Ultrason görüntülerinde benek gürültüsünün azaltımı için hibrit dalgacık tabanlı yaklaşım

Öz

Ultrason görüntülemenin doğasında bulunan benek gürültüsü (speckle noise), tanısal doğruluğu düşürmektedir. Bu bağlamda, bu çalışma dalgacık tabanlı dinamik eşikleme ile Gauss ön filtrelemeyi birleştiren hibrit bir gürültü giderme yöntemi önerilmektedir. Çalışmada, dalgacık tabanlı dinamik eşikleme ile Gauss ön filtrelemeyi birleştiren hibrit bir gürültü giderme yöntemi önerilmiştir. Yöntem; çarpımsal gürültüyü logaritmik dönüşümle toplamsal hale getirme, Gauss ön filtreleme uygulama, 2D-DWT ve detay katsayılarına Tri-shrink eşikleme uygulama adımlarını içerir. Yöntem, Breast Ultrasound Images (BUSI) veri kümesinden seçilen 780 meme ultrason görüntüsü üzerinde yedi farklı geleneksel ve modern yöntemle karşılaştırılmıştır. Deneysel sonuçlar, önerilen yöntemin ortalama 29.59 dB PSNR (Tepe Sinyal Gürültü Oranı) ve 0.8367 SSIM (Yapısal Benzerlik İndeksi Ölçütü) değerlerine ulaştığını; ayrıca ENL (Eşdeğer Görüntü Sayısı) ve EPI (Kenar Koruma İndeksi) için sırasıyla 4.48 ve 0.82 sonuçları elde ettiğini göstermektedir. Gerçekleştirilen istatistiksel analizler (p <0.05), önerilen yaklaşımın karşılaştırılan tüm yöntemlere göre anlamlı düzeyde daha yüksek performans sergilediğini ortaya koymaktadır. Bu bulgular, geliştirilen yöntemin benek gürültüsünü etkin biçimde bastırırken dokusal ayrıntıları koruduğunu göstermektedir.

Anahtar Kelimeler

• Benek gürültüsü
• Dalgacık dönüşümü
• Gürültü bastırma
• Tri-shrink algoritması
• Ultrason görüntüleri

A hybrid wavelet based approch for speckle noise reduction in ultrasound imaging

Abstract

Speckle noise inherent in ultrasound imaging reduces diagnostic accuracy. In this context, this study proposes a hybrid noise reduction method that combines wavelet-based dynamic thresholding with Gaussian pre-filtering. The study proposes a hybrid noise reduction method that combines wavelet-based dynamic thresholding with Gaussian pre-filtering. The method includes the steps of converting multiplicative noise to additive noise using logarithmic transformation, applying Gaussian pre-filtering, and applying Tri-shrink thresholding to the 2D-DWT and detail coefficients. The method was compared with seven different traditional and modern methods on 780 breast ultrasound images selected from the Breast Ultrasound Images (BUSI) dataset. Experimental results show that the proposed method achieved an average of 29.59 dB PSNR (Peak Signal-to-Noise Ratio) and 0.8367 SSIM (Structural Similarity Index Measure) values; and also obtained results of 4.48 and 0.82 for ENL (Equivalent Number of Images) and EPI (Edge Preservation Index), respectively. The statistical analyses performed (p <0.05) reveal that the proposed approach exhibits significantly higher performance than all compared methods. These findings demonstrate that the developed method effectively suppresses speckle noise while preserving textural details.

Keywords

• Speckle noise
• Wavelet transform
• Denoising
• Tri-shrink algorithm
• Ultrasound images

Kaynakça

1. X. Chen, X. Wang, K. Zhang, K. Fung, T. C. Thai, K. Moore, R. S. Mannel, H. Liu, B. Zheng and Y. Qiu, Recent advances and clinical applications of deep learning in medical image analysis. Medical Image Analysis, 79, 102444, 1-15, 2022. https://doi.org/10. 1016/j.media.2022.102444.
2.     P. M. Cheng, E. Montagnon, R. Yamashita, I. Pan, A. Cadrin-Chênevert, F. P. Romero, G. Chartrand, S. Kadoury and A. Tang, Deep learning: an update for radiologists. Radiographics, 41(5), 1427–1445, 2021. https://doi.org/10.1148/rg.2021200210.
3.     R. L. Siegel, K. D. Miller, H. E. Fuchs and A. Jemal, Cancer Statistics. CA: A Cancer Journal for Clinicians, 73(1), 17–48, 2023. https://doi.org/10.3322/caac.21 763.
4.     A. Bennett, N. Shaver, N. Vyas, F. Almoli, R. Pap, J. Wilkinson and D. Moher, Screening for breast cancer: a systematic review update to inform the Canadian Task Force on Preventive Health Care guideline. Systematic Reviews, 13, 304, 1-18, 2024. https://doi. org/10.1186/s13643-024-02700-3.
5.     B. Gupta and V. Khandelwal, A new technique based on adaptive multi-resolution image decomposition using adaptive thresholding for ultrasound speckle reduction. Journal of Circuits, Systems and Computers, 31(5), 2050047, 2022. https://doi.org/10.1142/S02 18126623500779.
6.     W. A. Berg, Combined screening with ultrasound and mammography vs mammography alone in women at elevated risk of breast cancer. JAMA, 299(18), 2151, 2008. https://doi.org/10.1001/jama.299.18.2151.
7.     S. Sudha, G. R. Suresh and R. Sukanesh, Speckle noise reduction in ultrasound images using context-based adaptive wavelet thresholding. IETE Journal of Research, 55(3), 135–143, 2009. https://doi.org/10. 4103/0377-2063.54891.
8.     N. Y. Yu and S. Acton, Speckle reducing anisotropic diffusion. IEEE Transactions on Image Processing, 11(11), 1260–1270, 2002. https://doi.org/10.1109/tip. 2002.804276.

9.     H.-C. Lee, L.-M. Chen and N.-F. Lin, Systematic review and meta‑analysis of ultrasound features differentiating benign from malignant breast lesions. Journal of Ultrasound in Medicine, 42(2), 253–267, 2023. https://doi.org/10.1002/jum.15309.
10.   A. Santonocito, G. Di Leo, P. Panizza, M. Bazzocchi, C. Zuiani and F. Sardanelli, Head‑to‑head comparison of contrast‑enhanced mammography and contrast‑enhanced MRI in breast cancer detection: A systematic review and meta‑analysis. Radiology, 301(2), 345–355, 2021. https://doi.org/10.1148/radiol. 212530.
11.   F. Gaillard, H. Knipe, A. Ashraf and et al., Benign and malignant characteristics of breast lesions at ultrasound. Radiopaedia, 1-10, 2025. https://doi.org/ 10.53347/rID-1014.
12.   R. Tenajas, D. Miraut, C. I. Illana, R. Alonso-Gonzalez, F. Arias-Valcayo and J. L. Herraiz, Recent advances in artificial intelligence-assisted ultrasound scanning. Applied Sciences, 13(6), 3693, 2023. https://doi.org /10.3390/app13063693.
13.   A. Achim, A. Bezerianos and P. Tsakalides, Novel Bayesian multiscale method for speckle removal in medical ultrasound images. IEEE Transactions on Medical Imaging, 20(8), 772–783, 2001. https://doi. org/10.1109/42.938245.
14.   M. N. Khan and A. Altalbe, Experimental evaluation of filters used for removing speckle noise and enhancing ultrasound image quality. Biomedical Signal Processing and Control, 73, 103399, 2021. https://doi.org/10.1016/j.bspc.2021.103399.
15.   A. K. Bedi and R. K. Sunkaria, Ultrasound speckle reduction using adaptive wavelet thresholding. Multidimensional Systems and Signal Processing, 38, 2525–2542, 2021. https://doi.org/10.1007/s11045-021-00799-4.
16.   S. K. Randhawa, R. K. Sunkaria and E. Puthooran, Despeckling of ultrasound images using novel adaptive wavelet thresholding function. Multidimensional Systems and Signal Processing, 30(3), 1545–1561, 2019. https://doi.org/10.1007/s11045-018-0616-y.
17.   C. Tian, Y. Xu and W. Zuo, Image denoising using deep CNN with batch renormalization. Neural Networks, 121, 461-473, 2020. https://doi.org/10. 1016/j.neunet.2019.08.022.
18.   S. W. Zamir, A. Arora, S. Khan, M. Hayat, F. S. Khan and M. H. Yang, Restormer-plus: towards practical and efficient image restoration. IEEE Transactions on Pattern Analysis and Machine Intelligence, 1-12, 2024. https://doi.org/10.48550/arXiv.2111.09881.
19.   BUSI Dataset, Breast ultrasound images dataset (BUSI). Kaggle, 2018. https://www.kaggle.com/ datasets/aryashah2k/breast-ultrasound-images-dataset.
20.   A. A. Chaaraoui, A. A. El-Sallab and A. García, Total variation‐based ultrasound image despeckling using homomorphic log transformation. International Journal on Advances in Imaging, 11, 140–153, 2021. https://doi.org/10.1002/ima.22851.
21.   S. Suryanarayana, A. Y. S. Varma, H. Jinaga and K. P. Kumar, Speckle noise reduction in ultrasound images using a hybrid SRAD–DWT–guided filtering approach. International Journal of Research in Applied Science and Engineering Technology (IJRASET), 11(3), 379–387, 2023. https://doi.org/10.22214/ijraset.2023.526 72.
22.   R. S. Chowdhury, J. Jana, S. Tripathi and J. Bhaumik, Improved DWT and IDWT architectures for image compression. Microprocessors and Microsystems, 104, 104990, 2023. https://doi.org/10.1016/j.micpro.2023. 104990.
23.   S. Makgakga and P. Sepeng, Teaching and learning the mathematical exponential and logarithmic functions: a transformation approach. Mediterranean Journal of Social Sciences, 4(13), 177, 2013. https://doi.org/ 10.5901/mjss.2013.v4n13p177.
24.   F. Olaoye, A. Egon and L. Doris, Deep learning techniques for medical image analysis and diagnosis. International Journal of Computer Vision, 1-18, 2024. https://doi.org/10.21203/rs.3.rs-5339461/v1.
25.   E. O. Rybakova, E. E. Limonova and D. P. Nikolaev, Fast gaussian filter approximations comparison on SIMD computing platforms. Applied Sciences, 14(11), 4664, 2024. https://doi.org/10.3390/app14114664.
26.   N. Cao and Y. Liu, High-Noise Grayscale image denoising using an improved median filter for the adaptive selection of a threshold. Applied Sciences, 14(2), 635, 2024. https://doi.org/10.3390/app140206 35.
27.   V. Göreke, A novel method based on Wiener filter for denoising Poisson noise from medical X-Ray images. Biomedical Signal Processing and Control, 79, 104031, 2022. https://doi.org/10.1016/j.bspc.2022.104031.
28.   E. Radhi and M. Kamil, Anisotropic diffusion method for speckle noise reduction in breast ultrasound images. International Journal of Intelligent Engineering and Systems, 17(2), 621–631, 2024. https://doi.org/10. 22266/ijies2024.0430.50.
29.   N. Nezamoddini-Kachouie and P. Fieguth, A gabor based technique for image denoising. Canadian Conference on Electrical and Computer Engineering, 980–983, 2006. https://doi.org/10.1109/ccece.2005.15 57140.
30.   X. Li, Y. Wang, Y. Zhao and Y. Wei, Fast speckle noise suppression algorithm in breast ultrasound image using three-dimensional deep learning. Frontiers in Physiology, 13, 880966, 2022. https://doi.org/10.3389 /fphys.2022.880966.
31.   M. Khalifa, H. M. Hamza and K. M. Hosny, De-speckling of medical ultrasound image using metric-optimized knowledge distillation. Scientific Reports, 15(1), 2025. https://doi.org/10.1038/s41598-025-07115-1.
32.   T. O. Hodson, T. M. Over and S. S. Foks, Mean squared error, Deconstructed. Journal of Advances in Modeling Earth Systems, 13(12), 2021. https://doi.org/10. 1029/2021ms002681.
33.   A. Hore and D. Ziou, Image quality metrics: PSNR vs. SSIM. 2010 20th International Conference on Pattern Recognition, 2366–2369, 2010. https://doi.org/10. 1109/ICPR.2010.579.
34.   S. Anfinsen, A. Doulgeris and T. Eltoft, Estimation of the equivalent number of looks in polarimetric synthetic aperture radar imagery. IEEE Transactions on Geoscience and Remote Sensing, 47(11), 3795–3809, 2009. https://doi.org/10.1109/tgrs.2009.2019269.
35.   R. C. Bolles, H. H. Baker and D. H. Marimont, Epipolar-plane image analysis: An approach to determining structure from motion. International Journal of Computer Vision, 1(1), 7–55, 1987. https://doi.org/10.1007/bf00128525.