“智”疗甲状腺癌：人工智能在甲状腺癌诊疗中的应用与展望

doi:10.3969/j.issn.1009-976X.2026.02.009

摘要/Abstract

摘要： 甲状腺癌（TC）是内分泌系统最常见的恶性肿瘤,全球范围内发病率持续上升。虽然大多数患者预后状况良好,但仍面临早期诊断准确性不足、淋巴结转移评估不准确、个体化治疗难以有效开展以及随访效率低等问题。近年来,人工智能（AI）技术快速发展,为TC精准诊疗带来了变革。本综述主要聚焦AI在TC诊断中的应用,梳理了AI技术的演进历程,比较了不同方法在良恶性鉴别、淋巴结转移预测及分子分型中的效能。同时,探讨了AI在治疗决策、预后评估及随访管理中的应用潜力,分析了当前面临的挑战,旨在推动AI技术向临床应用转化。

关键词: 甲状腺癌, 人工智能, 深度学习, 外科决策, 精准诊断

Abstract: Thyroid cancer （TC） is the most common malignant tumor of the endocrine system, with its incidence continuously rising worldwide. Although most patients have a favorable prognosis, challenges remain, including insufficient accuracy in early diagnosis, inaccurate assessment of lymph node metastasis, difficulties in effectively implementing individualized treatment, and low follow-up efficiency. In recent years, the rapid development of artificial intelligence （AI） technology has brought transformative changes to the precise diagnosis and treatment of TC. This review primarily focuses on the application of AI in TC diagnosis, outlining the evolution of AI technologies and comparing the efficacy of different methods in distinguishing benign from malignant lesions, predicting lymph node metastasis, and molecular subtyping. Simultaneously, it explores the potential of AI in treatment decision-making, prognosis assessment, and follow-up management, analyzes current challenges, and aims to promote the translation of AI technology into clinical practice.

Key words: thyroid cancer, artificial intelligence, surgical decision, deep learning, precise diagnosis

中图分类号:

R736.1

努尔班努·塔布斯别克, 邵国安. “智”疗甲状腺癌：人工智能在甲状腺癌诊疗中的应用与展望[J]. 岭南现代临床外科, 2026, 26(02): 131-139.

NUERBANNU Tabusibieke, SHAO Guoan. “Intelligent” treatment for thyroid cancer： application and prospect of artificial intelligence in thyroid cancer diagnosis and treatment[J]. Lingnan Modern Clinics In Surgery, 2026, 26(02): 131-139.

参考文献

[1] 刘领云, 谢天皓, 付燕, 等. 人工智能技术在甲状腺癌诊断与治疗中的应用[J]. 中国普通外科杂志, 2025, 34(5): 1018-1026.
[2] Zhu L, Lu C, Zhang J.Letter to editor: Artificial intelligence-based multi-modal multi-tasks analysis reveals tumor molecular heterogeneity, predicts preoperative lymph node metastasis and prognosis in papillary thyroid carcinoma: a retrospective study[J]. Int J Surg, 2026, 112(2): 5337-5338.
[3] 刘才广, 莫屈, 肖羿, 等. 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.
[4] 董竞方. 机器学习在甲状腺恶性结节超声图像识别及中医舌象分类中的应用: 04[D]. 北京中医药大学, 2020.
[5] Srivastava N, Verma S, Singh A, et al. Advances in artificial intelligence-based technologies for increasing the quality of medical products [J]. Daru, 2024, 33(1): 1.?
[6] Deniz MS, Guler BY.Assessment of ChatGPT's adherence to ETA-thyroid nodule management guideline over two different time intervals 14 days apart: in binary and multiple-choice queries[J]. Endocrine, 2024, 85(2): 794-802.
[7] Li Y, Li T, He K, et al.A predictive nomogram of thyroid nodules based on deep learning ultrasound image analysis[J]. Front Endocrinol (Lausanne), 2025, 16: 1504412.
[8] Cao CL, Li QL, Tong J, et al.Artificial intelligence in thyroid ultrasound[J]. Front Oncol, 2023, 13:1060702.
[9] Liu T, Guo Q, Lian C, et al.Automated detection and classification of thyroid nodules in ultrasound images using clinical-knowledge-guided convolutional neural networks[J]. Med Image Anal, 2019, 58: 101555.
[10] Zhang B, Tian J, Pei S, et al.Machine Learning-Assisted System for Thyroid Nodule Diagnosis[J]. Thyroid, 2019, 29(6): 858-867.
[11] Zhao KC,Ren TT,Yin FY, et al.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[J].Thyroid,2021,31(3):470-481.
[12] Ouyang F, Guo B, Ouyang L, et al.Comparison between linear and nonlinear machine-learning algorithms for the classification of thyroid nodules[J]. Eur J Radiol, 2019, 113: 251-257.
[13] Chen C, Jiang Y, Yao J, et al.Deep learning to assist composition classification and thyroid solid nodule diagnosis: a multicenter diagnostic study[J]. Eur Radiol, 2024, 34(4): 2323-2333.
[14] Zhang X, Lee VC, Rong J, et al.Deep convolutional neural networks in thyroid disease detection: A multi-classification comparison by ultrasonography and computed tomography[J]. Comput Methods Programs Biomed, 2022, 220: 106823.
[15] Li X, Zhang S, Zhang Q, et al.Diagnosis of thyroid cancer using deep convolutional neural network models applied to sonographic images: a retrospective, multicohort, diagnostic study[J]. Lancet Oncol, 2019, 20(2): 193-201.
[16] Buda M, Wildman-Tobriner B, Hoang JK, et al.Management of Thyroid Nodules Seen on US Images: Deep Learning May Match Performance of Radiologists[J]. Radiology, 2019, 292(3): 695-701.
[17] Wildman-Tobriner B, Buda M, Hoang JK, et al.Using Artificial Intelligence to Revise ACR TI-RADS Risk Stratification of Thyroid Nodules: Diagnostic Accuracy and Utility[J]. Radiology, 2019, 292(1): 112-119.
[18] Chen YF, Gao ZX, He YN, et al.An Artificial Intelligence Model Based on ACR TI-RADS Characteristics for US Diagnosis of Thyroid Nodules[J]. Radiology, 2022, 303(3):613-619.
[19] Peng S, Liu Y, Lv W, et al.Deep learning-based artificial intelligence model to assist thyroid nodule diagnosis and management: a multicentre diagnostic study[J]. Lancet Digit Health, 2021, 3(4): e250-e259.
[20] Tong W, Wu S, Cheng M, et al.Integration of Artificial Intelligence Decision Aids to Reduce Workload and Enhance Efficiency in Thyroid Nodule Management[J]. JAMA Netw Open, 2023, 6(5): e2313674.
[21] Li Y, Liu Y, Xiao J, et al.Clinical value of artificial intelligence in thyroid ultrasound: a prospective study from the real world[J]. Eur Radiol, 2023, 33(7): 4513-4523.
[22] Wei Q, Zeng S, Wang L, et al.The value of S-Detect in improving the diagnostic performance of radiologists for the differential diagnosis of thyroid nodules[J]. Med Ultrason, 2020, 22(4): 415-423.
[23] Zhao HN, Liu JY, Lin QZ, et al.Partially cystic thyroid cancer on conventional and elastographic ultrasound: a retrospective study and a machine learning-assisted system[J]. Ann Transl Med, 2020, 8(7):495.
[24] Chen C, Zhou Y, Xu B, et al.A multicenter diagnostic study of thyroid nodule with Hashimoto′s thyroiditis enabled by Hashimoto′s thyroiditis nodule-artificial intelligence model[J]. Eur Radiol, 2025, 35(8): 4610-4620.
[25] Alabrak MMA, Megahed M, Alkhouly AA, et al.Artificial Intelligence Role in Subclassifying Cytology of Thyroid Follicular Neoplasm[J]. Asian Pac J Cancer Prev, 2023, 24(4): 1379-1387.
[26] Lee JH, Ha EJ, Kim JH.Application of deep learning to the diagnosis of cervical lymph node metastasis from thyroid cancer with CT[J]. Eur Radiol, 2019, 29(10): 5452-5457.
[27] Li J, Wu X, Mao N, et al.Computed Tomography-Based Radiomics Model to Predict Central Cervical Lymph Node Metastases in Papillary Thyroid Carcinoma: A Multicenter Study[J]. Front Endocrinol (Lausanne), 2021, 12: 741698.
[28] 陆钰,龚涵颖, 韩俊, 等. 基于双期增强CT影像组学模型对甲状腺乳头状癌被膜侵犯的预测价值[J]. 浙江临床医学, 2024, 26(7): 970-973.
[29] Wang H, Song B, Ye N, et al.Machine learning-based multiparametric MRI radiomics for predicting the aggressiveness of papillary thyroid carcinoma[J]. Eur J Radiol, 2020, 122: 108755.
[30] Halicek M, Lu G, Little JV, et al.Deep convolutional neural networks for classifying head and neck cancer using hyperspectral imaging[J]. J Biomed Opt, 2017, 22(6): 60503.
[31] Qian T, Feng X, Zhou Y, et al.Diagnostic value of deep learning of multimodal imaging of thyroid for TI-RADS category 3-5 classification[J]. Endocrine, 2025, 88(3): 776-785.
[32] Qin P, Wu K, Hu Y, et al.Diagnosis of benign and malignant thyroid nodules using combined conventional ultrasound and ultrasound elasticity imaging[J].IEEE J Biomed Health Inform,2020, 24(4):1028-1036.
[33] Xiang Z, Zhuo Q, Zhao C, et al.Self-supervised multi-modal fusion network for multi-modal thyroid ultrasound image diagnosis[J]. Comput Biol Med, 2022, 150: 106164.
[34] Zhang N, Liu J, Jin Y, et al.An adaptive multi-modal hybrid model for classifying thyroid nodules by combining ultrasound and infrared thermal images[J]. BMC Bioinformatics, 2023, 24(1): 315.
[35] Dai Q, Tao Y, Liu D, et al.Ultrasound radiomics models based on multimodal imaging feature fusion of papillary thyroid carcinoma for predicting central lymph node metastasis[J]. Front Oncol, 2023, 13: 1261080.
[36] Patel KN, Angell TE, Babiarz J, et al.Performance of a Genomic Sequencing Classifier for the Preoperative Diagnosis of Cytologically Indeterminate Thyroid Nodules[J]. JAMA Surg, 2018, 153(9): 817-824.
[37] Abdolali F, Kapur J, Jaremko JL, et al.Automated thyroid nodule detection from ultrasound imaging using deep convolutional neural networks[J]. Comput Biol Med, 2020, 122: 103871.
[38] Dov D, Range DE, Cohen J, et al.Deep-Learning-Based Screening and Ancillary Testing for Thyroid Cytopathology[J]. Am J Pathol, 2023, 193(9): 1185-1194.
[39] Wang J, Zheng N, Wan H, et al.Deep learning models for thyroid nodules diagnosis of fine-needle aspiration biopsy: a retrospective, prospective, multicentre study in China[J]. Lancet Digit Health, 2024, 6(7): e458-e469.
[40] Li Y, Chen P, Li Z, et al.Rule-based automatic diagnosis of thyroid nodules from intraoperative frozen sections using deep learning[J]. ArtifIntell Med, 2020, 108: 101918.
[41] Liu Y, Lai F, Lin B, et al.Deep learning to predict cervical lymph node metastasis from intraoperative frozen section of tumour in papillary thyroid carcinoma: a multicentre diagnostic study[J]. EClinicalMedicine, 2023, 60:102007.
[42] Hao Y, Duh Q, Kloos RT, et al.Identification of Hürthle cell cancers: solving a clinical challenge with genomic sequencing and a trio of machine learning algorithms[J]. BMC Syst Biol, 2019, 13(Suppl 2): 27.
[43] Craig S, Stretch C, Farshidfar F, et al.A clinically useful and biologically informative genomic classifier for papillary thyroid cancer[J]. Front Endocrinol (Lausanne), 2023, 14: 1220617.
[44] Liu Y, Zhang J, Li S, et al.Prediction of TNFRSF9 expression and molecular pathological features in thyroid cancer using machine learning to construct Pathomics models[J]. Endocrine, 2024, 86(1): 324-332.
[45] Tsou P, Wu C.Mapping Driver Mutations to Histopathological Subtypes in Papillary Thyroid Carcinoma: Applying a Deep Convolutional Neural Network[J]. J Clin Med, 2019, 8(10): 1675.
[46] Anand D, Yashashwi K, Kumar N, et al.Weakly supervised learning on unannotated H&E-stained slides predicts BRAF mutation in thyroid cancer with high accuracy[J]. J Pathol, 2021, 255(3): 232-242.
[47] Agyekum EA, Yuzhi Z, Fang Y, et al.Ultrasound-based classification of follicular thyroid Cancer using deep convolutional neural networks with transfer learning[J]. Sci Rep, 2025, 15(1): 21708.
[48] Hou F, Zhu Y, Zhao H, et al.Development and validation of an interpretable machine learning model for predicting the risk of distant metastasis in papillary thyroid cancer: a multicenter study[J]. EClinicalMedicine, 2024, 77: 102913.
[49] Wang H, Zhang C, Li Q, et al.Development and validation of prediction models for papillary thyroid cancer structural recurrence using machine learning approaches[J]. BMC Cancer, 2024, 24(1): 427.
[50] Bellantuono L, Tommasi R, Pantaleo E, et al.An eXplainable Artificial Intelligence analysis of Raman spectra for thyroid cancer diagnosis[J]. Sci Rep, 2023, 13(1): 16590.
[51] Wu Y, Rao K, Liu J, et al.Machine Learning Algorithms for the Prediction of Central Lymph Node Metastasis in Patients With Papillary Thyroid Cancer[J]. Front Endocrinol (Lausanne), 2020, 11: 577537.
[52] Yu J, Deng Y, Liu T, et al.Lymph node metastasis prediction of papillary thyroid carcinoma based on transfer learning radiomics[J]. Nat Commun, 2020, 11(1): 4807.
[53] Wu X, Li M, Cui X, et al.Deep multimodal learning for lymph node metastasis prediction of primary thyroid cancer[J]. Phys Med Biol, 2022, 67(3).
[54] Wang Z, Qu L, Chen Q, et al.Deep learning-based multifeature integration robustly predicts central lymph node metastasis in papillary thyroid cancer[J]. BMC Cancer, 2023, 23(1): 128.
[55] Feng J, Ye J, Qi G, et al.LASSO-based machine learning models for the prediction of central lymph node metastasis in clinically negative patients with papillary thyroid carcinoma[J]. Front Endocrinol (Lausanne), 2022, 13: 1030045.
[56] Zhou L, Zeng S, Xu J, et al.Deep learning predicts cervical lymph node metastasis in clinically node-negative papillary thyroid carcinoma[J]. Insights Imaging, 2023, 14(1): 222.
[57] Yao S, Shen P, Dai F, et al.Thyroid Cancer Central Lymph Node Metastasis Risk Stratification Based on Homogeneous Positioning Deep Learning[J]. Research (Wash D C), 2024, 7: 0432.
[58] Feng J, Ye J, Qi G, et al.A comparative analysis of eight machine learning models for the prediction of lateral lymph node metastasis in patients with papillary thyroid carcinoma[J]. Front Endocrinol (Lausanne), 2022, 13: 1004913.
[59] Qi Q, Huang X, Zhang Y, et al.Ultrasound image-based deep learning to assist in diagnosing gross extrathyroidal extension thyroid cancer: a retrospective multicenter study[J]. EClinicalMedicine, 2023, 58: 101905.
[60] Sa R, Yang T, Zhang Z, et al.Random Forest for Predicting Treatment Response to Radioiodine and Thyrotropin Suppression Therapy in Patients With Differentiated Thyroid Cancer But Without Structural Disease[J]. Oncologist, 2024, 29(1): e68-e80.
[61] Georgiou MF, Nielsen JA, Chiriboga R, et al.An Artificial Intelligence System for Optimizing Radioactive Iodine Therapy Dosimetry[J]. J Clin Med, 2023, 13(1): 117.
[62] Chantadisai M, Wongwijitsook J, Ritlumlert N, et al.Combined clinical variable and radiomics of post-treatment total body scan for prediction of successful I-131 ablation in low-risk papillary thyroid carcinoma patients[J]. Sci Rep, 2024, 14(1): 5001.
[63] Gao X, Chen H, Wang Y, et al.Automatic prediction of non-iodine-avid status in lung metastases for radioactive I131 treatment in differentiated thyroid cancer patients[J]. Front Endocrinol (Lausanne), 2024, 15: 1429115.
[64] Bülbül O, Nak D.Predicting excellent response to radioiodine in differentiated thyroid cancer using machine learning[J]. Acta Otorhinolaryngol Ital, 2024, 44(4): 261-268.
[65] Kim J, Ko S, Kim M, et al.Deep Learning Prediction of TERT Promoter Mutation Status in Thyroid Cancer Using Histologic Images[J]. Medicina (Kaunas), 2023, 59(3): 536.
[66] Wu, Fan, Lin, Xiangfeng, Chen, Yuying, et al.Breaking barriers: noninvasive AI model for BRAFV600E mutation identification[J]. Int J Comput Assist Radiol Surg, 2025, 20(5): 935-947.
[67] Sigawi T, Gelman R, Maimon O, et al.Improving the response to lenvatinib in partial responders using a Constrained-Disorder-Principle-based second-generation artificial intelligence-therapeutic regimen: a proof-of-concept open-labeled clinical trial[J]. Front Oncol, 2024, 14: 1426426.
[68] Yu Y, Ouyang W, Huang Y, et al.Artificial intelligence-based multi-modal multi-tasks analysis reveals tumor molecular heterogeneity, predicts preoperative lymph node metastasis and prognosis in papillary thyroid carcinoma: a retrospective study[J]. Int J Surg, 2025, 111(1): 839-856.
[69] Borzooei S, Briganti G, Golparian M, et al.Machine learning for risk stratification of thyroid cancer patients: a 15-year cohort study[J]. Eur Arch Otorhinolaryngol, 2024, 281(4): 2095-2104.
[70] Liu W, Li Z, Luo Z, et al.Machine learning for the prediction of bone metastasis in patients with newly diagnosed thyroid cancer[J]. Cancer Med, 2021, 10(8): 2802-2811.
[71] Jin S, Yang X, Zhong Q, et al.A Predictive Model for the 10-year Overall Survival Status of Patients With Distant Metastases From Differentiated Thyroid Cancer Using XGBoost Algorithm-A Population-Based Analysis[J]. Front Genet, 2022, 13: 896805.
[72] Xu L, Cai L, Zhu Z, et al.Comparison of the cox regression to machine learning in predicting the survival of anaplastic thyroid carcinoma[J]. BMC EndocrDisord, 2023, 23(1): 129.
[73] Barfejani AH, Rostami M, Rahimi M, et al.Predicting overall survival in anaplastic thyroid cancer using machine learning approaches[J]. Eur Arch Otorhinolaryngol, 2024, 282(3): 1653-1657.
[74] Wen H, Li X, Zhao X.TC check: a web app for thyroid cancer recurrence prediction using explainable machine learning[J]. J Cancer Res Clin Oncol, 2025, 152(1): 14.
[75] Li Y, Tang Z, Ren A, et al.A machine learning-based model for predicting recurrence in intermediate- and high-risk differentiated thyroid cancer: insights from a retrospective single-center study of 2388 patients[J]. Front Endocrinol (Lausanne), 2025, 16: 1552479.
[76] Xu Q, Wang J, Chen X, et al.Assessing the Efficacy of ChatGPT Prompting Strategies in Enhancing Thyroid Cancer Patient Education: A Prospective Study[J]. J Med Syst, 2025, 49(1): 11.
[77] AdhikaryPK, Srivastava A, Kumar S, et al. Exploring the Efficacy of Large Language Models in Summarizing Mental Health Counseling Sessions: Benchmark Study[J]. JMIR Ment Health, 2024, 11: e57306.
[78] HelvaciBC, Hepsen S, Candemir B, et al. Assessing the accuracy and reliability of ChatGPT's medical responses about thyroid cancer[J]. Int J Med Inform, 2024, 191: 105593.
[79] GorrisMA, Randle RW, Obermiller CS, et al. Assessing ChatGPT's Capability in Addressing Thyroid Cancer Patient Queries: A Comprehensive Mixed-Methods Evaluation [J]. J Endocr Soc, 2025, 9(2): bvaf003.
[80] Wang Z, Zhang Z, Traverso A, et al.Assessing the role of GPT-4 in thyroid ultrasound diagnosis and treatment recommendations: enhancing interpretability with a chain of thought approach[J]. Quant Imaging Med Surg, 2024, 14(2): 1602-1615.
[81] Jiang H, Xia S, Yang Y, et al.Transforming free-text radiology reports into structured reports using ChatGPT: A study on thyroid ultrasonography[J]. Eur J Radiol, 2024, 175: 111458.
[82] Habeeb A, Lim KH, Kochilas X, et al.Can Artificial Intelligence Software be Utilised for Thyroid Multi-Disciplinary Team Outcomes[J]. Clin Otolaryngol, 2025, 50(4): 769-774.
[83] Pandya, Shivam, Bresler, E. T, Wilson, Tyler, et al.Decoding the NCCN Guidelines With AI: A Comparative Evaluation of ChatGPT-4.0 and Llama 2 in the Management of Thyroid Carcinoma[J]. Am Surg, 2024, 91(1): 94-98.
[84] Köroğlu EY, Fakı S, Beştepe N, et al.A Novel Approach: Evaluating ChatGPT's Utility for the Management of Thyroid Nodules[J]. Cureus, 2023, 15(10): e47576.
[85] Song D, Yao J, Jiang Y, et al.A new xAI framework with feature explainability for tumors decision-making in Ultrasound data: comparing with Grad-CAM[J]. Comput Methods Programs Biomed, 2023, 235: 107527.
[86] Manh VT, Zhou J, Jia X, et al.Multi-Attribute Attention Network for Interpretable Diagnosis of Thyroid Nodules in Ultrasound Images[J]. IEEE Trans UltrasonFerroelectr Freq Control, 2022, 69(9): 2611-2620.
[87] Xu W, Jia X, Mei Z, et al.Generalizability and Diagnostic Performance of AI Models for Thyroid US[J]. Radiology, 2023, 307(5): e221157.
[88] Xiang Z, Tian X, Liu Y, et al.Federated learning via multi-attention guided UNet for thyroid nodule segmentation of ultrasound images[J]. Neural Netw, 2025, 181: 106754.
[89] Yao S, Dai F, Sun P, et al.Enhancing the fairness of AI prediction models by Quasi-Pareto improvement among heterogeneous thyroid nodule population[J]. Nat Commun, 2024, 15(1): 1958.
[90] Athreya S, Melehy A, Suthahar SSA, et al.Combining Ultrasound Imaging and Molecular Testing in a Multimodal Deep Learning Model for Risk Stratification of Indeterminate Thyroid Nodules[J]. Thyroid, 2025, 35(5): 590-594.