收稿日期: 2021-01-18
网络出版日期: 2021-08-03
Value of CT radiomic features in preoperative prediction of cervical lymph node metastasis in patients with papillary thyroid carcinoma
Received date: 2021-01-18
Online published: 2021-08-03
目的·探讨甲状腺乳头状癌（papillary thyroid carcinoma，PTC）CT增强检查的平扫期、动脉期和静脉期图像的影像组学特征对术前预测颈部淋巴结转移（cervical lymph node metastasis，CLNM）的价值。方法·收集2017年1月—2020年6月在上海市金山区亭林医院行甲状腺外科治疗的197例PTC患者的CT图像，筛选出满足要求的512帧（包括193帧平扫期、131帧动脉期、188帧静脉期），选择图像中显示病灶最大长径的层面进行影像组学研究。根据CLNM的状态，用全部512帧CT图像优选RandomForestClassifier的最佳参数；用具有全部3期CT图像的124例患者资料分别构建3期的随机森林（random forest，RF）分类模型，模型的评价标准为受试者操作特征曲线（receiver operator characteristic curve，ROC curve）的最大平均曲线下面积（area under the curve，AUC）和准确度。结果·RF分类模型显示平扫期、动脉期和静脉期的ROC曲线最大平均AUC分别为0.843、0.775、0.783，相应准确度分别为0.767、0.695、0.726，平扫期的最大平均AUC值明显高于动脉期及静脉期（均P=0.000）。结论·PTC的CT 3期影像组学特征可以较准确地预测CLNM，其中平扫期图像特征预测性能较高。
何俊林 , 路青 , 徐昕 , 胡曙东 . CT影像组学特征预测甲状腺乳头状癌颈部淋巴结转移的价值研究[J]. 上海交通大学学报（医学版）, 2021 , 41(9) : 1233 -1239 . DOI: 10.3969/j.issn.1674-8115.2021.09.015
·To explore the value of radiomic features of pre-contrast phase,arterial phase and venous phase in predicting preoperatively cervical lymph node metastasis (CLNM) in patients with papillary thyroid carcinoma (PTC) in multi-phase images of contrast-enhanced CT scan.
·CT images of 197 PTC patients who underwent thyroid surgery in Tinglin Hospital of Jinshan District of Shanghai from January 2017 to June 2020 were collected. 512 frames that meet the research requirement, consisting of 193 pre-contrast phases,131 arterial phases and 188 venous phases, were selected from the 3 phases of CT images 197 patients, and the CT images showing the largest length to diameter of PTC lesion were chosen for the radiomic study in each one of the 512 frames. The optimal parameters of RandomForestClassifier were selected with all the 512 frames of CT images and random forest (RF) classification model for the prediction of CLNM was established based on CT images with all the 3 phases of 124 patients who had concurrent CT images of pre-contrast phase, arterial phase and venous phase. The predictive performance of the models was estimated by area under the curve (AUC) of receiver operator characteristic curve (ROC curve) analysis.
·The RF classification models showed that the maximal average AUC of ROCs of pre-contrast phase, arterial phase and venous phase were 0.843, 0.775 and 0.783, and the corresponding predictive accuracy were 0.767, 0.695 and 0.726, respectively. Compared with the arterial phase and venous phase, the radiomic features extracted from pre-contrast phase of CT images show better performance to predict CLNM (both P=0.000).
·Radiomic features extracted from pre-contrast phase, arterial phase and venous phase of CT images can all feasibly be used to predict CLNM in patients with PTC, and radiomic features from pre-contrast phase of CT images show better performance.
| 1 | Siegel RL, Miller KD, Jemal A. Cancer statistics, 2019[J]. CA Cancer J Clin, 2019, 69(1): 7-34. |
| 2 | Vaccarella S, Franceschi S, Bray F, et al. Worldwide thyroid-cancer epidemic? The increasing impact of overdiagnosis[J]. N Engl J Med, 2016, 375(7): 614-617. |
| 3 | Londero SC, Krogdahl A, Bastholt L, et al. Papillary thyroid carcinoma in Denmark, 1996?2008: outcome and evaluation of established prognostic scoring systems in a prospective national cohort[J]. Thyroid, 2015, 25(1): 78-84. |
| 4 | Lee YK, Kim D, Shin DY, et al. The prognosis of papillary thyroid cancer with initial distant metastasis is strongly associated with extensive extrathyroidal extension: a retrospective cohort study[J]. Ann Surg Oncol, 2019, 26(7): 2200-2209. |
| 5 | Mulla M, Schulte KM. Central cervical lymph node metastases in papillary thyroid cancer: a systematic review of imaging-guided and prophylactic removal of the central compartment[J]. Clin Endocrinol (Oxf), 2012, 76(1): 131-136. |
| 6 | Hall CM, Snyder SK, Lairmore TC. Central lymph node dissection improves lymph node clearance in papillary thyroid cancer patients with lateral neck metastases, even after prior total thyroidectomy[J]. Am Surg, 2018, 84(4): 531-536. |
| 7 | Mulla M, Schulte KM. The accuracy of ultrasonography in the preoperative diagnosis of cervical lymph node (LN) metastasis in patients with papillary thyroid carcinoma: a meta-analysis[J]. Eur J Radiol, 2012, 81(8): 1965. |
| 8 | Suh CH, Baek JH, Choi YJ, et al. Performance of CT in the preoperative diagnosis of cervical lymph node metastasis in patients with papillary thyroid cancer: a systematic review and meta-analysis[J]. AJNR Am J Neuroradiol, 2017, 38(1): 154-161. |
| 9 | Gross ND, Weissman JL, Talbot JM, et al. MRI detection of cervical metastasis from differentiated thyroid carcinoma[J]. Laryngoscope, 2001, 111(11Pt 1): 1905-1909. |
| 10 | Chen QH, Raghavan P, Mukherjee S, et al. Accuracy of MRI for the diagnosis of metastatic cervical lymphadenopathy in patients with thyroid cancer[J]. La Radiol Med, 2015, 120(10): 959-966. |
| 11 | Paek SH, Yi KH, Kim SJ, et al. Feasibility of sentinel lymph node dissection using Tc-99m phytate in papillary thyroid carcinoma[J]. Ann Surg Treat Res, 2017, 93(5): 240-245. |
| 12 | Suh CH, Choi YJ, Lee JJ, et al. Comparison of core-needle biopsy and fine-needle aspiration for evaluating thyroid incidentalomas detected by 18F-fluorodeoxyglucose positron emission tomography/computed tomography: a propensity score analysis[J]. Thyroid, 2017, 27(10): 1258-1266. |
| 13 | 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. |
| 14 | van Griethuysen JJM, Fedorov A, Parmar C, et al. Computational radiomics system to decode the radiographic phenotype[J]. Cancer Res, 2017, 77(21): e104-e107. |
| 15 | Barry WT, Kernagis DN, Dressman HK, et al. Intratumor heterogeneity and precision of microarray-based predictors of breast cancer biology and clinical outcome[J]. J Clin Oncol, 2010, 28(13): 2198-2206. |
| 16 | Gambardella C, Patrone R, di Capua F, et al. The role of prophylactic central compartment lymph node dissection in elderly patients with differentiated thyroid cancer: a multicentric study[J]. BMC Surg, 2019, 18(): 110. |
| 17 | Lu W, Zhong LZ, Dong D, et al. Radiomic analysis for preoperative prediction of cervical lymph node metastasis in patients with papillary thyroid carcinoma[J]. Eur J Radiol, 2019, 118: 231-238. |
| 18 | Liu TT, Zhou SC, Yu JH, et al. Prediction of lymph node metastasis in patients with papillary thyroid carcinoma: a radiomics method based on preoperative ultrasound images[J]. Technol Cancer Res Treat, 2019, 18: 1533033819831713. |
| 19 | O′Connor JP, Rose CJ, Waterton JC, et al. Imaging intratumor heterogeneity: role in therapy response, resistance, and clinical outcome[J]. Clin Cancer Res, 2015, 21(2): 249-257. |
| 20 | 徐天伟. 基于灰度共生矩阵的医学PET图像纹理分析研究[J]. 电脑知识与技术, 2017, 13(5): 219-220. |
| 21 | 颜智敏, 冯智超, 曹鹏, 等. 多层螺旋CT图像纹理分析对直肠癌转移性淋巴结的诊断价值[J]. 中华放射学杂志, 2017, 51(6): 432-436. |
| 22 | El Naqa I, Grigsby P, Apte A, et al. Exploring feature-based approaches in PET images for predicting cancer treatment outcomes[J]. Pattern Recognit, 2009, 42(6): 1162-1171. |
| 23 | 梁子超, 李智炜, 赖铿, 等. 10折交叉验证用于预测模型泛化能力评价及其R软件实现[J]. 中国医院统计, 2020, 27(4): 289-292. |
| 24 | Rodríguez JD, Pérez A, Lozano JA. Sensitivity analysis of kappa-fold cross validation in prediction error estimation[J]. IEEE Trans Pattern Anal Mach Intell, 2010, 32(3): 569-575. |
| 25 | Johnstone IM, Titterington DM. Statistical challenges of high-dimensional data[J]. Philos Trans A Math Phys Eng Sci, 2009, 367(1906): 4237-4253. |
| 26 | Clarke R, Ressom HW, Wang A, et al. The properties of high-dimensional data spaces: implications for exploring gene and protein expression data[J]. Nat Rev Cancer, 2008, 8(1): 37-49. |
/
| 〈 |
|
〉 |