Comparative study of C-TIRADS, shear-wave elastography, and artificial intelligence in size-stratified diagnosis of thyroid nodules

ZHOU Yuwei; LI Ruifen; ZHENG Weiwei; WANG Yang; LIU Zhaoguang; YANG Jing

doi:10.19732/j.cnki.2096-6210.2026.02.008

您当前的位置：

首页 >

文章列表页 >

Comparative study of C-TIRADS, shear-wave elastography, and artificial intelligence in size-stratified diagnosis of thyroid nodules

Article | 更新时间：2026-05-07

- Comparative study of C-TIRADS, shear-wave elastography, and artificial intelligence in size-stratified diagnosis of thyroid nodules
- Oncoradiology Vol. 35, Issue 2, Pages: 282-290(2026)
- 作者机构：
  
  唐山市人民医院超声科，河北唐山 063000
- 作者简介：
  
  ZHOU Yuwei E-mail: 398869487@qq.com
- 基金信息：
  
  Medical Science Research Project of Hebei(20251223)
- DOI：10.19732/j.cnki.2096-6210.2026.02.008
  CLC： R736.1;R445.1
- Received：17 November 2025，
  
  Revised：2026-02-06，
  
  Published：28 April 2026
- 稿件说明：
移动端阅览
周宇微, 李瑞芬, 郑薇薇, 等. C-TIRADS、剪切波弹性成像及人工智能在甲状腺结节大小分层诊断中的比较研究［J］. 肿瘤影像学, 2026, 35(2): 282-290.

ZHOU Y W, LI R F , ZHENG W W, et al.Citation: Comparative study of C-TIRADS, shear-wave elastography, and artificial intelligence in size-stratified diagnosis of thyroid nodules［J］. Oncoradiology, 2026, 35(2): 282-290.
周宇微, 李瑞芬, 郑薇薇, 等. C-TIRADS、剪切波弹性成像及人工智能在甲状腺结节大小分层诊断中的比较研究［J］. 肿瘤影像学, 2026, 35(2): 282-290. DOI： 10.19732/j.cnki.2096-6210.2026.02.008.

ZHOU Y W, LI R F , ZHENG W W, et al.Citation: Comparative study of C-TIRADS, shear-wave elastography, and artificial intelligence in size-stratified diagnosis of thyroid nodules［J］. Oncoradiology, 2026, 35(2): 282-290. DOI： 10.19732/j.cnki.2096-6210.2026.02.008.

摘要

目的

比较剪切波弹性成像（shear wave elastography，SWE）、中国甲状腺影像报告和数据系统（Chinese Thyroid Imaging Reporting and Data System，C-TIRADS）及人工智能（artificial intelligence，AI）辅助诊断系统在不同大小甲状腺结节良恶性鉴别中的诊断效能。

方法

回顾并分析2024年7月—2025年3月于唐山市人民医院就诊的甲状腺结节患者的影像学资料，根据最大径分为

10 mm组和≥10 mm组。每个结节均接受常规超声检查以获取C-TIRADS分级，并进行SWE及AI分析。采用受试者工作特征（receiver operating characteristic，ROC）曲线评估SWE（

max

、

mean

、

med

）、C-TIRADS、AI及其联合应用的诊断效能。

结果

共纳入90例甲状腺结节患者，年龄16~73岁，共计103枚病灶。依据结节最大径，将病灶分为

10 mm组（

=47）和≥10 mm组（

=56）。在≥10 mm组中，AI表现出较高的诊断效能［曲线下面积（area under curve，AUC）=0.875，95% CI 0.775~0.976，灵敏度为96.55%，特异度为77.78%］，优于其在

10 mm组中的表现（AUC=0.654，95% CI 0.381~0.928，特异度为33.33%）。AI与C-TIRADS联合可提高灵敏度（98.57%），但特异度中等（57.58%）。值得注意的是，在

10mm组结节中，该联合方式并未优于AI单独诊断，AUC甚至下降至0.488（95% CI 0.242~0.733）。在SWE参数中，

max

在≥10 mm组的AUC最高（AUC：0.895，95% CI 0.811~0.979）。然而，将

max

与AI+C-TIRADS联合后并未进一步提高诊断准确度。

结论

AI辅助诊断系统及

max

在≥10 mm结节中均表现出较高的诊断效能。对于≥1 cm结节，AI结合C-TIRADS可进一步提升诊断准确度，而SWE，尤其是

max

，在反映结节组织硬度方面具有独特优势，可作为AI与C-TIRADS诊断结果的重要参考。

Abstract

Objective

To compare the diagnostic performance of shear wave elastography (SWE)

the Chinese Thyroid Imaging Reporting and Data System (C-TIRADS)

and an artificial intelligence (AI)-assisted diagnostic system in differentiating benign and malignant thyroid nodules of different sizes.

Methods

A retrospective analysis was conducted on the imaging data of patients with thyroid nodules who visited Tangshan People's Hospital between July 2024 and March 2025 and categorized into two groups based on maximum diameter:

10 mm and ≥10 mm. Each nodule underwent conventional ultrasound to obtain C-TIRADS scores

SWE assessment

an AI analysis. Receiver operating characteristic (ROC) curves were used to evaluate the diagnostic performance of SWE parameters (

max

mean

med

)

C-TIRADS

and their combinations.

Results

A total of 90 patients with thyroid nodules

aged 16 to 73 years

were included in the study

representing a total of 103 lesions. Based on the maximum diameter of the nodules

the lesions were divided into a

10 mm group (

=47) and a ≥10 mm group (

=56).

In nodules ≥10 mm

AI exhibited superior diagnostic performance (AUC=0.875

95% CI 0.775-0.976

sensitivity=96.55%

specificity=77.78%) compared to nodules

10 mm (AUC=0.654

95% CI 0.381-0.928

specificity=33.33%). The combination of AI and C-TIRADS increased sensitivity to 98.57%

but specificity remained moderate (57.58%). Notably

in nodules

10 mm

this combination did not outperform AI alone

with a decreased AUC of 0.488（95% CI 0.242-0.733）. Among SWE parameters

max

achieved the highest AUC in the ≥10 mm group (AUC=0.895，95% CI 0.811-0.979). However

adding

max

to AI+C-TIRADS did not further improve diagnostic accuracy.

Conclusion

The AI-assisted diagnostic system and

max

both demonstrated high diagnostic performance in nodules ≥10 mm. For nodules ≥1 cm

combining AI with C-TIRADS could further enhance diagnostic accuracy

while SWE

particularly

max

provides unique advantages in reflecting tissue stiffness and may serve as an important reference for interpreting AI and C-TIRADS findings.

关键词

Keywords

references

何惠珍 , 叶洁仪 , 黄伟俊 . 多模态超声检查对甲状腺乳头状癌颈部中央区淋巴结转移的预测价值［J］. 肿瘤影像学 , 2024 , 33 ( 6 ): 609 - 614 .

HE H Z , YE J Y , HUANG W J . The predictive value of multimodal ultrasound in central lymph node metastasis of papillary carcinoma of the thyroid ［J］. Oncoradiology , 2024 , 33 ( 6 ): 609 - 614 .

孙　鑫 , 张　巍 , 程令刚 , 等 . 甲状腺乳头状癌临床、多模态超声及病理学特征与 BRAF V600E 突变的相关性［J］. 中国医学影像技术 , 2024 , 40 ( 5 ): 730 - 734 .

SUN X , ZHANG W , CHENG L G , et al . Correlations of clinical, multi-modal ultrasonic and pathological features of papillary thyroid carcinoma with BRAF V600E mutation ［J］. Chin J Med Imag Technol , 2024 , 40 ( 5 ): 730 - 734 .

周建桥 , 詹维伟 . 2020年中国超声甲状腺影像报告和数据系统（C-TIRADS）指南解读［J］. 诊断学理论与实践 , 2020 , 19 ( 4 ): 350 - 353 .

ZHOU J Q , ZHAN W W . Interpretation of 2020 Chinese guidelines for thyroid imaging reporting and data system (C-TIRADS) for ultrasound ［J］. J Diagn Concepts Pract , 2020 , 19 ( 4 ): 350 - 353 .

HA E J , CHUNG S R , NA D G , et al . 2021 Korean thyroid imaging reporting and data system and imaging-based management of thyroid nodules: Korean Society of Thyroid Radiology consensus statement and recommendations ［J］. Korean J Radiol , 2021 , 22 ( 12 ): 2094 - 2123 .

JEONG E Y , KIM H L , HA E J , et al . Computer-aided diagnosis system for thyroid nodules on ultrasonography: diagnostic performance and reproducibility based on the experience level of operators ［J］. Eur Radiol , 2019 , 29 ( 4 ): 1978 - 1985 .

BORA MAKAL G , ASLAN A . The diagnostic value of the American College of Radiology Thyroid Imaging Reporting and Data System classification and shear-wave elastography for the differentiation of thyroid nodules ［J］. Ultrasound Med Biol , 2021 , 47 ( 5 ): 1227 - 1234 .

FILHO R H C , PEREIRA F L , IARED W . Diagnostic accuracy evaluation of two-dimensional shear wave elastography in the differentiation between benign and malignant thyroid nodules: systematic review and meta-analysis ［J］. J Ultrasound Med , 2020 , 39 ( 9 ): 1729 - 1741 .

TUO J M , SI X J , SONG H Q . Artificial intelligence technology enhances the performance of shear wave elastography in thyroid nodule diagnosis ［J］. Am J Transl Res , 2023 , 15 ( 10 ): 6226 - 6233 .

CHUNG S R , BAEK J H , LEE M K , et al . Computer-aided diagnosis system for the evaluation of thyroid nodules on ultrasonography: prospective non-inferiority study according to the experience level of radiologists ［J］. Korean J Radiol , 2020 , 21 ( 3 ): 369 - 376 .

ADLER D D , CARSON P L , RUBIN J M , et al . Doppler ultrasound color flow imaging in the study of breast cancer: preliminary findings ［J］. Ultrasound Med Biol , 1990 , 16 ( 6 ): 553 - 559 .

TAN R , LIU J , TANG Q , et al . Clinical diagnostic value of shear-wave elastography in detecting malignant nipple retraction ［J］. J Comput Assist Tomogr , 2025 , 49 ( 1 ): 73 - 79 .

中华医学会内分泌学会 , 中华医学会外科学分会甲状腺及代谢外科学组 , 中国抗癌协会头颈肿瘤专业委员会 , 等 . 甲状腺结节和分化型甲状腺癌诊治指南（第二版） . 中华内分泌代谢杂志 , 2023 , 39 ( 3 ): 181 - 226 .

Chinese Society of Endocrinology , Thyroid and Metabolic Surgery Group of the Chinese Society of Surgery , Head and Neck Tumor Committee of the Chinese Anti-Cancer Association , et al . Guidelines for the diagnosis and treatment of thyroid nodules and differentiated thyroid carcinoma (2nd edition) ［J］. Chin Int J Endocrinol Metab , 2023 , 39 ( 3 ): 181 - 226 .

LIH , KANGC , XUEJ , et al . Influence of lesion size on shear elastography in the diagnosis of benign and malignant thyroid nodules ［J］. Sci Rep , 2021 , 11 ( 1 ): 21616 .

WANG B , WAN Z , ZHANG M B , et al . Diagnostic value of a dynamic artificial intelligence ultrasonic intelligent auxiliary diagnosis system for benign and malignant thyroid nodules in patients with Hashimoto thyroiditis ［J］. Quant Imaging Med Surg , 2023 , 13 ( 6 ): 3618 - 3629 .

ZHOU J Q , YIN L X , WEI X , et al . 2020 Chinese guidelines for ultrasound malignancy risk stratification of thyroid nodules: the C-TIRADS ［J］. Endocrine , 2020 , 70 ( 2 ): 256 - 279 .

CAVALLO A , JOHNSON D N , WHITE M G , et al . Thyroid nodule size at ultrasound as a predictor of malignancy and final pathologic size ［J］. Thyroid , 2017 , 27 ( 5 ): 641 - 650 .

花　霞 , 赵艳红 , 鹿丹丹 , 等 . 甲状腺结节大小对细针穿刺细胞学及多模态超声诊断准确度的影响［J］. 河北医科大学学报 , 2022 , 43 ( 10 ): 1178 - 1182 .

HUA X , ZHAO Y H , LU D D , et al . The influence of thyroid nodule size on the accuracy of fine needle aspiration cytology and multimodal ultrasound diagnosis ［J］. J Hebei Med Univ , 2022 , 43 ( 10 ): 1178 - 1182 .

CHAMBARA N , LO X , CHOW T C M , et al . Combined shear wave elastography and EU TI-RADS in differentiating malignant and benign thyroid nodules ［J］. Cancers , 2022 , 14 ( 22 ): 5521 .

XUE J P , KANG X Y , MIAO J W , et al . Analysis of the influence of thyroid nodule characteristics on the results of shear wave elastography ［J］. Front Endocrinol , 2022 , 13 : 858565 .

FUKUHARA T , MATSUDA E , ENDO Y , et al . Correlation between quantitative shear wave elastography and pathologic structures of thyroid lesions ［J］. Ultrasound Med Biol , 2015 , 41 ( 9 ): 2326 - 2332 .

何　珂 , 周兴华 , 何炼图 , 等 . C-TIRADS分类联合剪切波弹性成像鉴别诊断不同大小甲状腺结节的临床价值［J］. 临床超声医学杂志 , 2024 , 26 ( 1 ): 54 - 58 .

HE K , ZHOU X H , HE L T , et al . Clinical value of C-TIRADS category combined with shear wave elastography in the differential diagnosis of thyroid nodules with different sizes ［J］. J Clin Ultrasound Med , 2024 , 26 ( 1 ): 54 - 58 .

董明华 , 孟　芳 . 超声AI联合C-TIRADS在甲状腺结节良恶性鉴别中的效果分析［J］. 中国实验诊断学 , 2025 , 29 ( 8 ): 910 - 915 .

DONG M H , MENG F . Effect analysis of ultrasonic AI combined with C-TIRADS in differential diagnosis of benign and malignant thyroid nodules ［J］. Chin J Lab Diagn , 2025 , 29 ( 8 ): 910 - 915 .

Views

下载量

CNKI被引量

Alert me when the article has been cited

提交

Tools

Publicity Resources

Value of SE and SWE elastic ultrasound in differential diagnosis of TI-RADS 4 thyroid nodule with a maximum diameter ≤1 cm

Application value of shear wave elastography in the evaluation of glomerular diseases in children

Multivariate analysis of ultrasonographic characteristics for differentiating benign and malignant BethesdaⅢ category thyroid nodules

Diagnostic value of contrast-enhanced ultrasound combined with fine-needle aspiration biopsy in thyroid TI-RADS 4 nodules

ATA guidelines, Kwak TI-RADS, ACR TI-RADS, and C TI - RADS are compared for the diagnostic performance of thyroid nodules in children

Related Author

LI Gang

JIA Chao

LIU Long

ZHANG Fan

KUANG Yi

GAO Feng

SHI Qiusheng

DU Lianfang

Related Institution

Department of Ultrasound, Shanghai Jiao Tong University School of Medicine Affiliated Xinhua Hospital

Department of Pathology, Shanghai Jiao Tong University School of Medicine Affiliated Xinhua Hospital

Department of Ultrasound, The Fourth Affiliated Hospital of Nanjing Medical University

Department of Ultrasound, Jinling Clinical Medical College, Nanjing Medical University, General Hospital of the Eastern Theater of the Chinese People's Liberation Army

Department of Ultrasound, Tangshan Central Hospital

AI脑图

AI问答

⁰