A COMPREHENSIVE INVESTIGATION INTO THE DEVELOPMENT OF A DEEP LEARNING MODEL FOR ROBUST CLASSIFICATION IN THYROID DISEASE DIAGNOSIS
DOI:
https://doi.org/10.29121/shodhkosh.v4.i2.2023.3795Keywords:
Convolutional Neural Networks (CNN), Deep Learning, Thyroiddisease Classification, Medical Diagnostic Accuracy, Biomedical Image ProcessingAbstract [English]
In recent years, the emerging field of deep learning has attracted widespread attention, especially in its application to the detection of thyroid nodules, aiming to distinguish between benign and malignant cases. However, the lack of sufficient clinical images has posed a significant hurdle, hindering the development of effective deep learning models. This research introduces a pioneering deep learning-based characterization framework explicitly designed to address the challenge of detecting malignancy in thyroid nodules from healthcare medical images.The methodology used in this paper focuses on the use of convolutional neural networks. By improving the capabilities of CNNs, a powerful class of deep learning algorithms specifically designed for image processing, our study aims to improve the accuracy and efficiency of the diagnostic process for thyroid disease.The CNN method enables automated extraction of complex patterns and features from thyroid images, providing a robust framework for detecting and classifying thyroid abnormalities. This approach represents an important step forward in the use of advanced computational techniques to improve the efficiency of clinical diagnosis, especially in the thyroid diagnostic domain. The proposed deep learning framework not only represents architectural convergence but also makes significant improvements in overcoming data limitations in thyroid nodule detection. The integration of multi-level transfer learning enriches the model from different data sources, improving its ability to adapt to the complex features inherent in thyroid ultrasound images. Our findings highlight the potential of this approach to revolutionize diagnostic tools for thyroid nodules, meeting a critical need in the field of clinical imaging and diagnosis for more accurate and reliable Provides solutions. This research contributes to the broader landscape of deep learning in clinical diagnosis, pushing the boundaries of innovation and paving the way for improved diagnostic accuracy in the microscopic field of thyroid nodule characterization.
References
L. Aversano, M. L. Bernardi, M. Cimitile, A. Maiellaro and R. Pecori, “A systematic review on artificial intelligence techniques for detecting thyroid diseases,” PeerJ Computer Science, vol. 9, 2023. DOI: https://doi.org/10.7717/peerj-cs.1394
H. Fang, L. Gong, Y. Xu, Y. Zhuo, W. Kong, C. Peng and J. Yuan, “Reliable Thyroid Carcinoma Detection with Real-Time Intelligent Analysis of Ultrasound Images,” Ultrasound in Medicine and Biology, vol. 47, no. 3, 2021. DOI: https://doi.org/10.1016/j.ultrasmedbio.2020.11.024
X. Ma and L. Zhang, “Diagnosis of Thyroid Nodules Based on Image Enhancement and Deep Neural Networks,” Computational Intelligence and Neuroscience, vol. 2022, 2022. DOI: https://doi.org/10.1155/2022/5582029
T. Wang, D. Yan, Z. Liu, L. Xiao, C. Liang, H. Xin, M. Feng, Z. Zhao and Y. Wang, “Diagnosis of cervical lymph node metastasis with thyroid carcinoma by deep learning application to CT images,” Frontiers in Oncology, vol. 13, 2023. DOI: https://doi.org/10.3389/fonc.2023.1099104
X. Zhang, V. C. S. Lee, J. Rong, J. C. Lee and F. Liu, “Deep convolutional neural networks in thyroid disease detection: A multi-classification comparison by ultrasonography and computed tomography,” Computer Methods and Programs in Biomedicine, vol. 220, 2022. DOI: https://doi.org/10.1016/j.cmpb.2022.106823
C. S. Nageswari, M. N. V. Kumar, C. Raveena, J. S. Sharma and M. Y. Devi, “An Identification and Classification of Thyroid Diseases Using Deep Learning Methodology,” RevistaGestãoInovação e Tecnologias, vol. 11, no. 2, 2021. DOI: https://doi.org/10.47059/revistageintec.v11i2.1820
J. H. Moon and S. R. Steinhubl, Digital medicine in thyroidology: A new era of managing thyroid disease, vol. 34, 2019. DOI: https://doi.org/10.3803/EnM.2019.34.2.124
S. Yao, J. Yan, M. Wu, X. Yang, W. Zhang, H. Lu and B. Qian, “Texture Synthesis Based Thyroid Nodule Detection From Medical Ultrasound Images: Interpreting and Suppressing the Adversarial Effect of In-place Manual Annotation,” Frontiers in Bioengineering and Biotechnology, vol. 8, 2020. DOI: https://doi.org/10.3389/fbioe.2020.00599
T. Y. Yang, L. Q. Zhou, D. Li, X. H. Han and J. C. Piao, “An improved CNN-based thyroid nodule screening algorithm in ultrasound images,” Biomedical Signal Processing and Control, vol. 87, 2024. DOI: https://doi.org/10.1016/j.bspc.2023.105371
L. Wang, O. Sourina, M. Erdt, Y. Wang and Q. Chang, Machine learning methods for bio-medical image and signal processing: Recent advances, vol. 202, 2022. DOI: https://doi.org/10.1016/j.ymeth.2022.03.009
S. Sreelakshmi and V. S. Anoop, “A deep convolutional neural network model for medical data classification from computed tomography images,” Expert Systems, 2023. DOI: https://doi.org/10.1111/exsy.13427
L. A. Pramono, “COVID-19 and thyroid diseases: How the pandemic situation affects thyroid disease patients,” Journal of the ASEAN Federation of Endocrine Societies, vol. 35, no. 2, 2020. DOI: https://doi.org/10.15605/jafes.035.02.01
P. Poudel, A. Illanes, M. Sadeghi and M. Friebe, “Patch Based Texture Classification of Thyroid Ultrasound Images using Convolutional Neural Network,” Annual International Conference of the IEEE Engineering in Medicine and Biology Society. IEEE Engineering in Medicine and Biology Society. Annual International Conference, vol. 2019, 2019. DOI: https://doi.org/10.1109/EMBC.2019.8857929
S. Mallat, A Wavelet Tour of Signal Processing: The Sparse Way, 2008.
R. Khan and I. Kumar, Advancements in Bio-Medical Image Processing and Authentication in Telemedicine, 2023. DOI: https://doi.org/10.4018/978-1-6684-6957-6
J. Kaur and A. Jindal, “Comparison of Thyroid Segmentation Algorithms in Ultrasound and Scintigraphy Images,” International Journal of Computer Applications, vol. 50, no. 23, 2012. DOI: https://doi.org/10.5120/7959-0924
Downloads
Published
How to Cite
Issue
Section
License
Copyright (c) 2023 Minal Chaphekar, Omprakash Chandrakar
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.
