Thyroid Cancer Diagnosis with Machine Learning: A Multimodal Ensemble Approach for Clinical Decision Support
Keywords:
Deep Learning, Machine Learning, Ensemble Methods, Thyroid ultrasound, Thyroid cancer diagnosisAbstract
Despite ongoing research, the current diagnostic methods of thyroid cancer may still have limitations, leading to potential errors in determining the malignancy of thyroid nodules. To address these challenges, this research introduces a cutting-edge multimodal thyroid cancer diagnosis framework that integrates data from multiple sources, including both ultrasound images and its clinical data. To carry out the experiments, the researchers utilised the Thyroid Nodule Ultrasound Images Dataset (TDID), an open-access public dataset.
The research is divided into two phases. In phase I, a wide range of machine learning and deep learning models are employed to create thyroid cancer prediction models using thyroid US image and the corresponding clinical data. The models that consistently demonstrated high prediction accuracy are selected for further consideration. Phase II focuses on creating ensemble combinations of models to perform multimodal prediction of thyroid nodules. The results of the experiments are highly promising, with certain ensemble combinations achieving impressive accuracy. A web app interface, ThyroPredict, has been developed, to generate a final prediction from the uploaded ultrasound image and initial radiologist's input. ThyroPredict app is powered by multimodal ensemble framework.
Downloads
References
Parul Puri et al., “Burden and determinants of multimorbidity among women in reproductive age group: a cross-sectional study based in India.,” 2021 Feb 18. doi: 10.12688/wellcomeopenres.16398.2
American Cancer Society. Cancer Statistics Center. https://cancerstatisticscenter.cancer.org/ (2023).
Kitahara CM, Sosa JA. “The changing incidence of thyroid cancer”, Nat Rev Endocrinol 2016 Nov;12(11):646-653.
Davies L, Welch HG. “Current thyroid cancer trends in the United States”, JAMA Otolaryngol Head Neck Surg. 2014 Apr;140(4):317-22.
Tessler, F.N.; Middleton, W.D.; Grant, E.G.; Hoang, J.K.; Berland, L.L.; Teefey, S.A.; Cronan, J.J.; Beland, M.D.; Desser, T.S.; Frates, M.C.; et al. “ACR Thyroid Imaging, Reporting and Data System (TI-RADS): White Paper of the ACR TI-RADS Committee.” J. Am. Coll. Radiol. 2017, 14, 587–595. [CrossRef] [PubMed]
Kwak, J.Y.; Han, K.H.; Yoon, J.H.; Moon, H.J.; Son, E.J.; Park, S.H.; Jung, H.K.; Choi, J.S.; Kim, B.M.; Kim, E.-K. “Thyroid Imaging Reporting and Data System for US Features of Nodules: A Step in Establishing Better Stratification of Cancer Risk”, Radiology 2011, 260, 892–899. [CrossRef]
W. Song et al., "Multitask Cascade Convolution Neural Networks for Automatic Thyroid Nodule Detection and Recognition," in IEEE Journal of Biomedical and Health Informatics, vol. 23, no. 3, pp. 1215-1224, May 2019, doi: 10.1109/JBHI.2018.2852718.
Yi-Cheng Zhu, Alaa AlZoubi, Sabah Jassim, Quan Jiang, Yuan Zhang, Yong-Bing Wang, Xian-De Ye, Hongbo DU, “A generic deep learning framework to classify thyroid and breast lesions in ultrasound images”, Ultrasonics, Volume 110, 2021, 106300, ISSN 0041-624X, https://doi.org/10.1016/j.ultras.2020.106300.
Gayathry Sobhanan Warrier ,1T. M. Amirthalakshmi, K. Nimala, T. Thaj Mary Delsy, P. Stella Rose Malar, G. Ramkumar, and Raja Raju, Yuvaraja Teekaraman, “Automated Recognition of Cancer Tissues through Deep Learning Framework from the Photoacoustic Specimen”, Hindawi, Volume 2022 | Article ID 4356744
Elmer Jeto Gomes Ataide, Nikhila Ponugoti, Alfredo Illanes, Simone Schenke, Michael Kreissl, and Michael Friebe, “Thyroid Nodule Classification for Physician Decision Support Using Machine Learning-Evaluated Geometric and Morphological Features”, Sensors 2020, 20, 6110; doi:10.3390/s20216110
Chen HL, Yang B, Wang G, Liu J, Chen YD, Liu DY. “A three-stage expert system based on support vector machines for thyroid disease diagnosis.”, J Med Syst. 2012 Jun;36(3):1953-63. doi: 10.1007/s10916-011-9655-8. Epub 2011 Feb 1. PMID: 21286792.
Khalid Salman and Emrullah Sonuç, “Thyroid Disease Classification Using Machine Learning Algorithms”, 2021 J. Phys.: Conf. Ser. 1963 012140 doi:10.1088/1742-6596/1963/1/012140
Koundal, D.; Gupta, S.; Singh, S., “Computer aided thyroid nodule detection system using medical ultrasound images”; Biomed. Signal Process. Control 2018, 40, 117–130. [CrossRef]
Gu Jianhua, Xie Rongli, Zhao Yanna, Zhao Zhifeng, Xu Dan, Ding Min, Lin Tingyu, Xu Wenjuan, Nie Zihuai, Miao Enjun, Tan Dan, Zhu Sibo, Shen Dongjie, Fei Jian, “A machine learning-based approach to predicting the malignant and metastasis of thyroid cancer “, Frontiers in Oncology 12 2022, https://www.frontiersin.org/articles/10.3389/fonc.2022.938292, doi=10.3389/fonc.2022.938292
Nanda S, M Sukumar "Identification of Thyroid Cancerous Nodule using Local Binary Pattern Variants in Ultrasound Images", International Journal of Engineering Trends and Technology (IJETT), V49(6),369-374 July 2017. ISSN:2231-5381. www.ijettjournal.org. published by seventh sense research group. [CrossRef]
Xi, N.M., Wang, L. & Yang, C. Improving the diagnosis of thyroid cancer by machine learning and clinical data. Sci Rep 12, 11143 (2022). https://doi.org/10.1038/s41598-022-15342-z
Li W, Cheng S, Qian K, Yue K, Liu H. Automatic Recognition and Classification System of Thyroid Nodules in CT Images Based on CNN. Comput Intell Neurosci. 2021 May 27; 2021:5540186. doi: 10.1155/2021/5540186. PMID: 34135949; PMCID: PMC8175135.
Pedraza L., Vargas C., Narvaez F., Duran O., Munoz E., Romero E. An open access thyroid ultrasound-image database; Proceedings of the 10th International Symposium on Medical Information Processing and Analysis; Cartagena de Indias, Colombia. 28 January 2015; pp. 1–6. [Google Scholar]
Horvath E, Majlis S, Rossi R, Franco C, Niedmann JP, Castro A, et al. An ultrasonogram reporting system for thyroid nodulesstratifying cancer risk for clinical management. J Clin EndocrinolMetab 2009; 94(5):1748-51
Nguyen DT, Pham TD, Batchuluun G, Yoon HS, Park KR. Artificial Intelligence-Based Thyroid Nodule Classification Using Information from Spatial and Frequency Domains. J Clin Med. 2019 Nov 14;8(11):1976. doi: 10.3390/jcm8111976. PMID: 31739517; PMCID: PMC6912332.
Zhu Y., Fu Z., Fei J. An image augmentation method using convolutional network for thyroid nodule classification by transfer learning; Proceedings of the 3rd IEEE International Conference on Computer and Communication; Chengdu, China. 13–16 December 2017; pp. 1819–1823. [Google Scholar]
Chi J., Walia E., Babyn P., Wang J., Groot G., Eramian M. “Thyroid nodule classification in ultrasound images by fine-tuning deep convolutional neural network.” J. Digit. Imaging. 2017;30:477–486. doi: 10.1007/s10278-017-9997-y. [PMC free article] [PubMed] [CrossRef] [Google Scholar]
Szegedy C, Vanhoucke V, Ioffe S, “Rethinking the Inception architecture for computer vision”, [C]//Proceedings of the IEEE Conference on Computer Vision and Pattern Recognition. 2016; 2818-26. [Ref list]
Evaluation: From Precision, Recall and F-Measure to ROC, Informedness, Markedness & Correlation. Journal of Machine Learning Technologies.
Sundar K.V.S., Rajamani K.T., Sai S.-S.S. Proceedings of the International Conference on ISMAC in Computational Vision and Bio-Engineering. Springer; Cham, Germany: 2018. “Exploring image classification of thyroid ultrasound images using deep learning”, pp. 1635–1641. [Google Scholar]
Guan Q, Wang Y, Ping B, Li D, Du J, Qin Y, Lu H, Wan X, Xiang J.;” Deep convolutional neural network VGG-16 model for differential diagnosing of papillary thyroid carcinomas in cytological images: a pilot study.”; J Cancer. 2019 Aug 27; 10(20):4876-4882. doi: 10.7150/jca.28769. PMID: 31598159; PMCID: PMC6775529.
Luoyan Wang, et.al, “A Multi-Scale Densely Connected Convolutional Neural Network for Automated Thyroid Nodule Classification,” Front Neurosci. 2022; 16: 878718., Published online 2022 May 19. doi:10.3389/fnins.2022. 878718.
Nguyen DT, Kang JK, Pham TD, Batchuluun G, Park KR. “Ultrasound Image-Based Diagnosis of Malignant Thyroid Nodule Using Artificial Intelligence.,” Sensors (Basel). 2020 Mar 25;20(7):1822. doi: 10.3390/s20071822. PMID: 32218230; PMCID: PMC7180806.
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.
