LIVER CANCER IMAGE PREPROCESSING AND FEATURE SELECTION USING A HYBRID DEEP LEARNING NETWORK
DOI:
https://doi.org/10.29121/shodhkosh.v5.i6.2024.2370Keywords:
Liver Segmentation, Deep Learning, VGG19, UNet, Liver CancerAbstract [English]
A liver's primary duties include producing bile, which is necessary for the breakdown of fats, filtering and changing potentially harmful compounds in the blood, and storing vitamins and nutrients. The diagnosis of malignant liver lesions can be made using a variety of techniques, including magnetic resonance imaging (MRI) and/or CT scanning with multiphase contrast agent injection. focuses on the methods for creating tumor and liver segmentation with the IVGG19-UNeT hybrid deep learning network. The suggested model's deep learning network scheme structure is made up of preprocessing, feature extraction, classification, and segmentation. With over 98% accuracy in tumor categorization, the suggested method accurately identifies the greatest number of tumor regions.
References
Chidambaranathan-Reghupaty, S., Fisher, P.B. and Sarkar, D. (2021) ‘Hepatocellular carcinoma (HCC): Epidemiology, etiology and Molecular Classification’, Advances in Cancer Research, pp. 1–61. doi:10.1016/bs.acr.2020.10.001. DOI: https://doi.org/10.1016/bs.acr.2020.10.001
Mizouri, N. (2022) Deep Learning neural network with transfer learning for liver cancer classification [Preprint]. doi:10.21203/rs.3.rs-2355564/v1. DOI: https://doi.org/10.21203/rs.3.rs-2355564/v1
Rahman, H. et al. (2022) ‘A deep learning approach for liver and tumor segmentation in CT images using ResUNet’, Bioengineering, 9(8), p. 368. doi:10.3390/bioengineering9080368. DOI: https://doi.org/10.3390/bioengineering9080368
Khoshkhabar, M. et al. (2023) ‘Automatic liver tumor segmentation from CT images using graph Convolutional Network’, Sensors, 23(17), p. 7561. doi:10.3390/s23177561. DOI: https://doi.org/10.3390/s23177561
Hansch, A. et al. (2022) ‘Improving automatic liver tumor segmentation in late-phase MRI using multi- model training and 3D convolutional Neural Networks’, Scientific Reports, 12(1). doi:10.1038/s41598- 022-16388-9. DOI: https://doi.org/10.1038/s41598-022-16388-9
Ozcan, F. et al. (2023) ‘Fully automatic liver and tumor segmentation from CT image using an AIM-Unet’, Bioengineering, 10(2), p. 215. doi:10.3390/bioengineering10020215. DOI: https://doi.org/10.3390/bioengineering10020215
Anwar, S.M. et al. (2018) ‘Segmentation of liver tumor for computer aided diagnosis’, 2018 IEEE-EMBS Conference on Biomedical Engineering and Sciences (IECBES) [Preprint]. doi:10.1109/iecbes.2018.8626682. DOI: https://doi.org/10.1109/IECBES.2018.8626682
El-Regaily, S.A. et al. (2020) ‘Multi-view convolutional neural network for lung nodule false positive reduction’, Expert Systems with Applications, 162, p. 113017. doi:10.1016/j.eswa.2019.113017. DOI: https://doi.org/10.1016/j.eswa.2019.113017
Clement Sherlin.Cet al.(2024) ‘Liver CT Image Noise Reduction using Enhanced Filtering and Edge Detection Technique for Liver Segmentation’Journal of Nonlinear Analysis and Optimization.Vol. 15, Issue. 1, No.4 2024 p-137-243[Preprint].
Clement Sherlin.Cet al.(2023) ‘Liver Cancer Segmentation through Enhanced Feature Extraction and Mapping using Improved Transfer Learning Techniques’International Journal on Recent and Innovation Trends in Computing and Communication,11(11), 38–43. doi.org/10.17762/ijritcc.v11i11.9085. DOI: https://doi.org/10.17762/ijritcc.v11i11.9085
Hossain, Md.S. et al. (2023) ‘Deep Learning Framework for liver segmentation from T1-weighted MRI images’, Sensors, 23(21), p. 8890. doi:10.3390/s23218890. DOI: https://doi.org/10.3390/s23218890
Downloads
Published
How to Cite
Issue
Section
License
Copyright (c) 2024 C. Clement Sherlin, Dr. N.A. Sheela Selvakumari
This work is licensed under a Creative Commons Attribution 4.0 International License.
With the licence CC-BY, authors retain the copyright, allowing anyone to download, reuse, re-print, modify, distribute, and/or copy their contribution. The work must be properly attributed to its author.
It is not necessary to ask for further permission from the author or journal board.
This journal provides immediate open access to its content on the principle that making research freely available to the public supports a greater global exchange of knowledge.
