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

doi:10.6040/j.issn.1673-3770.0.2020.490

摘要/Abstract

摘要： 目的探讨基于CT影像组学与临床危险因素的诺模图在术前预测甲状腺乳头状癌颈部中央区淋巴结转移中的价值。方法回顾性分析114例PTC患者,收集治疗前的CT及临床资料。以7∶3比例通过完全随机方法将入组患者分为训练集(n=85)和测试集(n=29),从CT平扫期和增强动脉期的图像中提取影像组学特征。在训练集中,使用方差阈值法、最小绝对收缩与选择算子算法筛选出与中央区淋巴结转移密切相关的特征并建立影像组学标签。结合临床危险因素,通过多因素逻辑回归分析建立术前预测PTC颈部中央区淋巴结转移的影像组学诺模图。利用受试者工作特征曲线和校准曲线评估模型的诊断效能,利用决策曲线分析法评估模型的临床应用价值,并在测试集中对模型进行验证。结果从每个患者的CT平扫期与增强CT动脉期图像共提取2 818个影像组学特征,经过特征筛选,共25个与PTC颈部中央区淋巴结转移高度相关的特征,联合影像组学标签与临床独立危险因素(CT报告的淋巴结状态)构建的诺模图,在测试集中的ROC曲线下面积是0.858,高于单独影像组学标签(AUC, 0.769)的效能,同时也高于CT报告的淋巴结状态(AUC, 0.721)的效能。结论影像组学诺模图是一种非侵入性的术前预测工具,它结合了影像组学特征和CT报告的淋巴结状态,对PTC患者的颈部中央区淋巴结转移具有良好的预测效能,具有潜在的临床应用价值。

关键词: 甲状腺乳头状癌, 中央区淋巴结转移, 机器学习, 影像组学, 诺模图

Abstract: Objective To evaluate the value of a nomogram based on CT radiomics and clinical risk factors for the preoperative prediction of lymph node metastases of papillary thyroid carcinomas(PTCs)in the central neck. Methods The cases of 114 patients with PTCs diagnosed and treated surgically at Yantai Yuhuangding hospital were retrospectively analyzed, and the clinical and CT imaging data before treatment were collected. The data of the 114 patients were randomly divided into the training(n=85)and test(n=29)sets using a ratio of 7∶3. Radiological features were extracted from the images during the plain CT scan and the enhanced CT arterial phases. Analysis of variance(ANOVA)and the least absolute shrinkage and selection operator(LASSO)algorithm were used to reduce the dimensionality of the radiomics features in the training set to screen out the features with statistical significance. Combining the clinical risk factors and CT-reported lymph nodes status, the efficacy predictors were screened by multivariate logistic regression, and a radiomics nomogram was established for the preoperative prediction of lymph node metastases of PTCs in the central cervical region. The ROC curve was used to evaluate the diagnostic efficiency of the model, and the model was internally verified, calibrated, and clinically applied. Results A total of 2818 CT radiomics features were extracted from the plain and enhanced CT images of 114 patients. After dimensional reduction, 25 features were highly correlated with lymph node metastases of PTCs in the central neck area. The radiomic nomogram, which incorporated the radiomic signature and CT-reported lymph node status, also showed good calibration and discrimination for the test set(AUC 0.858), which were higher than those of the individual CT image nomogram model for the test set(AUC 0.769)those of the prediction model for the individual lymph node status test set(AUC 0.721). The degree of calibration, internal verification consistency, and clinical value were high for this nomogram. Conclusion The presented radiomics nomogram, a non-invasive preoperative tool that incorporates the radiomic signature and CT-reported lymph node status, showed a favorable predictive accuracy for central lymph node metastases in patients with PTCs.

Key words: Papillary thyroid carcinoma, Central lymph node metastasis, Machine learning, Radiomics, Nomogram

中图分类号:

R739

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.

LI Jingjing, WU Xinxin, MAO Ning, ZHENG Guibin, MU Yakui, CHU Tongpeng, JIA Chuanliang, ZHENG Haitao, MI Jia, SONG Xicheng. CT-based radiomics nomogram for the preoperative prediction of central lymph node metastases of papillary thyroid carcinoma[J]. Journal of Otolaryngology and Ophthalmology of Shandong University, 2021, 35(4): 51-59.

参考文献

[1] Rosenbaum MA, McHenry CR. Contemporary management of papillary carcinoma of the thyroid gland[J]. Expert Rev Anticancer Ther, 2009, 9(3): 317-329. doi:10.1586/14737140.9.3.317.
[2] Hundahl SA, Fleming ID, Fremgen AM, et al. A National Cancer Data Base report on 53, 856 cases of thyroid carcinoma treated in the US, 1985-1995 [J]. Cancer, 1998, 83(12): 2638-2648. doi:10.1002/(sici)1097-0142(19981215)83: 12<2638: aid-cncr31>3.0.co;2-1.
[3] Chen L, Zhu Y, Zheng K, et al. The presence of cancerous nodules in lymph nodes is a novel indicator of distant metastasis and poor survival in patients with papillary thyroid carcinoma[J]. J Cancer Res Clin Oncol. 2017, 143(6): 1035-1042. doi:10.1007/s00432-017-2345-2.
[4] Haddad RI, Kandeel F, Scheri RP. NCCN guidelines index table of contents discussion[J]. 2019:132.
[5] Cabanillas ME, McFadden DG, Durante C. Thyroid cancer[J]. Lancet, 2016, 388(10061): 2783-2795. doi:10.1016/s0140-6736(16)30172-6.
[6] Cady B. Hayes Martin Lecture. Our AMES is true: how an old concept still hits the mark: or, risk group assignment points the arrow to rational therapy selection in differentiated thyroid cancer[J]. Am J Surg, 1997, 174(5): 462-468. doi:10.1016/s0002-9610(97)00162-1.
[7] Shaha AR. Implications of prognostic factors and risk groups in the management of differentiated thyroid cancer[J]. Laryngoscope, 2004, 114(3): 393-402. doi:10.1097/00005537-200403000-00001.
[8] 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. doi:10.6040/j.issn.1673-3770.1.2016.01. 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. doi:10.6040/j.issn.1673-3770.1.2016.01.
[9] Kim E, Park JS, Son KR, et al. Preoperative diagnosis of cervical metastatic lymph nodes in papillary thyroid carcinoma: comparison of ultrasound, computed tomography, and combined ultrasound with computed tomography[J]. Thyroid, 2008, 18(4): 411-418. doi:10.1089/thy.2007.0269.
[10] Jeong HS, Baek CH, Son YI, et al. Integrated 18F-FDG PET/CT for the initial evaluation of cervical node level of patients with papillary thyroid carcinoma: comparison with ultrasound and contrast-enhanced CT[J]. Clin Endocrinol(Oxf), 2006, 65(3): 402-407. doi:10.1111/j.1365-2265.2006.02612.x.
[11] Choi JS, Kim J, Kwak JY, et al. Preoperative staging of papillary thyroid carcinoma: comparison of ultrasound imaging and CT[J]. AJR Am J Roentgenol, 2009, 193(3): 871-878. doi:10.2214/ajr.09.2386.
[12] Roh JL, Park JY, Kim JM, et al. Use of preoperative ultrasonography as guidance for neck dissection in patients with papillary thyroid carcinoma[J]. J Surg Oncol, 2009, 99(1): 28-31. doi:10.1002/jso.21164.
[13] Lambin P, Rios-Velazquez E, Leijenaar R, et al. Radiomics: extracting more information from medical images using advanced feature analysis[J]. European Journal of Cancer. 2012, 48(4): 441-446. doi: 10.1016/j.ejca.2011.11.036.
[14] 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.
[15] Lee G, Lee HY, Park H, et al. Radiomics and its emerging role in lung cancer research, imaging biomarkers and clinical management: State of the art[J]. European Journal of Radiology. 2017, 86: 297-307. doi: 10.1016/j.ejrad.2016.09.005.
[16] Kotrotsou A, Zinn PO, Colen RR. Radiomics in brain tumors: an emerging technique for characterization of tumor environment[J]. Magn Reson Imaging Clin N Am, 2016, 24(4): 719-729. doi:10.1016/j.mric.2016.06.006.
[17] 武欣欣, 李静静, 毛宁, 等. 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. doi: 10.6040/j.issn.1673-3770.1.2020.028. WU Xinxin, LI Jingjing, MAO Ning, et al. 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. doi: 10.6040/j.issn.1673-3770.1.2020.028.
[18] Liu X, Ouyang D, Li H, et al. Papillary thyroid cancer: dual-energy spectral CT quantitative parameters for preoperative diagnosis of metastasis to the cervical lymph nodes[J]. Radiology, 2015, 275(1): 167-176. doi:10.1148/radiol.14140481.
[19] Randolph GW, Duh Q-Y, Heller KS, et al. The prognostic significance of nodal metastases from papillary thyroid carcinoma can be stratified based on the size and number of metastatic lymph nodes, as Well as the presence of extranodal extension[J]. Thyroid, 2012, 22(11): 1144-1152. doi:10.1089/thy.2012.0043.
[20] Zhao Y, Li X, Li L, et al. Preliminary study on the diagnostic value of single-source dual-energy CT in diagnosing cervical lymph node metastasis of thyroid carcinoma[J]. Journal of Thoracic Disease, 2017, 9(11): 4758-4766. doi: org/10.21037/jtd.2017.09.151.
[21] Mazzaferri EL, Kloos RT. Current approaches to primary therapy for papillary and follicular thyroid cancer[J]. J Clin Endocrinol Metab, 2001, 86(4): 1447-1463. doi:10.1210/jcem.86.4.7407.
[22] Gross ND, Weissman JL, Talbot JM, et al. MRI detection of cervical metastasis from differentiated thyroid carcinoma[J]. Laryngoscope, 2001, 111(11 pt 1): 1905-1909. doi:10.1097/00005537-200111000-00006.
[23] Patel NU, McKinney K, Kreidler SM, et al. Ultrasound-based clinical prediction rule model for detecting papillary thyroid cancer in cervical lymph nodes: a pilot study[J]. J Clin Ultrasound, 2016, 44(3): 143-151.
[24] Nam SY, Shin JH, Han B-K, et al. Preoperative ultrasonographic features of papillary thyroid carcinoma predict biological behavior[J]. The Journal of Clinical Endocrinology & Metabolism, 2013, 98(4): 1476-1482. doi:10.1210/jc.2012-4072.

多维度评价

Viewed

Full text

Abstract

Cited

Shared

Discussed