基于超声的人工智能在甲状腺癌诊疗中的应用现状与未来展望
Application Status and Future Prospects of Ultrasound-Based Artificial Intelligence in the Diagnosis and Treatment of Thyroid Cancer
DOI: 10.12677/jcpm.2026.54270, PDF,   
作者: 李芳轩：山东大学校医院影像科，山东 济南；王 数*：大连大学附属中山医院急诊医学科，辽宁 大连；易天翔*：娄底市中心医院血液内科，湖南 娄底
关键词: 甲状腺癌；超声诊断；人工智能；综述；Thyroid Cancer； Ultrasound Diagnosis； Artificial Intelligence； Review
摘要: 甲状腺癌是内分泌系统最常见的恶性肿瘤，近年来发病率呈逐年上升趋势，早期诊断和治疗对改善患者预后至关重要。超声检查在甲状腺癌的诊断、分期、危险分层及治疗中发挥着重要作用。然而，超声图像的分析高度依赖于医生的能力和经验，医生对图像的解读容易受到自身主观性和工作量大小的影响。人工智能是一门模拟和扩展人类智能的技术科学，越来越多的AI产品被应用于甲状腺癌超声诊断领域。本文综述了基于超声的AI技术在甲状腺癌诊疗全过程中的研究进展，探讨了目前AI技术的优势与不足，并展望了其未来的发展方向。
Abstract: Thyroid cancer is the most common malignant tumor of the endocrine system, and its incidence has been increasing year by year in recent years. Early diagnosis and treatment are essential to improve the prognosis of patients. Ultrasonography plays an important role in the diagnosis, staging, risk stratification and treatment of thyroid cancer. However, the analysis of ultrasound images is highly dependent on the ability and experience of doctors, whose interpretation of images is easily affected by their own subjectivity and workload. Artificial intelligence is a technical science that simulates and extends human intelligence. More and more AI products have been applied in the field of thyroid nodule ultrasound diagnosis. This article reviews the research progress of ultrasound-based AI technology in the diagnosis and treatment of thyroid cancer, discusses the advantages and disadvantages of current AI technology, and looks forward to its future development direction.
文章引用：李芳轩, 王数, 易天翔. 基于超声的人工智能在甲状腺癌诊疗中的应用现状与未来展望[J]. 临床个性化医学, 2026, 5(4): 450-458. https://doi.org/10.12677/jcpm.2026.54270

参考文献

[1] Wang, L., Li, R., Zeng, X. and Zhang, H. (2026) Evaluation and Projection of the Global Burden of Thyroid Cancer from 1990 to 2035: An Analysis Based on the Global Burden of Disease Study. Thyroid Research, 19, 10-25.
https://doi.org/10.1186/s13044-026-00288-5
[2] Fu, M., Peng, Z. and Wu, M. (2026) Thyroid Cancer in Asia: Incidence, Mortality in 2022, and Future Projections to 2050. European Journal of Cancer Prevention, 35, 126-140.
https://doi.org/10.1097/cej.0000000000000983
[3] 苏艳军. 2025版《中国肿瘤整合诊治指南(CACA)-甲状腺癌》系统解读[J]. 中国普通外科杂志, 2025, 34(5): 867-878.
[4] Kim, S.H., Park, C.S., Jung, S.L., Kang, B.J., Kim, J.Y., Choi, J.J., et al. (2010) Observer Variability and the Performance between Faculties and Residents: US Criteria for Benign and Malignant Thyroid Nodules. Korean Journal of Radiology, 11, 149-155.
https://doi.org/10.3348/kjr.2010.11.2.149
[5] Idrees, T., Rashied, A.A. and Kim, B. (2025) Nondiagnostic Fine Needle Aspiration of Thyroid Nodules: Review of Predisposing Factors. Endocrine Practice, 31, 85-91.
https://doi.org/10.1016/j.eprac.2024.09.015
[6] Vaghaiwalla, T.M., Henriksen, E.M., Chang, J., Saghira, C. and Lew, J.I. (2025) Reassessing False-Negative Rate and Size Cutoff for Papillary Thyroid Cancer with Fine-Needle Aspiration in Thyroid Nodules. Surgery, 186, Article 109577.
https://doi.org/10.1016/j.surg.2025.109577
[7] He, L., Chen, F., Zhou, D., Zhang, Y., Li, Y., et al. (2022) A Comparison of the Performances of Artificial Intelligence System and Radiologists in the Ultrasound Diagnosis of Thyroid Nodules. Current Medical Imaging Formerly Current Medical Imaging Reviews, 18, 1369-1377.
https://doi.org/10.2174/1573405618666220422132251
[8] Tang, X., Zhou, H., Liu, Y., Gao, S. and Zhou, Y. (2025) Diagnostic Performance of the Ultrasound-Based Artificial Intelligence Diagnostic System in Predicting Cervical Lymph Node Metastasis in Patients with Thyroid Cancer: A Systematic Review and Meta-Analysis. Science Progress, 108, 00368504251346906.
https://doi.org/10.1177/00368504251346906
[9] Bini, F., Pica, A., Azzimonti, L., Giusti, A., Ruinelli, L., Marinozzi, F., et al. (2021) Artificial Intelligence in Thyroid Field—A Comprehensive Review. Cancers, 13, Article 4740.
https://doi.org/10.3390/cancers13194740
[10] 刘才广. 医学影像人工智能在甲状腺癌诊疗中的应用: 现状与展望[J]. 中国普通外科杂志, 2024, 33(11): 1874-1882.
[11] Atri, H., Shadi, M. and Sargolzaei, M. (2023) Generating Synthetic Medical Images with Limited Data Using Auxiliary Classifier Generative Adversarial Network: A Study on Thyroid Ultrasound Images. Journal of Ultrasound, 27, 105-121.
https://doi.org/10.1007/s40477-023-00837-w
[12] Prochazka, A. and Zeman, J. (2026) Domain Adaptation of Stable Diffusion for Ultrasound Inpainting: A Synthetic Data Approach for Enhanced Thyroid Nodule Segmentation. Journal of Biomedical Informatics, 173, Article 104963.
https://doi.org/10.1016/j.jbi.2025.104963
[13] Sujini, G.N. and Balakrishna, S. (2025) Automated Thyroid Nodule Classification in Ultrasound Imaging Using a Hybrid Vision Transformer and Wasserstein GAN with Gradient Penalty. Scientific Reports, 15, Article No. 40786.
https://doi.org/10.1038/s41598-025-24651-y
[14] Ni, C., Feng, B., Yao, J., Zhou, X., Shen, J., Ou, D., et al. (2023) Value of Deep Learning Models Based on Ultrasonic Dynamic Videos for Distinguishing Thyroid Nodules. Frontiers in Oncology, 12, Article ID: 1066508.
https://doi.org/10.3389/fonc.2022.1066508
[15] Kang, S., Lee, E., Chung, C.W., Jang, H.N., Moon, J.H., Shin, Y., et al. (2021) A Beneficial Role of Computer-Aided Diagnosis System for Less Experienced Physicians in the Diagnosis of Thyroid Nodule on Ultrasound. Scientific Reports, 11, Article No. 20448.
https://doi.org/10.1038/s41598-021-99983-6
[16] 杨明, 许彩娜, 张宁, 等. 2023-2024年度河北省甲状腺癌超声诊断符合率现状分析[J]. 中华医学超声杂志(电子版), 2025, 22(9): 846-849.
[17] Gao, L., Li, J., Niu, Z., Cai, S., Lu, S., Xu, W., et al. (2024) How to Improve Diagnostic Accuracy of Thyroid Ultrasounds: A Multicenter Quality Study in China. NEJM Catalyst, vol. 5.
https://doi.org/10.1056/cat.24.0362
[18] Liu, S., Yang, Y., Cai, M., Xu, Z., He, S., Su, Q., et al. (2025) Human-Machine Collaborative Risk Assessment Model for Thyroid Nodules Based on Local Attention and Multi-Scale Feature Extraction: A Multi-Center Clinical Study. Endocrine, 89, 772-780.
https://doi.org/10.1007/s12020-025-04278-9
[19] Kim, J., Lee, J., Ha, J., Kwon, O., Baek, K., Song, C.M., et al. (2026) Artificial Intelligence-Assisted Risk Stratification of Thyroid Nodules with Atypia of Undetermined Significance. European Thyroid Journal, 15, ETJ250268.
https://doi.org/10.1530/etj-25-0268
[20] Guo, F., Chang, W., Zhao, J., Xu, L., Zheng, X. and Guo, J. (2023) Assessment of the Statistical Optimization Strategies and Clinical Evaluation of an Artificial Intelligence-Based Automated Diagnostic System for Thyroid Nodule Screening. Quantitative Imaging in Medicine and Surgery, 13, 695-706.
https://doi.org/10.21037/qims-22-85
[21] 中华医学会超声医学分会浅表器官和血管学组, 中国甲状腺与乳腺超声人工智能联盟. 2020甲状腺结节超声恶性危险分层中国指南: C-TIRADS [J]. 中华超声影像学杂志, 2021, 30(3): 185-200.
[22] Potipimpanon, P., Charakorn, N. and Hirunwiwatkul, P. (2022) A Comparison of Artificial Intelligence versus Radiologists in the Diagnosis of Thyroid Nodules Using Ultrasonography: A Systematic Review and Meta-Analysis. European Archives of Oto-Rhino-Laryngology, 279, 5363-5373.
https://doi.org/10.1007/s00405-022-07436-1
[23] Wu, G.G., Lv, W.Z., Yin, R., Xu, J., Yan, Y., Chen, R., et al. (2021) Deep Learning Based on ACR TI-RADS Can Improve the Differential Diagnosis of Thyroid Nodules. Frontiers in Oncology, 11, Article ID: 575166.
https://doi.org/10.3389/fonc.2021.575166
[24] 张鑫茹, 李扬, 孙萌, 等. Vision-LSTM模型在甲状腺影像报告与数据系统4b类甲状腺结节超声影像诊断中的应用与评估[J]. 山东大学学报(医学版), 2025, 63(11): 68-74.
[25] Zhao, C.K., Ren, T.T., Yin, Y.F., Shi, H., Wang, H., Zhou, B., et al. (2021) A Comparative Analysis of Two Machine Learning-Based Diagnostic Patterns with Thyroid Imaging Reporting and Data System for Thyroid Nodules: Diagnostic Performance and Unnecessary Biopsy Rate. Thyroid®, 31, 470-481.
https://doi.org/10.1089/thy.2020.0305
[26] 邹颖. 基于超声的迁移学习人工智能模型对甲状腺囊实性结节恶性概率的评估效能[J]. 实用医学杂志, 2025, 41(6): 889-895.
[27] Gatta, E., Gatta, R., Morandi, R., Isoli, S., Corvaglia, S., Vetrugno, S., et al. (2026) Machine Learning for Diagnosis of Malignant Thyroid Nodules Based on Thyroid Ultrasound: Systematic Review and Meta-Analysis of Studies with External Datasets. European Journal of Radiology Open, 16, Article 100716.
https://doi.org/10.1016/j.ejro.2025.100716
[28] Jin, Z., Zhu, Y., Zhang, S., Xie, F., Zhang, M., Zhang, Y., et al. (2020) Ultrasound Computer-Aided Diagnosis (CAD) Based on the Thyroid Imaging Reporting and Data System (TI-RADS) to Distinguish Benign from Malignant Thyroid Nodules and the Diagnostic Performance of Radiologists with Different Diagnostic Experience. Medical Science Monitor, 26, e918452.
https://doi.org/10.12659/msm.918452
[29] Zhu, J., Zhang, S., Yu, R., Liu, Z., Gao, H., Yue, B., et al. (2021) An Efficient Deep Convolutional Neural Network Model for Visual Localization and Automatic Diagnosis of Thyroid Nodules on Ultrasound Images. Quantitative Imaging in Medicine and Surgery, 11, 1368-1380.
https://doi.org/10.21037/qims-20-538
[30] Shen, H., Pei, S., Huang, Y., Wu, S., Zhang, C., Liang, T., et al. (2025) Artificial Intelligence-Augmented Ultrasound Diagnosis of Follicular-Patterned Thyroid Neoplasms: A Multicenter Retrospective Study. eClinicalMedicine, 86, Article 103351.
https://doi.org/10.1016/j.eclinm.2025.103351
[31] Yang, Z., Yao, S., Heng, Y., Shen, P., Lv, T., Feng, S., et al. (2023) Automated Diagnosis and Management of Follicular Thyroid Nodules Based on the Devised Small-Dataset Interpretable Foreground Optimization Network Deep Learning: A Multicenter Diagnostic Study. International Journal of Surgery, 109, 2732-2741.
https://doi.org/10.1097/js9.0000000000000506
[32] Wu, F., Pan, T., Huang, X., Huang, K., Shi, J., Mao, L., et al. (2025) Revolutionizing Thyroid Nodule Diagnosis in Hashimoto’s Thyroiditis: AI-Driven Radiomics and Deep Learning Model. International Journal of Surgery, 112, 10157-10171.
https://doi.org/10.1097/js9.0000000000004546
[33] Song, R., Kim, H.S. and Kang, K.H. (2022) Minimal Extrathyroidal Extension Is Associated with Lymph Node Metastasis in Single Papillary Thyroid Microcarcinoma: A Retrospective Analysis of 814 Patients. World Journal of Surgical Oncology, 20, 170-175.
https://doi.org/10.1186/s12957-022-02629-8
[34] Lu, W.J., Qiu, Y.R., Wu, Y.W., et al. (2022) Radiomics Based on Two-Dimensional and Three-Dimensional Ultrasound for Extrathyroidal Extension Feature Prediction in Papillary Thyroid Carcinoma. Acta Endocrinologica (Bucharest), 18, 407-416.
https://doi.org/10.4183/aeb.2022.407
[35] Chen, L., Chen, L., Liang, Z., Shao, Y., Sun, X. and Liu, J. (2022) Value of Contrast-Enhanced Ultrasound in the Preoperative Evaluation of Papillary Thyroid Carcinoma Invasiveness. Frontiers in Oncology, 11, Article ID: 795302.
https://doi.org/10.3389/fonc.2021.795302
[36] Wang, X., Agyekum, E.A., Ren, Y., Zhang, J., Zhang, Q., Sun, H., et al. (2021) A Radiomic Nomogram for the Ultrasound-Based Evaluation of Extrathyroidal Extension in Papillary Thyroid Carcinoma. Frontiers in Oncology, 11, Article ID: 625646.
https://doi.org/10.3389/fonc.2021.625646
[37] Carnazza, M., Quaranto, D., DeSouza, N., Moscatello, A.L., Garber, D., Hemmerdinger, S., et al. (2025) The Current Understanding of the Molecular Pathogenesis of Papillary Thyroid Cancer. International Journal of Molecular Sciences, 26, Article 4646.
https://doi.org/10.3390/ijms26104646
[38] Yang, Q., Cheng, W., Liang, Q. and Yan, L. (2025) Case Report: A Case of Micropapillary Thyroid Carcinoma with Level I Cervical Lymph Node Metastasis. Frontiers in Oncology, 15, Article ID: 1650616.
https://doi.org/10.3389/fonc.2025.1650616
[39] Yu, K., Wu, X., Dai, L., Le, Q., Xie, Y., Wang, Y., et al. (2024) Risk Factors Associated with Lymph Node Metastasis in Papillary Thyroid Cancer: A Retrospective Analysis Based on 2,428 Cases. Frontiers in Oncology, 14, Article ID: 1473858.
https://doi.org/10.3389/fonc.2024.1473858
[40] 甲状腺癌诊疗指南(2022年版) [J]. 中国实用外科杂志, 2022, 42(12): 1343-1357+1363.
[41] Zhang, M.B., Meng, Z.L., Mao, Y., Jiang, X., Xu, N., Xu, Q., et al. (2024) Cervical Lymph Node Metastasis Prediction from Papillary Thyroid Carcinoma US Videos: A Prospective Multicenter Study. BMC Medicine, 22, 153-165.
https://doi.org/10.1186/s12916-024-03367-2
[42] Peng, X., Wu, P., Li, W., Ou-Yang, T., Tang, S.C., Zhou, S., et al. (2025) AI-Based Multimodal Prediction of Lymph Node Metastasis and Capsular Invasion in Ct1n0m0 Papillary Thyroid Carcinoma. Frontiers in Endocrinology, 16, Article ID: 1580885.
https://doi.org/10.3389/fendo.2025.1580885
[43] Yao, S., Shen, P., Dai, F., Deng, L., Qiu, X., Zhao, Y., et al. (2024) Thyroid Cancer Central Lymph Node Metastasis Risk Stratification Based on Homogeneous Positioning Deep Learning. Research, 7, Article ID: 0432.
https://doi.org/10.34133/research.0432
[44] 狄子臣, 武新宇, 汤敏敏, 等. 首次131I治疗后生化持续异常甲状腺乳头状癌患者结构性复发的影响因素[J]. 中华实用诊断与治疗杂志, 2026, 40(5): 448-453.
[45] Otsuki, N., Shimoda, H., Morita, N., Furukawa, T., Teshima, M., Shinomiya, H., et al. (2020) Salvage Surgery for Structural Local Recurrence of Papillary Thyroid Cancer: Recurrence Patterns and Surgical Outcome. Endocrine Journal, 67, 949-956.
https://doi.org/10.1507/endocrj.ej20-0152
[46] 刘志艳, 赵一蔚. 远处转移性甲状腺乳头状癌分子病理特征[J]. 中国实用外科杂志, 2024, 44(6): 640-644.
[47] Agyekum, E.A., Wang, Y., Xu, F., Akortia, D., Ren, Y., Chambers, K.H., et al. (2023) Predicting BRAFV600E Mutations in Papillary Thyroid Carcinoma Using Six Machine Learning Algorithms Based on Ultrasound Elastography. Scientific Reports, 13, Article No. 12604.
https://doi.org/10.1038/s41598-023-39747-6
[48] Yu, Y., Zhao, C., Guo, R., Zhang, Y., Li, X., Liu, N., et al. (2025) Deep Learning Model Based on Ultrasound Images Predicts BRAF V600E Mutation in Papillary Thyroid Carcinoma. iScience, 28, Article 112482.
https://doi.org/10.1016/j.isci.2025.112482
[49] Li, Q., Zhang, W., Liao, T., Gao, Y., Zhang, Y., Jin, A., et al. (2025) An Artificial Intelligence-Driven Preoperative Radiomic Subtype for Predicting the Prognosis and Treatment Response of Patients with Papillary Thyroid Carcinoma. Clinical Cancer Research, 31, 139-150.
https://doi.org/10.1158/1078-0432.ccr-24-2356
[50] Wang, X., Qi, Y., Zhang, X., Liu, F. and Li, J. (2025) Ultrasound-Based Artificial Intelligence for Predicting Cervical Lymph Node Metastasis in Papillary Thyroid Cancer: A Systematic Review and Meta-Analysis. Frontiers in Endocrinology, 16, Article ID: 1570811.
https://doi.org/10.3389/fendo.2025.1570811