AN ENTROPY-ADAPTIVE MODIFICATION OF THE PERONA–MALIK MODEL FOR SPECKLE NOISE SUPPRESSION IN ECHOCARDIOGRAPHIC ULTRASOUND IMAGES
Received: 2026-07-15 14:57:20
Published: 2026-04-18
Abstract
This paper investigates the problem of speckle noise reduction in ultrasound imaging, a key challenge that significantly affects diagnostic interpretation and automated segmentation accuracy. An entropy-driven adaptive modification of the classical Perona–Malik anisotropic diffusion model is proposed. Unlike the conventional model, the proposed approach adaptively controls the diffusion rate for each pixel using local statistical descriptors — namely, entropy and variance — thereby achieving spatially variant and context-sensitive smoothing. In homogeneous, low-entropy regions the model enhances diffusion to suppress multiplicative speckle noise, while in high-entropy regions diffusion is automatically slowed down to preserve structural details. Experimental validation demonstrates improvements of approximately 3–4 dB in PSNR and 0.06 in SSIM over the classical model.
Keywords
List of references
-
Savarese G., Lund L.H. Global public health burden of heart failure // Cardiac Failure Review. — 2017. — Vol. 3, No. 1. — P. 7–11.
-
Ponikowski P. et al. 2016 ESC guidelines for the diagnosis and treatment of acute and chronic heart failure // European Heart Journal. — 2016— Vol. 37, No. 27. — P. 2129–2200.
-
World Health Organization. Cardiovascular diseases (CVDs). — Geneva: WHO, 2021.
-
Litjens G. et al. A survey on deep learning in medical image analysis // Medical Image Analysis. — 2017. — Vol. 42. — P. 60–88.
-
Shen D., Wu G., Suk H.I. Deep learning in medical image analysis // Annual Review of Biomedical Engineering. — 2017. — Vol. 19. — P. 221–248.
-
Nieminen T. et al. Median filtering in medical image processing // Journal of Medical Imaging. — 2010. — Vol. 7. — P. 45–52.
-
Press W.H. et al. Numerical Recipes: The Art of Scientific Computing. — Cambridge: Cambridge University Press, 2007.
-
Zhang B., Allebach J.P. Adaptive bilateral filter for sharpness enhancement and noise removal // IEEE Transactions on Image Processing. — 2008. — Vol. 17, No. 5. — P. 664–678.
-
Portilla J. et al. Image denoising using scale mixtures of Gaussians in the wavelet domain // IEEE Transactions on Image Processing. — 2003. — Vol. 12, No. 11. — P. 1338–1351.
-
Zhu J.Y. et al. Unpaired image-to-image translation using cycle-consistent adversarial networks // Proceedings of the IEEE ICCV. — 2017. — P. 2223–2232.
-
Perona P., Malik J. Scale-space and edge detection using anisotropic diffusion // IEEE Transactions on Pattern Analysis and Machine Intelligence. — 1990. — Vol. 12, No. 7. — P. 629–639.
-
Kingsbury N. Complex wavelets for shift invariant analysis and filtering of signals // Applied and Computational Harmonic Analysis. — 2001. — Vol. 10, No. 3. — P. 234–253.
-
Rasmussen C.E., Williams C.K.I. Gaussian Processes for Machine Learning. — Cambridge: MIT Press, 2006.
-
Saunders C., Gammerman A., Vovk V. Ridge regression learning algorithm in dual variables // Proceedings of the 15th ICML. — 1998. — P. 515–521.
-
Jain A.K. Fundamentals of Digital Image Processing. — Upper Saddle River: Prentice-Hall, 1989.
-
Yu Y., Acton S.T. Speckle reducing anisotropic diffusion // IEEE Transactions on Image Processing. — 2002. — Vol. 11, No. 11. — P. 1260–1270.
-
Weickert J. Anisotropic Diffusion in Image Processing. — Stuttgart: Teubner, 1998.
-
Courant R., Friedrichs K., Lewy H. Über die partiellen Differenzengleichungen der mathematischen Physik // Mathematische Annalen. — 1928. — Vol. 100, No. 1. — P. 32–74.
-
Mohan J., Krishnaveni V., Guo Y. A survey on the magnetic resonance image denoising methods // Biomedical Signal Processing and Control. — 2014. — Vol. 9. — P. 56–69.
About the Authors
License
This work is licensed under a Creative Commons Attribution 4.0 International License.
How to Cite
