SUPPRESSION OF SPECKLE NOISE IN MEDICAL IMAGES VIA SEGMENTATION-GROUPING OF 3D OBJECTS USING SPARSE CONTOURLET REPRESENTATION

V. F. Kravchenko; Кравченко В. Ф.; Yu. V. Guliaev; Гуляев Ю. В.; V. I. Ponomaryov; Пономарев В. И.; G. Aranda Bojorges; Аранда-Бохоргес Г.

doi:10.31857/S2686954322600562

SUPPRESSION OF SPECKLE NOISE IN MEDICAL IMAGES VIA SEGMENTATION-GROUPING OF 3D OBJECTS USING SPARSE CONTOURLET REPRESENTATION

Authors: Kravchenko V.F.¹^,2, Guliaev Y.V.¹, Ponomaryov V.I.³, Bojorges G.A.³
Affiliations:
1. Kotelnikov Institute of Radioengineering and Electronics of the Russian Academy of Sciences
2. Bauman Moscow State Technical University
3. Instituto Politecnico Nacional de Mexico
Issue: Vol 509 (2023)
Pages: 94-100
Section: COMPUTER SCIENCE
URL: https://ruspoj.com/2686-9543/article/view/647926
DOI: https://doi.org/10.31857/S2686954322600562
EDN: https://elibrary.ru/CQFBDY
ID: 647926

Cite item

Full Text

Open Access
Restricted Access

Access granted
Restricted Access

Subscription or Fee Access

Abstract

Novel filtering method in medical images (MRI and US) that are contaminated by noise consisting of mixture speckle and additive noise is designed in this paper. Proposed method consists of several stages: segmentation of image areas, grouping of similar 2D structures in accordance mutual information (MI) measure, homomorphic transformation, 3D filtering approach based on sparse representation in contourlet (CLT) space with posterior filtering in accordance with MI weights similar 2D structures, and final inverse homomorphic transformation. During numerous experiments, the developed method has confirmed their superiority in term of visual image quality via human visual perception as well as in better criteria values, such as PSNR, SSIM, EPI and alfa for different test MRI and US mages corrupted by speckle noise.

Keywords

filtering, speckle noise, additive noise, homomorphic transformation, Mutual Information, peak signal/noise ratio

References

Кравченко В.Ф., Пономарев В.И., Пустовойт В.И., Аранда-Бохоргес Г. // Доклады РАН. Математика, информатика, процессы управления. 2021. Т. 499. № 2. С. 67–72.
Aranda-Bojorges G., Ponomaryov V., Reyes-Reyes R., Cruz-Ramos C., Sadovnychiy S. // IEEE Geosci. Rem. Sens. Lett. 2020. V. 19, art. 4018005. https://doi.org/10.1109/LGRS.2021.3108774
Reyes-Reyes R., Aranda-Bojorges G., Garcia-Salgado B., Ponomaryov V., Cruz-Ramos C., Sadovnychiy S. // Sensors. 2022. V. 22. 5113. https://doi.org/10.3390/s22145113
Kravchenko V., Perez H., Ponomaryov V. Adaptive Signal Processing of Multidimensional Signals with Applications. Moscow: Fizmatlit, 2009.
Dabov K., Foi A., Katkovnik V., Egiazarian K. // IEEE Trans. Image Process. 2007. V. 16. № 8. P. 2080–2095.
Santos C.A.N., Martins D.L.N., Mascarenhas N.D.A. // IEEE Trans. Image Process. 2017. V. 26. 2632–2643. https://doi.org/10.1109/TIP.2017.2685339
Sameera V.M.S., Sudhish N.G. // Sensing Imaging. 2017. V. 18. P. 1–28. https://doi.org/10.1007/s11220-017-0181-8
Jubairahmed L., Satheeskumaran S., Venkatesan C. // Clust. Comput. 2019. V. 22. P. 11237–11246.
Jaburalla M.Y., Lee H.N. // Appl. Sci. 2018. V. 8. 903. P. 1–17. https://doi.org/10.3390/app8060903
Achanta R., Shaji A., Smith K., Lucchi A., Fua P., Süsstrunk S. // IEEE Trans. Pattern Anal. Mach. Intell. 2012. V. 34. P. 2274–2282.
Jensen J.A. // Med. Biol. Eng. Comput. 1996. V. 34. P. 351–352.
Wang Z., Bovik A. // IEEE Signal Process. Mag. 2009. V. 26. № 1. P. 98–117.
https://openfmri.org/dataset/ (accessed: June21, 2022).
http://splab.cz/en/download/databaze/ultrasound (accessed: June 19, 2022).