切换至 "中华医学电子期刊资源库"

中华医学超声杂志(电子版) ›› 2023, Vol. 20 ›› Issue (09) : 895 -903. doi: 10.3877/cma.j.issn.1672-6448.2023.09.002

高帧频超声影像学

基于高帧频超声造影的影像组学特征鉴别诊断甲状腺结节良恶性的价值
张茜, 陈佳慧, 高雪萌, 赵傲雪, 黄瑛()   
  1. 110004 沈阳,中国医科大学附属盛京医院超声科
  • 收稿日期:2023-06-07 出版日期:2023-09-01
  • 通信作者: 黄瑛

Value of radiomics features based on high-frame-rate contrast-enhanced ultrasound in differential diagnosis of benign and malignant thyroid nodules

Qian Zhang, Jiahui Chen, Xuemeng Gao, Aoxue Zhao, Ying Huang()   

  1. Department of Ultrasound, Shengjing Hospital of China Medical University, Shenyang 110004, China
  • Received:2023-06-07 Published:2023-09-01
  • Corresponding author: Ying Huang
引用本文:

张茜, 陈佳慧, 高雪萌, 赵傲雪, 黄瑛. 基于高帧频超声造影的影像组学特征鉴别诊断甲状腺结节良恶性的价值[J]. 中华医学超声杂志(电子版), 2023, 20(09): 895-903.

Qian Zhang, Jiahui Chen, Xuemeng Gao, Aoxue Zhao, Ying Huang. Value of radiomics features based on high-frame-rate contrast-enhanced ultrasound in differential diagnosis of benign and malignant thyroid nodules[J]. Chinese Journal of Medical Ultrasound (Electronic Edition), 2023, 20(09): 895-903.

目的

评估从甲状腺灰阶超声图像、常规超声造影(CEUS)及高帧频超声造影(H-CEUS)图像中提取的影像组学特征对于甲状腺结节良恶性诊断的价值及其诊断效能。

方法

回顾性收集并最终纳入2021年1月至2022年4月中国医科大学附属盛京医院的186例患者的186个结节的灰阶超声图像、常规CEUS及H-CEUS视频数据,分别选择灰阶超声图像中结节最大长轴的横向切面、纵向切面以及常规CEUS和H-CEUS视频中造影剂到达时间、达峰时间、平均消退时间对应的3个关键帧图像这8张图像进行分析并提取相应的影像组学特征,采用逻辑回归和随机森林建立3种影像组学模型(灰阶超声、灰阶超声+常规CEUS和灰阶超声+H-CEUS模型),最后,评估这些影像组学特征的诊断效能,比较3种模型在测试集(38个结节)中的曲线下面积(AUC)、敏感度、特异度、阳性预测值(PPV)、阴性预测值(NPV)、准确性、F1评分。

结果

共提取186例患者186个结节的9000个影像组学特征,灰阶超声模型在测试集中的AUC、准确性、敏感度、特异度、PPV、NPV和F1评分分别为0.81、81.6%、68.8%、90.9%、84.6%、80.0%和0.76。灰阶超声+常规CEUS模型在测试集中的AUC、准确性、敏感度、特异度、PPV、NPV和F1评分分别为0.87、84.2%、68.8%、95.5%、91.7%、80.8%和0.79。灰阶超声+H-CEUS模型在测试集中的AUC、准确性、敏感度、特异度、PPV、NPV和F1评分分别为0.91、86.8%、87.5%、86.4%、82.4%、90.5%和0.85。

结论

基于灰阶超声图像、常规CEUS和H-CEUS关键帧图像的影像组学特征对于鉴别良恶性甲状腺结节具有一定价值,灰阶超声+H-CEUS图像的影像组学模型的诊断效能优于灰阶超声模型和灰阶超声+常规CEUS影像组学模型。

Objective

To evaluate the clinical application and diagnostic efficiency of the radiomics features extracted from thyroid B-mode ultrasound (B-US) images, contrast-enhanced ultrasound (CEUS) images, and high-frame-rate contrast-enhanced ultrasound (H-CEUS) images in classifying and predicting benign and malignant thyroid nodules.

Methods

We retrospectively collected and ultimately included B-US images, CEUS videos, and H-CEUS videos of 186 nodules from 186 patients. Next, we selected the following eight images to manually select the regions of interest: nodule in transverse section, nodule in longitudinal section, and the "rise time" frame, "time to peak" frame, and "mean transit time" frame of both CEUS and H-CEUS videos, and then extracted the corresponding radiomics features from these images. We established three radiomics models (B-US radiomics model, B-US+CEUS radiomics model, and B-US+H-CEUS radiomics model) based on these radiomics features by Logistic regression and random forest, and assessed the diagnostic performance of these radiomics features. Finally, the area under curve (AUC), sensitivity, specificity, positive predictive value (PPV), and negative predictive value (NPV), accuracy (ACC), and F1-score in the test set (n=38) were calculated and compared.

Results

A total of 9000 significant radiomics features of 186 nodules from 186 patients were extracted. The AUC in the differential diagnosis of the nature of thyroid nodules was 0.81 for the B-US radiomics model, 0.87 for the B-US+CEUS radiomics model, and 0.91 for the B-US+H-CEUS radiomics model. The accuracy, sensitivity, specificity, PPV, NPV, and F1 scores of the B-US radiomics model in the test set were 81.6%, 68.8%, 90.9%, 84.6%, 80.0%, and 0.76, respectively; the corresponding values were 84.2%, 68.8%, 95.5%, 91.7%, 80.8%, and 0.79 for the B-US+CEUS radiomics model, and 86.8%, 87.5%, 86.4%, 82.4%, 90.5%, and 0.85 for the B-US+H-CEUS radiomics model.

Conclusion

Radiomics features based on B-US images, CEUS, and H-CEUS key frame images have appreciated clinical value in differentiating benign and malignant thyroid nodules. The diagnostic efficacy of the B-US+H-CEUS radiomics model is better than that of other radiomics models.

图1 图像选择、感兴趣区(ROI)勾画及特征提取流程
表1 不同超声组学模型对测试集甲状腺结节的诊断结果
表2 良恶性甲状腺结节组一般临床资料及影像特征比较
图2 恶性结节常规超声造影图像及高帧频超声造影(H-CEUS)图像。该结节细针穿刺病理结果为“Bethesda Ⅵ”,甲状腺乳头状癌;图a为常规超声造影到达时刻图像;图b为常规超声造影达峰时刻图像;图c为常规超声造影平均消退时刻图像;图d为H-CEUS到达时刻图像;图e为H-CEUS达峰时刻图像;图f为H-CEUS平均消退时刻图像。本图中常规超声造影帧频为15帧/s,H-CEUS帧频为87帧/s
图3 良性结节常规超声造影图像及高帧频超声造影(H-CEUS)图像。该结节细针穿刺病理结果为“Bethesda Ⅱ”。图a为常规超声造影到达时刻图像;图b为常规超声造影达峰时刻图像;图c为常规超声造影平均消退时刻图像;图d为H-CEUS到达时刻图像;图e为H-CEUS达峰时刻图像;图f为H-CEUS平均消退时刻图像。本图中常规超声造影帧频为15帧/s,H-CEUS帧频为87帧/s
图4 灰阶超声模型、灰阶超声+常规超声造影(CEUS)模型和灰阶超声+高帧频超声造影(H-CEUS)模型在甲状腺结节测试集的受试者操作特征曲线
表3 3种诊断模型对测试集中甲状腺结节良恶性的诊断效能
12
Chen W, Zheng R, Baade PD, et al. Cancer statistics in China, 2015 [J]. CA Cancer J Clin, 2016, 66(2): 115-132.
13
Lo CY. Thyroidectomy for papillary thyroid carcinoma [J]. Methods Mol Biol, 2022, 2534: 39-56.
14
Cappelli C, Pirola I, Agosti B, et al. Complications after fine-needle aspiration cytology: a retrospective study of 7449 consecutive thyroid nodules [J]. Br J Oral Maxillofac Surg, 2017, 55(3): 266-269.
15
Zhu YC, Jin PF, Bao J, et al. Thyroid ultrasound image classification using a convolutional neural network [J]. Ann Transl Med, 2021, 9(20): 1526.
16
Park VY, Lee E, Lee HS, et al. Combining radiomics with ultrasound-based risk stratification systems for thyroid nodules: an approach for improving performance [J]. Eur Radiol, 2021, 31(4): 2405-2413.
17
Colakoglu B, Alis D, Yergin M. Diagnostic value of machine learning-based quantitative texture analysis in differentiating benign and malignant thyroid nodules [J]. J Oncol, 2019, 2019: 6328329.
18
Guo SY, Zhou P, Zhang Y, et al. Exploring the value of radiomics features based on B-mode and contrast-enhanced ultrasound in discriminating the nature of thyroid nodules [J]. Front Oncol, 2021, 11: 738909.
19
Liu Y, Wu H, Zhou Q, et al. Diagnostic value of conventional ultrasonography combined with contrast-enhanced ultrasonography in thyroid imaging reporting and data system (TI-RADS) 3 and 4 thyroid micronodules [J]. Med Sci Monit, 2016, 22: 3086-3094.
20
Zhou Q, Jiang J, Shang X, et al. Correlation of contrast-enhanced ultrasonoimagedata features with microvessel density in papillary thyroid carcinomas [J]. Asian Pac J Cancer Prev, 2014, 15(17): 7449-7452.
21
Hu Y, Li P, Jiang S, et al. Quantitative analysis of suspicious thyroid nodules by contrast-enhanced ultrasonography [J]. Int J Clin Exp Med, 2015, 8(7): 11786-11793.
22
韩鹏, 费翔, 罗渝昆, 等. 高帧频超声造影在鉴别诊断胆囊腺瘤性息肉与胆固醇性息肉中的临床应用 [J/OL]. 中华医学超声杂志(电子版), 2020, 17(9): 815-820.
23
Fei X, Han P, Jiang B, et al. High frame rate contrast-enhanced ultrasound helps differentiate malignant and benign focal liver lesions [J]. J Clin Transl Hepatol, 2022, 10(1): 26-33.
24
Giangregorio F, Garolfi M, Mosconi E, et al. High frame-rate contrast enhanced ultrasound (HIFR-CEUS) in the characterization of small hepatic lesions in cirrhotic patients [J]. J Ultrasound, 2023, 26(1): 71-79.
25
Sidhu PS, Cantisani V, Dietrich CF, et al. The EFSUMB guidelines and recommendations for the clinical practice of contrast-enhanced ultrasound (CEUS) in non-hepatic applications: update 2017 (short version) [J]. Ultraschall Med, 2018, 39(2): 154-180.
26
Radzina M, Ratniece M, Putrins DS, et al. Performance of contrast-enhanced ultrasound in thyroid nodules: review of current state and future perspectives [J]. Cancers (Basel), 2021, 13(21): 5469.
27
Pang T, Huang L, Deng Y, et al. Logistic regression analysis of conventional ultrasonography, strain elastosonography, and contrast-enhanced ultrasound characteristics for the differentiation of benign and malignant thyroid nodules [J]. PLoS One, 2017, 12(12): e0188987.
28
Xu Y, Qi X, Zhao X, et al. Clinical diagnostic value of contrast-enhanced ultrasound and TI-RADS classification for benign and malignant thyroid tumors: one comparative cohort study [J]. Medicine (Baltimore), 2019, 98(4): e14051.
29
Cao Y, Zhong X, Diao W, et al. Radiomics in differentiated thyroid cancer and nodules: explorations, application, and limitations [J]. Cancers (Basel), 2021, 13(10): 2436.
30
Rizzo S, Botta F, Raimondi S, et al. Radiomics: the facts and the challenges of image analysis [J]. Eur Radiol Exp, 2018, 2(1): 36.
31
Mayerhoefer ME, Materka A, Langs G, et al. Introduction to Radiomics [J]. J Nucl Med, 2020, 61(4): 488-495.
32
Sarica A, Cerasa A, Quattrone A. Random forest algorithm for the classification of neuroimaging data in Alzheimer's disease: a systematic review [J]. Front Aging Neurosci, 2017, 9: 329.
1
Durante C, Grani G, Lamartina L, et al. The diagnosis and management of thyroid nodules: a review [J]. JAMA, 2018, 319(9): 914-924.
2
Grani G, Sponziello M, Pecce V, et al. Contemporary thyroid nodule evaluation and management [J]. J Clin Endocrinol Metab, 2020, 105(9): 2869-2883.
3
Sorrenti S, Dolcetti V, Fresilli D, et al. The role of CEUS in the evaluation of thyroid cancer: from diagnosis to local staging [J]. J Clin Med, 2021, 10(19): 4559.
4
Cantisani V, Consorti F, Guerrisi A, et al. Prospective comparative evaluation of quantitative-elastosonography (Q-elastography) and contrast-enhanced ultrasound for the evaluation of thyroid nodules: preliminary experience [J]. Eur J Radiol, 2013, 82(11): 1892-1898.
5
Greis C. Quantitative evaluation of microvascular blood flow by contrast-enhanced ultrasound (CEUS) [J]. Clin Hemorheol Microcirc, 2011, 49(1-4): 137-149.
6
Rafailidis V, Huang DY, Yusuf GT, et al. General principles and overview of vascular contrast-enhanced ultrasonography [J]. Ultrasonography, 2020, 39(1): 22-42.
7
李楠, 梁舒媛, 费翔, 等. 高帧频超声造影对颈动脉粥样硬化斑块内新生血管的评价价值 [J/OL]. 中华医学超声杂志(电子版), 2020, 17(9): 854-859.
8
Chen JH, Huang Y. High-frame-rate contrast-enhanced ultrasound findings of liver metastasis of duodenal gastrointestinal stromal tumor: A case report and literature review [J]. World J Clin Cases, 2022, 10(17): 5899-5909.
9
任玲, 费翔, 张艳, 等. 高帧率超声造影对颈部浅表淋巴结病变良恶性的鉴别诊断 [J]. 中国医学影像学杂志, 2021, 29(10): 989-992, 997.
10
Lambin P, Rios-Velazquez E, Leijenaar R, et al. Radiomics: extracting more information from medical images using advanced feature analysis [J]. Eur J Cancer, 2012, 48(4): 441-446.
11
Cibas ES, Ali SZ. The 2017 Bethesda system for reporting thyroid cytopathology [J]. Thyroid, 2017, 27(11): 1341-1346.
[1] 丁雷, 罗文, 杨晓, 庞丽娜, 张佩蒂, 刘海静, 袁佳妮, 刘瑾. 高帧频超声造影在评价C-TIRADS 4-5类甲状腺结节成像特征中的应用[J]. 中华医学超声杂志(电子版), 2023, 20(09): 887-894.
[2] 朱连华, 费翔, 韩鹏, 姜波, 李楠, 罗渝昆. 高帧频超声造影在胆囊息肉样病变中的鉴别诊断价值[J]. 中华医学超声杂志(电子版), 2023, 20(09): 904-910.
[3] 李卫民, 陈军民, 黄艳丽, 范晓芳, 韩文, 贾磊, 张俊超, 瞿辰. 基于中国甲状腺超声报告与数据系统分析超声在不同大小甲状腺结节中的诊断价值[J]. 中华医学超声杂志(电子版), 2023, 20(07): 743-748.
[4] 付泽辉, 王思齐, 卢叶君, 张剑, 贺烨, 陈卉. 超声对易误诊的等回声、高回声甲状腺结节良恶性的鉴别[J]. 中华医学超声杂志(电子版), 2023, 20(05): 517-523.
[5] 郭云云, 解翔, 彭梅, 姜凡, 毕玉, 何年安, 胡蕾, 杨杨, 王涛, 石玉洁, 陈冬冬. ACR-TIRADS与C-TIRADS分类分别联合二维剪切波弹性成像对甲状腺结节分类的诊断效能——多中心回顾性研究[J]. 中华医学超声杂志(电子版), 2023, 20(05): 511-516.
[6] 郭东, 姚春, 庞海苏, 单悦. 超声微血流成像联合弹性成像评分对甲状腺TI-RADS 4类结节良恶性的鉴别诊断价值[J]. 中华医学超声杂志(电子版), 2022, 19(10): 1098-1102.
[7] 王瑛, 陈英格, 叶素敏, 陈东, 刘宇, 刘再毅, 刘敏. 超声影像组学标签对乳腺癌腋窝淋巴结转移的预测价值[J]. 中华医学超声杂志(电子版), 2022, 19(08): 774-778.
[8] 付泽辉, 卢叶君, 张剑, 莫晓民, 贺烨, 张晓青, 陶楚楚, 陈卉. 常规超声特征联合内部粗大钙化特征鉴别甲状腺结节良恶性的价值[J]. 中华医学超声杂志(电子版), 2022, 19(08): 767-773.
[9] 唐玮, 何融泉, 黄素宁. 深度学习在乳腺癌影像诊疗和预后预测中的应用[J]. 中华乳腺病杂志(电子版), 2023, 17(06): 323-328.
[10] 吴佩琪. 乳腺癌瘤周影像组学研究进展[J]. 中华乳腺病杂志(电子版), 2023, 17(05): 301-304.
[11] 李俊, 彭健韵, 邱婉冰, 窦倩怡, 潘福顺, 梁瑾瑜. 甲状腺结节恶性风险分层(指南):ACR TI-RADS与C-TIRADS诊断效能及不同医师使用指南一致性的多中心回顾性比较研究[J]. 中华普通外科学文献(电子版), 2023, 17(06): 401-407.
[12] 柴吉鑫, 张雪, 何时知, 齐艳涛, 王婧婧, 敖亚洲, 陈泳. 不同穿刺方法对甲状腺结节细胞学检查的应用[J]. 中华普外科手术学杂志(电子版), 2023, 17(03): 315-318.
[13] 叶垚坤, 姜家锁, 叶靖, 张丽莎, 蒋巧会, 丁贵苏, 闵凌峰. 基于CT的影像组学评估自发性气胸患者的预后[J]. 中华肺部疾病杂志(电子版), 2023, 16(02): 185-189.
[14] 吴凤芸, 滕鑫, 刘连娟. 高帧频超声造影与增强磁共振对不同直径原发性高分化肝细胞癌的诊断价值[J]. 中华消化病与影像杂志(电子版), 2023, 13(06): 404-408.
[15] 黄文鹏, 邱永康, 杨琦, 宋乐乐, 陈钊, 范岩, 康磊. PET相关影像组学在肿瘤预后中的研究进展[J]. 中华消化病与影像杂志(电子版), 2023, 13(02): 104-110.
阅读次数
全文


摘要