Machine Learning Approaches for Image Denoising and Artifact Removal in Medical Imaging
Keywords:
Recurrent Neural Network (RNN), CT lung images, Long Short-Term Memory (LSTM)Abstract
This study introduces a novel Recurrent Neural Network (RNN) for medical picture denoising that makes use of lengthy short-term memory-based batch normalisation. At first, noisy CT lung pictures are used as input. Denoising the input picture using an RNN. The training of deep neural networks that are feed-forward may now be sped up with the use of a technique known as batch normalisation. Batch normalisation is used in long-term short-term memory (LSTM), and it is shown to speed up optimisation and enhance generalisation. The Particle Swarm Optimisation (PSO) technique is used to choose the batch size in batch normalisation. MATLAB was used to create the suggested system. The experimental findings are compared to the current setup.
Downloads
References
Wang S., Summers R.M. Machine learning and radiology. J Med Image Anal. 2012;16:933–951.
Hassan M.A. Sixth International Conference on Digital Information Processing and Communications (ICDIPC) IEEE; Beirut, Lebanon: 2016. A comparative study of classification algorithms in e-health environment. pp. 42–7.
Gupta S., Chauhan R.C. Saxena. Homomorphic wavelet thresholding technique for denoising medical ultrasound images. Int J Med Eng Technol. 2005;29(5):208–214.
Donoho D.L. De-noising by soft-thresholding. IEEE Trans. Inf. Theory. 1992;41:613–627.
Gupta S., Chauhan R.C., Saxena S.C. A robust multi-scale non-homomorphic approach to speckle reduction in medical ultrasound images. IEEE J Int Fed Med Biol Eng. 2005;152(1):129–135.
Jenifa Sabeena, S. ., & Antelin Vijila, S. . (2023). Moulded RSA and DES (MRDES) Algorithm for Data Security. International Journal on Recent and Innovation Trends in Computing and Communication, 11(2), 154–162. https://doi.org/10.17762/ijritcc.v11i2.6140
Gupta S., Chauhan R.C., Saxena S.C. Locally adaptive wavelet domain bayesian processor for denoising medical ultrasound images using speckle modelling based on Rayleigh distribution.; 2005.
Gupta S., Kaur L., Chauhan R.C., et al. A wavelet based statistical approach for speckle reduction in medical ultrasound images. Med Image Process; 2003. pp. 534–537.
Gupta S., Kaur L., Chauhan R.C., et al. A versatile technique for visual enhancement of medical ultrasound images. Digit. Signal Process. 2007;17:542–560.
Gupta S., Chauhan R.C., Saxena S.C. A wavelet based statistical approach for speckle reduction in medical ultrasound images. IEEE J Int Fed Med Biol Eng. 2004;42:189–192.
Kaur L., Gupta S., Chauhan R.C., et al. Medical ultrasound image compression using joint optimization of thresholding quantization and best-basis selection of wavelet packets. Digit. Signal Process. 2007;17:189–198.
Kamble V.M., Parlewar P., Keskar A.G., et al. Performance evaluation of wavelet, ridgelet, curvelet and contourlet transforms based techniques for digital image denoising. Artif. Intell. Rev. 2016;45:509–533.
Singh, S. ., Wable, S. ., & Kharose, P. . (2021). A Review Of E-Voting System Based on Blockchain Technology. International Journal of New Practices in Management and Engineering, 10(04), 09–13. https://doi.org/10.17762/ijnpme.v10i04.125
Mendelson E.B., Bohm V.M., Berg W.A., et al. 2013. ACR BI-RADS Ultrasound.
Shan J., Alam S.K., Garra B., et al. Computer-aided diagnosis for breast ultrasound using computerized BI-RADS features and machine learning methods. Ultrasound Med. Biol. 2015;42(4):980–988.
Jain A. Denoising of medical ultrasound images in wavelet domain. Int J Eng Comp Sci. 2015;4(5):11871–11875.
Kaur L., Gupta S., Chauhan R.C. Image denoising using wavelet thresholding.; Indian conference on computer vision, graphics and image processing; 2002. pp. 1–4
Patil A.A., Singhai J. Image denoising using curvelet transform: An approach for edge preservation. J. Sci. Ind. Res. (India) 2010;69:34–38.
Downloads
Published
How to Cite
Issue
Section
License
This work is licensed under a Creative Commons Attribution-ShareAlike 4.0 International License.
All papers should be submitted electronically. All submitted manuscripts must be original work that is not under submission at another journal or under consideration for publication in another form, such as a monograph or chapter of a book. Authors of submitted papers are obligated not to submit their paper for publication elsewhere until an editorial decision is rendered on their submission. Further, authors of accepted papers are prohibited from publishing the results in other publications that appear before the paper is published in the Journal unless they receive approval for doing so from the Editor-In-Chief.
IJISAE open access articles are licensed under a Creative Commons Attribution-ShareAlike 4.0 International License. This license lets the audience to give appropriate credit, provide a link to the license, and indicate if changes were made and if they remix, transform, or build upon the material, they must distribute contributions under the same license as the original.