Advances in Artificial Intelligence for the Ultrasound Diagnosis of Thyroid Nodules
DOI:
https://doi.org/10.54097/4282w125Keywords:
Artificial Intelligence, Thyroid Nodules, Thyroid Cancer, Ultrasound Diagnosis, Deep Learning, Machine LearningAbstract
The increasing detection of thyroid nodules and thyroid cancer has made timely malignancy detection and the avoidance of unnecessary biopsy, surgery, and overtreatment important clinical priorities. Ultrasound is a convenient, real-time, inexpensive, easy-to-obtain and repeated non-invasive imaging method for screening and risk assessment of thyroid nodules. The diagnostic results of human operators and equipment settings can affect the sensitivity of image interpretation. Recently, with the development of artificial intelligence (AI), machine learning and deep learning have been applied to thyroid disease diagnosis. Segmentation of images, feature extraction, differentiation of benign and malignant nodules, risk stratification, biopsy decision support, cytological examination, contrast-enhanced ultrasound video analysis, and prediction of lymph node metastasis are all included. Research has shown that, at present, AI support can improve the precision and uniformity of diagnosis independently of operator experience. It will also be convenient for new doctors and health workers in primary care to use. Review of the technical foundations, current applications, advantages and disadvantages, and future directions of artificial intelligence in ultrasound diagnosis of benign and malignant thyroid tumors. To provide information on the clinical application and use of these technologies in personalised diagnosis and treatment.
Downloads
References
[1] Pizzato, M., Li, M., Vignat, J., Laversanne, M., Singh, D., Vaccarella, S., La Vecchia, C., & Bray, F. (2022). The epidemiological landscape of thyroid cancer worldwide: GLOBOCAN estimates for incidence and mortality rates in 2020. Lancet Diabetes & Endocrinology, 10(4), 264–272. https://doi.org/10.1016/S2213-8587(22)00035-3. DOI: https://doi.org/10.1016/S2213-8587(22)00035-3
[2] Durante, C., Grani, G., Lamartina, L., Filetti, S., Mandel, S. J., & Cooper, D. S. (2018). The diagnosis and management of thyroid nodules: A review. JAMA, 319(9), 914–924. https://doi.org/10.1001/jama.2018.0898. DOI: https://doi.org/10.1001/jama.2018.0898
[3] Kaul, V., Enslin, S., & Gross, S. A. (2020). History of artificial intelligence in medicine. Gastrointestinal Endoscopy, 92(4), 807–812. https://doi.org/10.1016/j.gie.2020.04.012. DOI: https://doi.org/10.1016/j.gie.2020.06.040
[4] Zhao, C. K., Ren, T. T., Yin, Y. F., Liu, B., & Wang, Y. (2021). A comparative analysis of two machine learning-based diagnostic patterns with Thyroid Imaging Reporting and Data System for thyroid nodules. Thyroid, 31(3), 470–481. https://doi.org/10.1089/thy.2020.0321. DOI: https://doi.org/10.1089/thy.2020.0305
[5] Vander, J. B., Gaston, E. A., & Dawber, T. R. (1968). The significance of nontoxic thyroid nodules. Annals of Internal Medicine, 69(3), 537–540. https://doi.org/10.7326/0003-4819-69-3-537. DOI: https://doi.org/10.7326/0003-4819-69-3-537
[6] Koundal, D., Gupta, S., & Singh, S. (2016). Automated delineation of thyroid nodules in ultrasound images using spatial neutrosophic clustering and level set. Applied Soft Computing, 40, 86–97. https://doi.org/10.1016/j.asoc.2015.11.015. DOI: https://doi.org/10.1016/j.asoc.2015.11.035
[7] Koundal, D., Gupta, S., & Singh, S. (2018). Computer aided thyroid nodule detection system using medical ultrasound images. Biomedical Signal Processing and Control, 40, 117–130. https://doi.org/10.1016/j.bspc.2017.09.012. DOI: https://doi.org/10.1016/j.bspc.2017.08.025
[8] Prochazka, A., Gulati, S., Holinka, S., & Smutek, D. (2019). Patch-based classification of thyroid nodules in ultrasound images using direction independent features extracted by two-threshold binary decomposition. Computerized Medical Imaging and Graphics, 71, 9–18. https://doi.org/10.1016/j.compmedimag.2018.10.002. DOI: https://doi.org/10.1016/j.compmedimag.2018.10.001
[9] Yu, Q., Jiang, T., Zhou, A., & Wang, H. (2017). Computer-aided diagnosis of malignant or benign thyroid nodes based on ultrasound images. European Archives of Oto-Rhino-Laryngology, 274(7), 2891–2897. https://doi.org/10.1007/s00405-017-4548-1. DOI: https://doi.org/10.1007/s00405-017-4562-3
[10] Ouyang, F. S., Guo, B. L., Ouyang, L. Z., & Chen, X. (2019). Comparison between linear and nonlinear machine-learning algorithms for the classification of thyroid nodules. European Journal of Radiology, 113, 251–257. https://doi.org/10.1016/j.ejrad.2019.02.017. DOI: https://doi.org/10.1016/j.ejrad.2019.02.029
[11] Tessler, F. N., & Thomas, J. (2023). Artificial intelligence for evaluation of thyroid nodules: A primer. Thyroid, 33(2), 150–158. https://doi.org/10.1089/thy.2022.0422. DOI: https://doi.org/10.1089/thy.2022.0560
[12] Acharya, U. R., Vinitha Sree, S., Mookiah, M. R., Yanti, R., & Saba, L. (2014). A review on ultrasound-based thyroid cancer tissue characterization and automated classification. Technology in Cancer Research & Treatment, 13(4), 289–301. https://doi.org/10.7785/tcrt.2012.500261. DOI: https://doi.org/10.7785/tcrt.2012.500381
[13] Feng, N., Zhao, S., Wang, K., & Li, Y. (2024). Deep learning model for diagnosis of thyroid nodules with size less than 1 cm: A multicenter, retrospective study. European Journal of Radiology Open, 13, 100609. https://doi.org/10.1016/j.ejro.2024.100609. DOI: https://doi.org/10.1016/j.ejro.2024.100609
[14] Xu, D., Sui, L., Zhang, C., & Li, Y. (2024). The clinical value of artificial intelligence in assisting junior radiologists in thyroid ultrasound: A multicenter prospective study from real clinical practice. BMC Medicine, 22(1), 293. https://doi.org/10.1186/s12916-024-03487-9. DOI: https://doi.org/10.1186/s12916-024-03510-z
[15] Li, X., Zhang, S., Zhang, Q., Wei, X., Zhang, Y., & Wang, Y. (2019). Diagnosis of thyroid cancer using deep convolutional neural network models applied to sonographic images: A retrospective, multicohort, diagnostic study. The Lancet Oncology, 20(2), 193–201. https://doi.org/10.1016/S1470-2045(18)30762-2. DOI: https://doi.org/10.1016/S1470-2045(18)30762-9
[16] Wang, J., Jiang, J., Zhang, D., & Li, X. (2022). An integrated AI model to improve diagnostic accuracy of ultrasound and output known risk features in suspicious thyroid nodules. European Radiology, 32(3), 2120–2129. https://doi.org/10.1007/s00330-021-08281-7. DOI: https://doi.org/10.1007/s00330-021-08298-7
[17] Rho, M., Chun, S. H., Lee, E., & Park, J. (2023). Diagnosis of thyroid micronodules on ultrasound using a deep convolutional neural network. Scientific Reports, 13(1), 7231. https://doi.org/10.1038/s41598-023-34478-2. DOI: https://doi.org/10.1038/s41598-023-34459-3
[18] Haugen, B. R., Alexander, E. K., Bible, K. C., Doherty, G. M., Mandel, S. J., Nikiforov, Y. E., Pacini, F., Randolph, G. W., Sawka, A. M., Schlumberger, M., Schuff, K. G., Sherman, S. I., Sosa, J. A., Steward, D. L., Tuttle, R. M., & Wartofsky, L. (2016). 2015 American Thyroid Association management guidelines for adult patients with thyroid nodules and differentiated thyroid cancer. Thyroid, 26(1), 1–133. https://doi.org/10.1089/thy.2015.0020. DOI: https://doi.org/10.1089/thy.2015.0020
[19] Lee, Y., Park, J., & Kim, J. (2024). Improved diagnostic accuracy of thyroid fine-needle aspiration cytology with artificial intelligence technology. Thyroid, 34(6), 723–734. https://doi.org/10.1089/thy.2023.0542. DOI: https://doi.org/10.1089/thy.2023.0384
[20] Hirokawa, M., Kondo, T., & Sato, K. (2023). Application of deep learning as an ancillary diagnostic tool for thyroid FNA cytology. Cancer Cytopathology, 131(4), 217–225. https://doi.org/10.1002/cncy.22684. DOI: https://doi.org/10.1002/cncy.22669
[21] Elliott Range, D. D., J. A., & Johnson, C. (2020). Application of a machine learning algorithm to predict malignancy in thyroid cytopathology. Cancer Cytopathology, 128(4), 287–295. https://doi.org/10.1002/cncy.22261. DOI: https://doi.org/10.1002/cncy.22238
[22] Alabrak, M. M. A., Megahed, M., Alkhouly, A. A., & El-Sayed, M. (2023). Artificial intelligence role in subclassifying cytology of thyroid follicular neoplasm. Asian Pacific Journal of Cancer Prevention, 24(4), 1379–1387. https://doi.org/10.2307/26940628. DOI: https://doi.org/10.31557/APJCP.2023.24.4.1379
[23] Liu, R., Yuan, F., Wang, B., & Zhang, H. (2025). A novel deep learning model based on multimodal contrast-enhanced ultrasound dynamic video for predicting occult lymph node metastasis in papillary thyroid carcinoma. Frontiers in Endocrinology, 16, 1634875. https://doi.org/10.3389/fendo.2025.1634875. DOI: https://doi.org/10.3389/fendo.2025.1634875
[24] Wan, P., Xue, H., Liu, C., & Chen, F. (2023). Dynamic perfusion representation and aggregation network for nodule segmentation using contrast-enhanced US. IEEE Journal of Biomedical and Health Informatics, 27(7), 3431–3442. https://doi.org/10.1109/JBHI.2023.3240829. DOI: https://doi.org/10.1109/JBHI.2023.3270307
[25] Chen, F., Han, H., Wan, P., & Liu, C. (2023). Joint segmentation and differential diagnosis of thyroid nodule in contrast-enhanced ultrasound images. IEEE Transactions on Biomedical Engineering, 70(9), 2722–2732. https://doi.org/10.1109/TBME.2023.3240830. DOI: https://doi.org/10.1109/TBME.2023.3262842
[26] Stack, B. C., Ferris, R. L., Goldenberg, D., Haymart, M. R., Shaha, A. R., & Tufano, R. P. (2012). American Thyroid Association consensus review and statement regarding lateral neck dissection in differentiated thyroid cancer. Thyroid, 22(5), 501–508. https://doi.org/10.1089/thy.2012.0031. DOI: https://doi.org/10.1089/thy.2011.0312
[27] Lee, J. H., Baek, J. H., Kim, J. H., & Choi, Y. J. (2018). Deep learning-based computer-aided diagnosis system for localization and diagnosis of metastatic lymph nodes on ultrasound: A pilot study. Thyroid, 28(10), 1332–1338. https://doi.org/10.1089/thy.2018.0176. DOI: https://doi.org/10.1089/thy.2018.0082
[28] Han, H., Sun, H., Zhou, C., & Wang, Y. (2025). Development and validation of a machine learning model for central compartmental lymph node metastasis in solitary papillary thyroid microcarcinoma via ultrasound imaging features and clinical parameters. BMC Medical Imaging, 25(1), 228. https://doi.org/10.1186/s12880-025-01687-0. DOI: https://doi.org/10.1186/s12880-025-01757-3
[29] Esce, A. R., Redemann, J. P., Sanchez, A. C., & Chen, H. (2021). Predicting nodal metastases in papillary thyroid carcinoma using artificial intelligence. The American Journal of Surgery, 222(5), 952–958. https://doi.org/10.1016/j.amjsurg.2021.02.030. DOI: https://doi.org/10.1016/j.amjsurg.2021.05.002
[30] Zhang, X. Y., Zhang, D., Wang, Z. Y., & Li, J. (2025). Automatic tumor segmentation and lymph node metastasis prediction in papillary thyroid carcinoma using ultrasound keyframes. Medical Physics, 52(1), 257–273. https://doi.org/10.1002/mp.17432. DOI: https://doi.org/10.1002/mp.17498
[31] Dai, F., Yao, S., Wang, M., & Zhang, Y. (2025). Improving AI models for rare thyroid cancer subtype by text guided diffusion models. Nature Communications, 16(1), 4449. https://doi.org/10.1038/s41467-025-58764-8. DOI: https://doi.org/10.1038/s41467-025-59478-8
[32] Guo, F. Q., Liu, S., Xu, L., & Zhang, Y. (2024). Ultrasound image analysis based on AI-SONIC TM Thyroid 5.3.3.0 to predict malignant risk of thyroid nodules. Academic Journal of Naval Medical University, 45(1), 29–36. (In Chinese.)
[33] Zhang, M. M., Gao, Z. Y., Wu, Q., & Li, H. (2025). Value of C-TIRADS and artificial intelligence assisted diagnosis system in diagnosis of thyroid nodules. Journal of Practical Oncology, 40(5), 447–451. (In Chinese.)
[34] Zeng, Y., Mao, J., Jiang, L., & Huang, X. (2025). Application of artificial intelligence-based ultrasound image recognition in the diagnosis of thyroid nodules. Imaging Research and Medical Application, 9(22), 81–83. (In Chinese.)
[35] Bo, X. W., Guo, L. H., Yu, S. Y., & Wang, Y. (2024). Establishment and verification of an artificial intelligence system for automatic segmentation and classification of thyroid nodules. Chinese Journal of Medical Ultrasound (Electronic Edition), 21(3), 304–309. (In Chinese.)
[36] Yang, J. W., Zhou, M. J., Chen, Y. F., & Liu, Y. (2024). Artificial intelligence ultrasound combined with quality control circle activity comprehensively improves ability of junior sonographers to assess risk of thyroid nodules. Chinese Journal of Medical Ultrasound (Electronic Edition), 21(5), 522–526. (In Chinese.)
[37] Jiang, L., Jiang, M., Jiang, L., & Wang, H. (2024). Diagnostic value of an ultrasound thyroid AI-assisted diagnostic system for medullary thyroid carcinoma. Chinese Journal of Medical Imaging Technology, 40(4), 506–510. (In Chinese.)
[38] Song, H. Q., Tuo, J. M., & Si, X. J. (2023). Application value of ultrasonic AI combined with thyroid stimulating hormone detection in the diagnosis of benign and malignant diagnosis of thyroid nodule. China Medical Devices, 38(11), 92–97. (In Chinese.)
[39] Zou, Y., Liu, J. H., Li, J. Y., & Chen, Y. (2025). Performance of an ultrasound-based transfer learning artificial intelligence model for estimating malignancy probability in mixed cystic-solid thyroid nodules. The Journal of Practical Medicine, 41(6), 889–895. (In Chinese.)
[40] Kundu, S. (2021). AI in medicine must be explainable. Nature Medicine, 27(8), 1328. https://doi.org/10.1038/s41591-021-01461-0. DOI: https://doi.org/10.1038/s41591-021-01461-z
[41] Castelvecchi, D. (2016). Can we open the black box of AI? Nature, 538(7623), 20–23. https://doi.org/10.1038/538020a. DOI: https://doi.org/10.1038/538020a
[42] Hicks, S. A., Strumke, I., Thambawita, V., & Halvorsen, P. (2022). On evaluation metrics for medical applications of artificial intelligence. Scientific Reports, 12(1), 5979. https://doi.org/10.1038/s41598-022-09987-2. DOI: https://doi.org/10.1038/s41598-022-09954-8
Downloads
Published
Issue
Section
License
This work is licensed under a Creative Commons Attribution-NonCommercial 4.0 International License.
