. A genetic-based prototyping for automatic image annotation. Computers & Electrical Engineering, 70:400–412, 2018.
  11. X. Zhang, Y. Zhang, and Y. Wang. Advanced autoencoder architectures for image denoising and enhancement. International Journal of Computer Vision, 44(1):123–135, 2024.
  12. B. Zhang, Y. Zhang, B. Wang, X. He, F. Zhang, and X. Zhang. Denoising swin transformer and perceptual peak signal-to-noise ratio for low-dose ct image denoising. Measurement, 227:114303, 2024.
  13. R. Xu, Y. Xu, X. Yang, H. Huang, Z. Lei, and Y. Quan. Wavelet analysis model inspired convolutional neural networks for image denoising. Applied Mathematical Modelling, 125:798–811, 2024.
  14. S. Paris and A. Durand. A fast approximation of the bilateral filter using a signal processing approach. International Journal of Computer Vision, 81:24–52, 2009.
  15. P. Shi, L. Guo, H. Cui, and L. Chen. Geometric consistent fuzzy cluster ensemble with membership reconstruction for image segmentation. Digital Signal Processing, 134:103901, 2023.
  16. Q. Wang, X. Wang, C. Fang, and W. Yang. Robust fuzzy c-means clustering algorithm with adaptive spatial & intensity constraint and membership linking for noise image segmentation. Applied Soft Computing, 92:106318, 2020.
  17. J. C. Dunn. A fuzzy relative of the isodata process and its use in detecting compact well-separated clusters. Journal of Cybernetics, 3:32–57, 1973.
  18. C. Wu and Y. Chen. Adaptive entropy weighted picture fuzzy clustering algorithm with spatial information for image segmentation. Soft Computing, 86:1–23, 2020.
  19. C. Feng, W. Li, J. Hu, K. Yu, and D. Zhao. Bcefcm s: Bias correction embedded fuzzy c-means with spatial constraint to segment multiple spectral images with intensity inhomogeneities and noises. Signal Processing, 168:1–21, 2020.
  20. A. A. Laghari, V. V. Estrela, H. Li, Y. Shoulin, A. A. Khan, M. S. Anwar, A. Wahab, and K. Bouraqia. Quality of experience assessment in virtual/augmented reality serious games for healthcare: A systematic literature review. Technology and Disability, pages 1–12, 2024.
  21. A. A. Laghari and S. Yin. How to collect and interpret medical pictures captured in highly challenging environments that range from nanoscale to hyperspectral imaging. Current Medical Imaging, pages 14–25, 2022.
  22. H. Zhang, L. Bruzzone, W. Shi, M. Hao, and Y. Wang. Enhanced spatially constrained remotely sensed imagery classification using a fuzzy local double neighborhood information c-means clustering algorithm. IEEE Journal of Selected Topics in Applied Earth Observations and Remote Sensing, 11(8):2896–2910, 2018.
  23. A. Elazab, C. Wang, F. Jia, J. Wu, G. Li, and Q. Hu. Segmentation of brain tissues from magnetic resonance images using adaptively regularized kernel-based fuzzy c-means clustering. Computational and Mathematical Methods in Medicine, pages 22–41, 2015.
  24. V. Goreke. Novel method based on wiener filter for denoising poisson noise from medical x-ray images. Biomedical Signal Processing and Control, 79:104031, 2023.
  25. Y. Cui, H. Huang, J. Liu, M. Zhao, C. Li, X. Han, N. Luo, J. Gao, D. M. Yan, C. Zhang, T. Jiang, and S. Yu. Ffcm-mrf: An accurate and generalizable cerebrovascular segmentation pipeline for humans and rhesus monkeys based on tof-mra. Computers in Biology and Medicine, 170:107996, 2024.
  26. T. Wei, X. Wang, X. Li, and S. Zhu. Fuzzy subspace clustering noisy image segmentation algorithm with adaptive local variance & non-local information and mean membership linking. Engineering Applications of Artificial Intelligence, 110:104672, 2022.
  27. S. Song, Z. Jia, F. Shi, J. Wang, and D. Ni. Adaptive fuzzy weighted c-mean image segmentation algorithm combining a new distance metric and prior entropy. Engineering Applications of Artificial Intelligence, 131:107776, 2024.
  28. J. C. Bezdek. Pattern recognition with fuzzy objective function algorithms. Plenum Press, New York, 1981.
  29. A. Halder and A. K. Nandi. Robust brain magnetic resonance image segmentation using modified rough-fuzzy c-means with spatial constraints. Applied Soft Computing, pages 1–17, 2019.
  30. T. Lei, X. Jia, Y. Zhang, H. He, H. Meng, and A. K. Nandi. Superpixel-based fast fuzzy c-means for color image segmentation. IEEE Transactions on Fuzzy Systems, 27(9):1753–1766, 2019.
  31. K. K. Tseng, R. Zhang, C. M. Chen, and M. M. Hassan. Dnetunet: A semi-supervised cnn for medical image segmentation in supercomputing ai services. The Journal of Supercomputing, 77:3594–3615, 2021.
  32. E. K. Wang, C. M. Chen, M. M. Hassan, and A. Almogren. A deep learning-based medical image segmentation technique in the internet-of-medical-things domain. Future Generation Computer Systems, 107:135–144, 2020.
  33. A. Bose, U. Maulik, and A. Sarkar. An entropy-based membership approach on type-ii fuzzy set (emt2fcm) for biomedical image segmentation. Engineering Applications of Artificial Intelligence, 127: 107267, 2024.
  34. O. Torun, S. Esen Yuksel, E. Erdem, N. Imamoglu, and A. Erdem. Hyperspectral image denoising via self-modulating convolutional neural networks. Signal Processing, 214:109248, 2024.
  35. R. Zhang, Z. Yu, Z. Sheng, J. Ying, S. Y. Cao, S. J. Chen, B. Yang, J. Li, and H. L. Shen. Sgdformer: One-stage transformer-based architecture for cross-spectral stereo image guided denoising. Information Fusion, 113:102603, 2025.
  36. H. Chen, Y. Zhang, M. K. Kalra, F. Lin, Y. Chen, and P. Liao. Low dose ct with a residual encoder-decoder convolutional neural network. IEEE Transactions on Medical Imaging, 36(12):2524–2535, 2017.
  37. J. Li and Y. Xu. Autoencoder-based techniques for noise reduction in medical imaging. Journal of Medical Imaging, 30(2):789–802, 2023.
  38. L. Chen and et al. Denoising autoencoders for image restoration. IEEE Transactions on Neural Networks and Learning Systems, 34 (3):456–468, 2023.
  39. B. Zhang, Y. Zhang, B. Wang, X. He, F. Zhang, and X. Zhang. Denoising swin transformer and perceptual peak signal-to-noise ratio for low-dose ct image denoising. Measurement, 227:114303.
  40. T. Zhao, M. McNitt-Gray, and D. Ruan. A convolutional neural network for ultra-low-dose ct denoising and emphysema screening. Medical Physics, 46(9):3941–3950, 2019.