基于CT影像组学诺模图预测微小甲状腺结节良恶性

doi:10.6040/j.issn.1673-3770.1.2020.028

山东大学耳鼻喉眼学报 ›› 2020, Vol. 34 ›› Issue (3): 32-39.doi: 10.6040/j.issn.1673-3770.1.2020.028

基于CT影像组学诺模图预测微小甲状腺结节良恶性

武欣欣¹,李静静^1,2,毛宁^3,4,郑桂彬^1,5,郑海涛⁵,崔景景⁶,贾传亮¹,初同朋⁴,牟亚魁^1,7,宋西成^1,4,7

北京)有限公司, 北京 100192;
7. 青岛大学附属烟台毓璜顶医院泰山学者实验室, 山东烟台 264000

发布日期:2020-06-29
通讯作者: 宋西成. E-mail:songxicheng@126.com;牟亚魁. E-mail:muykmd@126.com
作者简介:武欣欣. E-mail:wuxinxin0713@126.com;李静静. E-mail:m17862891556@163.com
基金资助:
泰山学者工程资助项目(ts20190991)

A radiomics nomogram based on computed tomography for predicting benign and malignant thyroid nodules

WU Xinxin¹, LI Jingjing^1,2, MAO Ning^3,4, ZHENG Guibin^1,5, ZHENG Haitao⁵, CUI Jingjing⁶, JIA Chuanliang¹, CHU Tongpeng⁴, MOU Yakui^1,7, SONG Xicheng^1,4,7

1. Department of Otorhinolaryngology & Head and Neck Surgery, Yantai Yuhuangding Hospital, Qingdao University, Yantai 264000, Shandong, China;
2. Binzhou Medical University, School of Clinical Medicine, Yantai 264003, Shandong, China;
3. Department of Radiology, Yantai Yuhuangding Hospital, Qingdao University, Yantai 264000, Shandong, China;
4. Big Data and Artificial Intelligence Laboratory, Yantai Yuhuangding Hospital, Qingdao University, Yantai 264000, Shandong, China;
5. Department of Thyroid Surgery, Yantai Yuhuangding Hospital, Qingdao University, Yantai 264000, Shandong, China;
6. Huiying Medical Technology Co., Ltd. Dongsheng Science and Technology Park, Beijing 100192, China;
7. Taishan Scholar Laboratory, Yantai Yuhuangding Hospital, Qingdao University, Yantai 264000, Shandong, China;

Published:2020-06-29

摘要/Abstract

摘要： 目的探讨基于CT的影像组学诺模图对≤1 cm甲状腺结节良恶性的预测价值。方法回顾性收集2019年1月至8月烟台毓璜顶医院收治的160例符合条件的甲状腺结节患者(良性56例、恶性104例)的影像学及临床资料,随机将其分为训练集(n=127)和验证集(n=33)。从患者的平扫和增强CT动脉期图像中分别提取影像组学特征。在训练集中,采用单因素方差分析(ANOVA)和最小绝对收缩和选择算子(LASSO)筛选与良恶性结节相关影像组学特征并构建影像组学标签,结合所选特征与其加权系数乘积的线性组合生成影像组学标签得分(影像组学评分)。采用ANOVA筛选独立临床危险因素,并采用多因素Logistic回归结合影像组学评分筛选最终预测因素构建影像组学诺模图。使用受试者工作特性(ROC)曲线评价模型预测效能。结果 19个与甲状腺结节状态相关的特征组成的影像组学标签取得了良好的预测效果,并计算影像组学评分。多因素Logistic回归结果显示,甲状腺影像报告和数据系统(TI-RADS分级)、影像组学评分为甲状腺结节良恶性预测相关的独立危险因素。纳入这2种因素的影像组学诺模图在训练集(AUC:0.835;95%置信区间［CI］:0.776,0.884)和验证集中(AUC:0.793;95%CI:0.642,0.901)均显示出较好的鉴别能力。结论所提出的影像组学诺模图是一种结合影像组学特征和临床危险因素的无创预测工具,对≤1 cm甲状腺结节良恶性预测具有较高效能,显著优于常规影像学方法。

关键词: 甲状腺结节, 甲状腺影像报告和数据系统, 计算机断层扫描, 影像组学, 诺模图

中图分类号:

R739

武欣欣,李静静,毛宁,郑桂彬,郑海涛,崔景景,贾传亮,初同朋,牟亚魁,宋西成. 基于CT影像组学诺模图预测微小甲状腺结节良恶性[J]. 山东大学耳鼻喉眼学报, 2020, 34(3): 32-39.

WU Xinxin, LI Jingjing, MAO Ning, ZHENG Guibin, ZHENG Haitao, CUI Jingjing, JIA Chuanliang, CHU Tongpeng, MOU Yakui, SONG Xicheng. A radiomics nomogram based on computed tomography for predicting benign and malignant thyroid nodules[J]. Journal of Otolaryngology and Ophthalmology of Shandong University, 2020, 34(3): 32-39.

参考文献

[1] Burman KD, Wartofsky L. CLINICAL PRACTICE. Thyroid nodules[J]. N Engl J Med, 2015, 373(24): 2347-2356. doi:10.1056/NEJMcp1415786.
[2] Haugen BR, Alexander EK, Bible KC, 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. doi:10.1089/thy.2015.0020.
[3] 房居高. 强化手术技能和规范诊疗是提高甲状腺癌疗效的根本[J]. 山东大学耳鼻喉眼学报, 2016, 30(2): 1-4. FANG Jugao. Operation skill and standard diagnosis and treatment are the basics of improving the curative effect of thyroid carcinoma[J]. Journal of Otolaryngology and Ophthalmology of Shandong University, 2016, 30(2): 1-4.
[4] Siegel RL, Miller KD, Jemal A. Cancer statistics, 2019[J]. CA A Cancer J Clin, 2019, 69(1): 7-34. doi:10.3322/caac.21551.
[5] Noguchi S, Yamashita H, Uchino S, et al. Papillary microcarcinoma[J]. World J Surg, 2008, 32(5): 747-753. doi:10.1007/s00268-007-9453-0.
[6] Qu H, Sun GR, Liu Y, et al. Clinical risk factors for central lymph node metastasis in papillary thyroid carcinoma: a systematic review and meta-analysis[J]. ClinEndocrinol(Oxf), 2015, 83(1): 124-132. doi:10.1111/cen.12583.
[7] Luo Y, Zhao Y, Chen K, et al. Clinical analysis of cervical lymph node metastasis risk factors in patients with papillary thyroid microcarcinoma[J]. J Endocrinol Invest, 2019, 42(2): 227-236. doi:10.1007/s40618-018-0908-y.
[8] 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. doi:10.1016/j.ejca.2011.11.036.
[9] Bi WL, Hosny A, Schabath MB, et al. Artificial intelligence in cancer imaging: Clinical challenges and applications[J]. CA Cancer J Clin, 2019, 69(2): 127-157. doi:10.3322/caac.21552.
[10] Khorrami M, Prasanna P, Gupta A, et al. Changes in CT radiomicfeatures associated with lymphocyte distribution predict overall survival and response to immunotherapy in non-small cell lung cancer[J]. Cancer Immunol Res, 2020, 8(1): 108-119. doi:10.1158/2326-6066.CIR-19-0476.
[11] Liu ZY, Li ZL, QuJR, et al. Radiomics of multiparametric MRI for pretreatment prediction of pathologic complete response to neoadjuvantchemotherapy in breast cancer: amulticenter study[J]. Clin Cancer Res, 2019, 25(12): 3538-3547. doi:10.1158/1078-0432.CCR-18-3190.
[12] Scialpi M, Bianconi F, Cantisani V, et al. Radiomicmachine learning: is it really a useful method for the characterization of prostate cancer?[J]. Radiology, 2019, 291(1): 269-270. doi:10.1148/radiol.2019182940.
[13] Kim JY, Park JE, Jo Y, et al. Incorporating diffusion- and perfusion-weighted MRI into a radiomics model improves diagnostic performance for pseudoprogression in glioblastomapatients[J]. Neuro-oncology, 2019, 21(3): 404-414. doi:10.1093/neuonc/noy133.
[14] Lambin P, Leijenaar RTH, Deist TM, et al. Radiomics: the bridge between medical imaging and personalized medicine[J]. Nat Rev ClinOncol, 2017, 14(12): 749-762. doi:10.1038/nrclinonc.2017.141.
[15] Verma V, Simone CB 2nd, Krishnan S, et al. The rise of radiomics and implications for oncologic management[J]. J Natl Cancer Inst, 2018,110(11):1275-1276. doi:10.1093/jnci/diy037.
[16] Limkin EJ, Sun R, Dercle L, et al. Promises and challenges for the implementation of computational medical imaging(radiomics)in oncology[J]. Ann Oncol, 2017, 28(6): 1191-1206. doi:10.1093/annonc/mdx034.
[17] Gillies RJ, Kinahan PE, Hricak H. Radiomics: images are more than pictures, they are data[J]. Radiology, 2016, 278(2): 563-577. doi:10.1148/radiol.2015151169.
[18] Fetit AE, Novak J, Rodriguez D, et al. Radiomics in paediatricneuro-oncology: amulticentre study on MRI texture analysis[J]. NMR Biomed, 2018, 31(1). doi:10.1002/nbm.3781.
[19] Wu SX, ZhengJJ, Li Y, et al. A radiomicsnomogram for the preoperative prediction of lymph node metastasis in bladder cancer[J]. Clin Cancer Res, 2017, 23(22): 6904-6911. doi:10.1158/1078-0432.CCR-17-1510.
[20] Siegel R, Naishadham D, Jemal A. Cancer statistics, 2012[J]. CA Cancer J Clin, 2012, 62(1): 10-29. doi:10.3322/caac.20138.
[21] Ahn HS, Kim HJ, Welch HG. Korea's thyroid-cancer “epidemic”: screening and overdiagnosis[J]. N Engl J Med, 2014, 371(19): 1765-1767. doi:10.1056/NEJMp1409841.
[22] Ito Y, Miyauchi A, Kihara M, et al. Patient age is significantly related to the progression of papillary microcarcinoma of the thyroid under observation[J]. Thyroid, 2014, 24(1): 27-34. doi:10.1089/thy.2013.0367.
[23] Nam-Goong IS, Kim HY, Gong G, et al. Ultrasonography-guided fine-needle aspiration of thyroid incidentaloma: correlation with pathological findings[J]. Clin Endocrinol(Oxf), 2004, 60(1): 21-28. doi:10.1046/j.1365-2265.2003.01912.x.
[24] Xu Y, Lu L, Lin-Ning LN, et al. Application of radiomics in predicting the malignancy of pulmonary nodules in different sizes[J]. AJR Am J Roentgenol, 2019, 213(6): 1213-1220. doi:10.2214/AJR.19.21490.
[25] Luo WQ, Huang QX, Huang XW, et al. Predicting breast cancer in breast imaging reporting and data system(BI-RADS)ultrasound category 4 or 5 lesions: anomogramcombining radiomics and BI-RADS[J]. Sci Rep, 2019, 9(1): 11921. doi:10.1038/s41598-019-48488-4.
[26] Lew JI, Snyder RA, Sanchez YM, et al. Fine needle aspiration of the thyroid: correlation with final histopathology in a surgical series of 797 patients[J]. J Am CollSurg, 2011, 213(1): 188-194. doi:10.1016/j.jamcollsurg.2011.04.029.
[27] Kiernan CM, Broome JT, Solórzano CC. The Bethesda system for reporting thyroid cytopathology: a single-center experience over 5 years[J]. Ann SurgOncol, 2014, 21(11): 3522-3527. doi:10.1245/s10434-014-3743-1.

多维度评价

Viewed

Full text

Abstract

Cited

Shared

Discussed

基于CT影像组学诺模图预测微小甲状腺结节良恶性

A radiomics nomogram based on computed tomography for predicting benign and malignant thyroid nodules

PDF (PC)

摘要/Abstract

引用本文

使用本文

参考文献

相关文章 7

多维度评价

本文评价

推荐阅读 10

[1]	李思瑶,包宇涵,李昕莹,孙晓菁,曹小丽. 微波消融治疗不同初始体积甲状腺实性结节的疗效研究[J]. 山东大学耳鼻喉眼学报, 2022, 36(2): 58-63.
[2]	李静静,武欣欣,毛宁,郑桂彬,牟亚魁,初同朋,贾传亮,郑海涛,米佳,宋西成. 基于CT影像组学诺模图术前预测甲状腺乳头状癌颈部中央区淋巴结转移的研究[J]. 山东大学耳鼻喉眼学报, 2021, 35(4): 51-59.
[3]	孙晓菁,李昕莹,李思瑶,曹小丽,薛杰,曲妮娜,高莹. 甲状腺良性结节微波消融短期疗效及影响因素分析[J]. 山东大学耳鼻喉眼学报, 2021, 35(4): 60-63.
[4]	潘新良. 加强甲状腺结节及恶性肿瘤的规范治疗[J]. 山东大学耳鼻喉眼学报, 2020, 34(3): 1-12.
[5]	马亚飞,张岩,商蒙蒙,郭鲁,孙霄,柳腾,李杰. 甲状腺TI-RADS 4类结节分值及强回声灶类型与细针穿刺病理的研究[J]. 山东大学耳鼻喉眼学报, 2020, 34(3): 81-87.
[6]	徐书杭, 李春睿, 刘超. 儿童甲状腺癌的规范化诊治[J]. 山东大学耳鼻喉眼学报, 2017, 31(6): 12-15.
[7]	房居高. 强化手术技能和规范诊疗是提高甲状腺癌疗效的根本[J]. 山东大学耳鼻喉眼学报, 2016, 30(2): 1-4.