Enhanced Wavelet Block Shrinkage Technique For Mammogram Denoising Using K-Means Clustering And Neural Networks

  • Authors

    • Ashok Kumar Sahoo Research Scholar, School of Computer Science and Engineering, Christ University, Bangalore, India
    • Rajkumar Rajavel Associate Professor, Department of AI, ML and Data Science, Christ University, Bangalore, India
    https://doi.org/10.14419/8psp9843

    Received date: July 6, 2025

    Accepted date: August 17, 2025

    Published date: August 25, 2025

  • Enhanced Wavelet Block Shrink, Wavelet Shrinkage, K-Means Clustering, Convolutional Neural Network, Digital Mammogram Denoising, Breast Cancer

  • Abstract

    The proposed research study introduces a novel approach for denoising digital mammograms by improving the existing wavelet block shrinkage filtering method with K-Means clustering and a convolutional neural network. This approach involves decomposing both the original and noisy mammograms into frequency subbands using 2D discrete wavelet transformation. The resulting subbands are then grouped into multiple clusters based on similar features of the wavelet coefficients, employing K-Means clustering. This represents an improvement over the traditional block shrinkage method, which uses fixed-size blocks. These clusters from the original and noisy mammograms are paired to train a convolutional neural network, which serves as an optimal shrinkage function. This neural network-based thresholding mechanism replaces traditional hard and soft thresholding methods that rely on a universal threshold. Test results demonstrate that the proposed enhanced wavelet block shrinkage mechanism achieves a 20% improvement in peak signal-to-noise ratio and a 5% increase in structural similarity index score compared to traditional wavelet block shrinkage.

  • References

    1. Bray, F., Ferlay, J., Laversanne, M., Soerjomataram, I., Jemal, A., & Torre, L. A. (2024). Global cancer statistics 2022: GLOBOCAN estimates of incidence and mortality worldwide for 36 cancers in 185 countries. CA: A Cancer Journal for Clinicians, 74, 229–263. https://doi.org/10.3322/caac.21834
    2. Kuroishi, T., Hirose, K., Suzuki, T., Tominaga, S., & Takashima, S. (1992). The effect of breast self-examination on early detection and survival. Japanese Journal of Cancer Research, 83, 344–350. https://doi.org/10.1111/j.1349-7006.1992.tb00113.x
    3. Chen, L., Linden, H. M., Anderson, B. O., & Li, C. I. (2014). Trends in 5-year survival rates among breast cancer patients by hormone receptor sta-tus and stage. Breast Cancer Research and Treatment, 147, 609–616. https://doi.org/10.1007/s10549-014-3112-6
    4. Aristokli, N., Polycarpou, I., Themistocleous, S. C., Sophocleous, D., & Mamais, I. (2022). Comparison of the diagnostic performance of magnetic resonance imaging (MRI), ultrasound and mammography for detection of breast cancer based on tumor type, breast density and patient’s history: A review. Radiography, 28, 848–856. https://doi.org/10.1016/j.radi.2022.01.006
    5. Jung, H., Ryu, S., Kim, S., Kim, J. H., & Kim, J. G. (2019). Effect of digital mammography for breast cancer screening: A comparative study of more than 8 million Korean women. Radiology, 293, 48–54. https://doi.org/10.1148/radiol.2019190951
    6. Warren, L. M., Mackenzie, A., Given-Wilson, R., & Wallis, M. G. (2012). Effect of image quality on calcification detection in digital mammogra-phy. Medical Physics, 39, 3202–3213. https://doi.org/10.1118/1.4718571
    7. Huda, W., Ogden, K. M., Scalzetti, E. M., Dance, D. R., & Bertrand, E. A. (2006). How do lesion size and random noise affect detection perfor-mance in digital mammography? Academic Radiology, 13, 1355–1366. https://doi.org/10.1016/j.acra.2006.07.011
    8. Iflaq, P., Wilczek, M., Bell, D., et al. (2025). Dead pixel artifact. Radiopaedia. https://doi.org/10.53347/rID-98016
    9. Saunders, R. S., Baker, J. A., Delong, D. M., Johnson, J. P., & Samei, E. (2007). Does image quality matter? Impact of resolution and noise on mammographic task performance. Medical Physics, 34, 3971–3981. https://doi.org/10.1118/1.2776253
    10. Pereira, L., et al. (2021). Biological effects induced by doses of mammographic screening. Physica Medica, 87, 90–98. https://doi.org/10.1016/j.ejmp.2021.06.002
    11. Cahn, R. N., Cederström, B., Danielsson, M., Hall, A., Lundqvist, M., & Nygren, D. (1999). Detective quantum efficiency dependence on x-ray energy weighting in mammography. Medical Physics, 26, 2680–2683. https://doi.org/10.1118/1.598807
    12. da Costa Junior, C. A., & Patrocinio, A. C. (2019). Performance evaluation of denoising techniques applied to mammograms of dense breasts. In XXVI Brazilian Congress on Biomedical Engineering (pp. 369–374). Springer. https://doi.org/10.1007/978-981-13-2119-1_58
    13. Nazir, N., Sarwar, A., & Saini, B. S. (2024). Recent developments in denoising medical images using deep learning: An overview of models, tech-niques, and challenges. Micron, 180, 103615. https://doi.org/10.1016/j.micron.2024.103615
    14. Cai, T. T., & Silverman, B. W. (2001). Incorporating information on neighboring coefficients into wavelet estimation. Sankhyā: The Indian Journal of Statistics, Series A, 63, 127–148. http://www.jstor.org/stable/25053168
    15. Dewangan, P., & Goswami, R. (2012). Adaptive wavelet thresholding for image denoising using various shrinkage under different noise conditions. International Journal of Engineering Research and Technology, 1(4), 1–5.
    16. Zhang, X., Burger, M., Bresson, X., & Osher, S. (2010). Bregmanized nonlocal regularization for deconvolution and sparse reconstruction. SIAM Journal on Imaging Sciences, 3, 253–276. https://doi.org/10.1137/090746379
    17. Rahman, W. T., & Helvie, M. A. (2022). Breast cancer screening in average and high-risk women. Best Practice & Research Clinical Obstetrics & Gynaecology, 83, 3–14. https://doi.org/10.1016/j.bpobgyn.2021.11.007
    18. Perez, A. M. M. M., Lopes, L. A. S., Caron, R. F., Oliveira, B. B., & Poletti, M. E. (2024). Performance evaluation of six digital mammography sys-tems. Radiation Physics and Chemistry, 218, 111635. https://doi.org/10.1016/j.radphyschem.2024.111635
    19. Kumar, A., Kumar, P., & Srivastava, A. (2022). A skewness reformed complex diffusion based unsharp masking for the restoration and enhance-ment of poisson noise corrupted mammograms. Biomedical Signal Processing and Control, 73, 103421. https://doi.org/10.1016/j.bspc.2021.103421
    20. Ghazdali, A., Hadri, A., & Laghrib, A. (2024). Poisson noise and Gaussian noise separation through copula theory. Multimedia Tools and Applica-tions, 83, 67927–67952. https://doi.org/10.1007/s11042-023-17898-y
    21. Pashaei, E., & Pashaei, E. (2023). Gaussian quantum arithmetic optimization-based histogram equalization for medical image enhancement. Multi-media Tools and Applications, 82, 34725–34748. https://doi.org/10.1007/s11042-023-15025-5
    22. Cederström, B., Svensson, B., Danielsson, M., & Fredenberg, E. (2014). The influence of anatomical noise on optimal beam quality in mammogra-phy. Medical Physics, 41, 071910. https://doi.org/10.1118/1.4900611
    23. Chowdappa, A., & Sheshadri, H. (2018). Probabilistic identification and estimation of noise: Application to MR images. Biomedical and Pharma-cology Journal, 11, 2101–2110. https://doi.org/10.13005/bpj/1589
    24. Arias-Castro, E., & Donoho, D. L. (2006). Does median filtering truly preserve edges better than linear filtering? arXiv. https://arxiv.org/abs/math/0612422
    25. Bhateja, V., Misra, M., & Urooj, S. (2020). Non-linear enhancement techniques for mammograms. In Non-linear filters for mammogram enhance-ment (pp. 137–160). Springer. https://doi.org/10.1007/978-981-15-0442-6_7
    26. Carnahan, M. B., et al. (2023). False-positive and false-negative contrast-enhanced mammograms: Pitfalls and strategies to improve cancer detec-tion. RadioGraphics, 43, e230100. https://doi.org/10.1148/rg.230100
    27. Amiriebrahimabadi, M., Rouhi, Z., & Mansouri, N. (2024). A comprehensive survey of multi-level thresholding segmentation methods for image processing. Archives of Computational Methods in Engineering. https://doi.org/10.1007/s11831-024-10093-8
    28. Mencattini, A., Salmeri, M., Lojacono, R., & Caselli, F. (2006). Mammographic images enhancement and denoising for microcalcification detection using dyadic wavelet processing. In Proceedings of the IEEE instrumentation and measurement technology conference (IMTC) (pp. 49–53). https://doi.org/10.1109/IMTC.2006.328171
    29. Vikhe, P. S., & Thool, V. R. (2019). A wavelet and adaptive threshold-based contrast enhancement of masses in mammograms for visual screening. International Journal of Biomedical Engineering and Technology, 31, 31–53
    30. Eckert, D., Vesal, S., Ritschl, L., Kappler, S., & Maier, A. (2019). Deep learning-based denoising of mammographic images using physics-driven data augmentation. arXiv preprint. https://arxiv.org/abs/1912.05240
    31. Singh, G., Mittal, A., & Aggarwal, N. (2019). Deep convolution neural network based denoiser for mammographic images. In Advances in compu-ting and data sciences (pp. 187–197). Springer. https://doi.org/10.1007/978-981-13-9939-8_16
    32. Ghosh, S. K., Biswas, B., & Ghosh, A. (2020). Restoration of mammograms by using deep convolutional denoising auto-encoders. In Computa-tional intelligence in data mining (pp. 429–440). Springer. https://doi.org/10.1007/978-981-13-8676-3_38
    33. Benhassine, N. E., Boukaache, A., & Boudjehem, D. (2021). Medical image denoising using optimal thresholding of wavelet coefficients with se-lection of the best decomposition level and mother wavelet. International Journal of Imaging Systems and Technology, 31, 1906–1920. https://doi.org/10.1002/ima.22589
    34. Do, M. N., & Vetterli, M. (2002). Wavelet-based texture retrieval using generalized Gaussian density. IEEE Transactions on Image Processing, 11, 146–158. https://doi.org/10.1109/83.982822
    35. Pizurica, A., & Philips, W. (2006). Estimating the probability of the presence of a signal of interest in multiresolution single- and multiband image denoising. IEEE Transactions on Image Processing, 15, 654–665. https://doi.org/10.1109/TIP.2005.863021
    36. Starck, J., Murtagh, F., & Candes, E. (2008). Wavelets, ridgelets, and curvelets for Poisson noise removal. IEEE Transactions on Image Processing, 17, 1093–1108. https://doi.org/10.1109/TIP.2008.924386
    37. Heath, M., Bowyer, K., Kopans, D., Moore, R., & Kegelmeyer, W. P. (2000). The digital database for screening mammography. In Digital mam-mography (pp. 212–218). Springer. http://dx.doi.org/10.1007/978-94-011-5318-8_75
    38. Dabov, K., Foi, A., Katkovnik, V., & Egiazarian, K. (2007). Image denoising by sparse 3-D transform-domain collaborative filtering. IEEE Trans-actions on Image Processing, 16(8), 2080–2095. https://doi.org/10.1109/TIP.2007.901238

  • Downloads

  • How to Cite

    Sahoo , A. K. ., & Rajavel, R. (2025). Enhanced Wavelet Block Shrinkage Technique For Mammogram Denoising Using K-Means Clustering And Neural Networks. International Journal of Basic and Applied Sciences, 14(4), 648-660. https://doi.org/10.14419/8psp9843