甲状腺癌已经成为目前发病率增长最快的恶性肿瘤，跻身十大恶性肿瘤之一。早期识别甲状腺恶性结节，提高诊断准确率并确定其病理分型，有助于甲状腺癌诊治的规范化。近年来，医学影像数据与基于深度学习的人工智能(AI)算法联合诊断逐渐成为研究热点，大量研究数据已经证实基于静态超声图像的AI对甲状腺结节良恶性判断有较高的诊断价值，在此基础上实时动态AI实现了在超声诊断过程中对目标结节的动态识别、准确勾勒及结节良恶性的实时动态分析，提高了医疗决策的精准化。本文对AI在甲状腺癌超声诊断中的应用进行了综述，重点回顾近年来实时动态AI应用于超声图像、超声造影、超声弹性成像及病理分型方面诊断甲状腺癌的研究进展，并对其面临的挑战和机遇进行了展望。

[1] HAUGEN B R,ALEXANDER E K,BIBLE K C,et al.2015 American thyroid association management guidelines for adult patients with thyroid nodules and differentiated thyroid cancer: the American thyroid association guidelines task force on thyroid nodules and differentiated thyroid cancer[J].Thyroid,2016,26(1):1-133.
[2] SUNG H,FERLAY J,SIEGEL R L,et al.Global cancer statistics 2020: GLOBOCAN estimates of incidence and mortality worldwide for 36 cancers in 185 countries[J].CA Cancer J Clin,2021,71(3):209-249.
[3] SHIN J H,BAEK J H,CHUNG J,et al.Ultrasonography diagnosis and imaging-based management of thyroid nodules: revised korean society of thyroid radiology consensus statement and recommendations[J].Korean J Radiol,2016,17(3):370-395.
[4] MENTO F,DEMI L.Dependence of lung ultrasound vertical artifacts on frequency,bandwidth,focus and angle of incidence: An in vitro study[J].J Acoust Soc Am,2021,150(6):4075.
[5] GRANT E G,TESSLER F N,HOANG J K,et al.Thyroid ultrasound reporting lexicon: white paper of the ACR thyroid imaging,reporting and data system (TIRADS) committee[J].J Am Coll Radiol,2015,12(12 Pt A):1272-1279.
[6] REN D,ZUO W,ZHANG D,et al.Simultaneous fidelity and regularization learning for image restoration[J].IEEE Trans Pattern Anal Mach Intell,2021,43(1):284-299.
[7] ZHANG K,ZUO W,ZHANG L.FFDNet: Toward a fast and flexible solution for CNN based image denoising[J].IEEE Trans Image Process,2018,27(9),4608-4622.
[8] ZHAO C K,REN T T,YIN Y F,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.
[9] GILLIES R J,SCHABATH M B.Radiomics improves cancer screening and early detection[J].Cancer Epidemiol Biomarkers Prev,2020,29(12):2556-2567.
[10] OUYANG F S,GUO B L,OUYANG L Z,et al.Comparison between linear and nonlinear machine-learning algorithms for the classification of thyroid nodules[J].Eur J Radiol,2019(4),113:251-257.
[11] 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.
[12] KWON S W,CHOI I J,KANG J Y,et al.Ultrasonographic thyroid nodule classification using a deep convolutional neural network with surgical pathology[J].J Digit Imaging,2020,33(5):1202-1208.
[13] SONG J,CHAI Y J,MASUOKA H,et al.Ultrasound image analysis using deep learning algorithm for the diagnosis of thyroid nodules[J].Medicine(Baltimore),2019,98(15):15133.
[14] NGUYEN D T,PHAM T D,BATCHULUUN G,et al.Artificial intelligence-based thyroid nodule classification using information from spatial and frequency domains[J].J Clin Med,2019,8(11):1976.
[15] HAN M,HA E J,PARK J H.Computer-aided diagnostic system for thyroid nodules on ultrasonography: diagnostic performance based on the thyroid imaging reporting and data system classification and dichotomous outcomes[J].AJNR Am J Neuroradiol,2021,42(3):559-565.
[16] THOMAS J,HAERTLING T.AIBx,artificial intelligence model to risk stratify thyroid nodules[J].Thyroid,2020,30(6):878-884.
[17] SORRENTI S,DOLCETTI V,RADZINA M,et al.Artificial intelligence for thyroid nodule characterization: where are we standing?[J].Cancers (Basel),2022,14(14):3357.
[18] YOO Y J,HA E J,CHO Y J,et al.Computer-aided diagnosis of thyroid nodules via ultrasonography: initial clinical experience[J].Korean J Radiol,2018,19(4):665-672.
[19] MA J,WU F,JIANG T,et al.Cascade convolutional neural networks for automatic detection of thyroid nodules in ultrasound images[J].Med Phys,2017,44(5): 1678-1691.
[20] MA J,WU F,JIANG T,et al.Ultrasound image-based thyroid nodule automatic segmentation using convolutional neural networks[J].Int J Comput Assist Radiol Surg,2017,12(11): 1895-1910.
[21] WANG L,YANG S,YANG S,et al.Automatic thyroid nodule recognition and diagnosis in ultrasound imaging with the YOLOv2 neural network[J].World J Surg Oncol,2019,17(1):12.
[22] 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.
[23] ZHOU S,QIU Y,HAN L,et al.A lightweight network for automatic thyroid nodules location and recognition with high speed and accuracy in ultrasound images[J].J Xray Sci Technol,2022,30(5):967-981.
[24] WANG B,WAN Z,LI C,et al.Identification of benign and malignant thyroid nodules based on dynamic AI ultrasound intelligent auxiliary diagnosis system[J].Front Endocrinol (Lausanne),2022,13(9):1018321.
[25] FANG Z,JIANG T A,JIN Q F,et al.Analyses of 35 cases of papillary thyroid carcinoma under the background of Hashimoto's thyroiditis[J].J Med Imaging,2011,21(2):1792-1797.
[26] ZHANG C,LIU D,HUANG L,et al.Classification of thyroid nodules by using deep learning radiomics based on ultrasound dynamic video[J].J Ultrasound Med,2022,41(12):2993-3002.
[27] LIU F,LIU D,WANG K,et al.Deep learning radiomics based on contrast-enhanced ultrasound might optimize curative treatments for very-early or early-stage hepatocellular carcinoma patients[J].Liver Cancer,2020,9(4):397-413.
[28] TONG T,GU J,XU D,et al.Deep learning radiomics based on contrast-enhanced ultrasound images for assisted diagnosis of pancreatic ductal adenocarcinoma and chronic pancreatitis[J].BMC Med,2022,20(1):74.
[29] WAN P,CHEN F,LIU C,et al.Hierarchical temporal attention network for thyroid nodule recognition using dynamic ceus imaging[J].IEEE Trans Med Imaging,2021,40(6):1646-1660.
[30] GUO L H,WANG D,QIAN Y Y,et al.A two-stage multi-view learning framework based computer-aided diagnosis of liver tumors with contrast enhanced ultrasound images[J].Clin Hemorheol Microcirc,2018,69(3):343-354.
[31] 徐丹凤，王志利，刘洋，等.超声弹性成像联合TSH检测对甲状腺结节良恶性鉴别诊断的价值分析[J].东南大学学报(医学版),2018,37(1):50-54.
[32] HU L,PEI C,XIE L,et al.Convolutional neural network for predicting thyroid cancer based on ultrasound elastography image of perinodular region[J].Endocrinology,2022,163(11):135.
[33] 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.
[34] ZHANG X Y,WEI Q,WU G G,et al.Artificial intelligence-based ultrasound elastography for disease evaluation-a narrative review[J].Front Oncol,2023,13:1197447.
[35] XIA S,YAO J,ZHOU W,et al.A computer-aided diagnosing system in the evaluation of thyroid nodules-experience in a specialized thyroid center[J].World J Surg Oncol,2019,17(1):210.
[36] ZHANG Y.Classification and diagnosis of thyroid carcinoma using reinforcement residual network with visual attention mechanisms in ultrasound images[J].J Med Syst,2019,43(11):323.
[37] PAN L,CAI Y,LIN N,et al.A two-stage network with prior knowledge guidance for medullary thyroid carcinoma recognition in ultrasound images[J].Med Phys,2022,49(4):2413-2426.
[38] LONDON A J.Artificial intelligence and black-box medical decisions: accuracy versus explainability[J].Hastings Cent Rep,2019,49(1):15-21.
[39] ZHAO W J,FU L R,HUANG Z M,et al.Effectiveness evaluation of computer-aided diagnosis system for the diagnosis of thyroid nodules on ultrasound: a systematic review and meta-analysis[J].Medicine (Baltimore),2019,98(32):16379.