Information Preserving and Edge Smoothening of Fetal Heart Chamber Using SRDCF with Total Variation

Main Article Content

C Shobana Nageswari
Mukesh S
S.Gayathri Priya
N. Vini Antony Grace
S.Rajan

Keywords

Spatially Regularized Discriminative Correlation Filter, Discriminative Correlation Filter, Total Variation Denoising, Speckle Noise

Abstract

Speckle is an inherent coarse noise that degrades medical ultrasound images. A point is created by the interference of the return wave in the sensor hole. In each resolution cell, several primary scatterers replicate the wave impinging on the sensor. In addition, the obtained images are corrupted by random grain patterns, making image interpretation difficult. Stains may contain useful diagnostic information. The smoothness of spotting depends on the application and knowledge of the doctor. In this work, preprocessing of fetal heart ultrasound images using a Spatially Regularized Discriminative Correlation Filter (SRDCF) with total variation is introduced to preserve fetal heart information and smooth edges. Then qualitatively and quantitatively compare the performance of the proposed filter with conventional methods.

Abstract 131 | pdf Downloads 148

References

1. Karthikeyan, T. Manikandan, V. Nandalal, J. L. Mazher Iqbal and J. J. Babu, "A Survey on Despeckling Filters for Speckle Noise Removal in Ultrasound Images," 2019 3rd International conference on Electronics, Communication and Aerospace Technology (ICECA), Coimbatore, India, 2019, pp. 605-609, doi: 10.1109/ICECA.2019.8822052.
2. Kaitheri Thacharedath Dilna and Duraisamy Jude Hemanth Novel image enhancement approaches for despeckling in ultrasound images for fibroiddetection in human uterus De Gruyter Open Computer Science 2021; 11: 399–410.https://doi.org/10.1515/comp-2020-0140.
3. C. S. Nageswari and K. H. Prabha, "Despeckle process in ultrasound fetal image using hybrid spatial filters," 2013 International Conference on Green Computing, Communication and Conservation of Energy (ICGCE), Chennai, India, 2013, pp. 174-179, doi: 10.1109/ICGCE.2013.6823423.
4. Nagashettappa Biradar,1 M. L. Dewal,1 and Manoj Kumar Rohit,"Edge Preserved Speckle Noise Reduction Using Integrated Fuzzy Filters" ,International Scholarly Research Notices, vol. 2014, Article ID 876434, 11 pages, 2014. https://doi.org/10.1155/2014/876434.
5. Onur Karaoğlu et al, Hasan Şakir Bilge, İhsan Uluer,"Removal of speckle noises from ultrasound images using five different deep learning networks", Engineering Science and Technology,,Vol ,2022,101030,0986,https://doi.org/10.1016/j.jestch.2021.06.010.
6. P.V.V. Kishore, K.L. Mallika, M.V.D. Prasad, K.L. Narayana, "Denoising Ultrasound Medical Images with Selective Fusion in Wavelet Domain",Procedia Computer Science,Volume 58,2015,Pages 129-139,ISSN 1877-0509,https://doi.org/10.1016/j.procs.2015.08.040
7. Hyunho Choi and Jechang Jeong, "Despeckling Algorithm for Removing Speckle Noise from Ultrasound Images" Symmetry 2020, 12, 938; doi:10.3390/sym12060938.
8. Rajeshwar Dass,"Speckle Noise Reduction of Ultrasound Images Using BFO Cascaded with Wiener Filter and Discrete Wavelet Transform in Homomorphic Region", Procedia Computer Science,Vol 132,2018, 1543-1551,ISSN 1877-0509,https://doi.org/10.1016/j.procs.2018.05.118
9. Szczepański M, Radlak K. Digital Path Approach Despeckle Filter for Ultrasound Imaging and Video. J Healthc Eng. 2017;2017:9271251. doi: 10.1155/2017/9271251. Epub 2017 Oct 8. PMID: 29118965; PMCID: PMC5651154.
10. Kriti, J. Virmani, and R. Agarwal, ‘‘Assessment of despeckle filtering algorithms for segmentation of breast tumours from ultrasound images’’, Biocybern. Biomed. Eng., vol. 39, no. 1, pp. 100–121, Jan. 2019, doi: 10.1016/j.bbe.2018.10.002.
11. C. Shobana Nageswari, M.N. Vimal Kumarb, N. Vini Antony Grace and J. Thiyagarajan,‘‘Tunicate swarm-based grey wolf algorithm for fetal heart chamber segmentation and classification: a heuristic-based optimal feature selection concept’’,Journal of Intelligent & Fuzzy Systems 44 (2023) 1029–1041,DOI:10.3233/JIFS-221654.