|本期目录/Table of Contents|

[1]徐珊珊,毛应凡,董国强,等.CT影像组学预测胰腺神经内分泌肿瘤的病理分级[J].医学研究与战创伤救治(原医学研究生学报),2021,23(05):460-465.[doi:10.3969/j.issn.1672-271X.2021.05.003]
　XU Shan-shan,MAO Ying-fan,DONG Guo-qiang,et al.CT radiomics predicts pathological grade of pancreatic neuroendocrine neoplasm[J].JOURNAL OF MEDICALRESEARCH —COMBAT TRAUMA CARE,2021,23(05):460-465.[doi:10.3969/j.issn.1672-271X.2021.05.003]
点击复制

CT影像组学预测胰腺神经内分泌肿瘤的病理分级()
分享到62.8K

《医学研究与战创伤救治》（原医学研究生学报）[ISSN:1672-271X/CN:32-1713/R]

卷:
第23卷
期数:
2021年05
页码:
460-465
栏目:
临床研究
出版日期:
2021-09-20

文章信息/Info

Title:
CT radiomics predicts pathological grade of pancreatic neuroendocrine neoplasm
作者:
徐珊珊; 毛应凡; 董国强; 祝琼洁; 汤盛楠; 张怡帆; 何健
作者单位：210008南京，南京大学医学院附属鼓楼医院核医学科（徐珊珊、毛应凡、董国强、祝琼洁、汤盛楠、张怡帆、何健）
Author(s):
XU Shan-shan;  MAO Ying-fan;  DONG Guo-qiang;  ZHU Qiong-jie;  TANG Sheng-nan;  ZHANG Yi-fang;  HE Jian
（Department of Nuclear Medicine, Nanjing Drum Tower Hospital, the Affiliated Hospital of Nanjing University Medical School, Nanjing 210008, Jiangsu, China）
关键词:
胰腺肿瘤; 病理分级; 影像组学; X线计算机体层摄影术
Keywords:
pancreatic neoplasm;  pathological grading;  radiomics;  computed tomography
分类号:
R730.44R735.9
DOI:
10.3969/j.issn.1672-271X.2021.05.003
文献标志码:
A
摘要:
目的探讨基于术前X线计算机体层摄影术（CT）检查影像组学对预测胰腺神经内分泌肿瘤的病理分级的价值。方法回顾性分析2017年1月至2020年5月南京大学医学院附属鼓楼医院48例经手术病理证实的胰腺神经内分泌瘤(PanNETs)患者临床资料，收集术前1个月内CT增强图像。分析所有纳入患者的手术前CT增强图像，采用影像组学技术自动分割动脉期和静脉期CT图像上的肿瘤边界并提取肿瘤全容积中的组学特征，使用LASSO回归分析方法进行特征选择以及Logistic回归筛选独立预测因子并建立预测病理分级的影像组学模型。使用受试者工作特征曲线（ROC）及曲线下面积（AUC）评价模型的预测效能。结果分别从患者的动脉期和静脉期提取200个组学特征，筛选出3个最具区分性的特征用于建立影像组学模型。对CT影像学表现进行单因素和多因素分析，筛选出肿瘤边界（OR=79.927,95%CI:3.037~2103.461; P=0.009）和周围器官侵犯（OR=19.001;95%CI:1.964~183.866;P=0.011）为预测因素并建立影像表现模型。综合模型结合了影像组学特征、肿瘤边界和周围器官侵犯，具有更好的预测效能（AUC=0.938），高于影像表现模型（AUC=0.892）和影像组学模型（AUC=0.901）。结论由术前的CT影像表现和影像组学特征建立的综合模型对PanNETs的病理分级具有最佳的预测效能，优于影像组学模型，更好地为临床医师对胰腺神经内分泌肿瘤患者的个体化治疗提供参考意义。
Abstract:
ObjectiveTo explore the value of CT-radiomic model for preoperative prediction of pathologic grade of pancreatic neuroendocrine neoplasm.Methods48 patients with pathologically confirmed PanNETs were included from January 2017 to May 2020, and preoperative CT-enhanced images were collected to establish a radiomics model. The preoperative contrast-enhanced CT images of all patients were analyzed, and the tumor boundaries on arterial phase and venous phase CT images were automatically segmented by imaging techniques, and the histological features of the entire tumor volume were extracted. LASSO regression analysis was used only for feature selection, and Logistic regression was adopted for screening predictors and set up a prediction model. The prediction efficiency of the model was assessed by receiver operating characteristic curve (ROC) and the area under the curve (AUC).ResultsA total of 200 radiomic features were extracted, and the three most distinguishing of which were identified to construct the radiomic model. Tumor boundaries （OR=79.927,95%CI:3.037-2103.461; P=0.009） and the invasion of peripheral organs （OR=19.001;95%CI:1.964-183.866;P=0.011） were selected as independent factors for multifactorial analysis of CT image characteristics.The combined model is mixing radiomics features with invasion of peripheral organs and tumor boundaries had better efficacy of forecast (AUC=0.938), which is higher than that of imaging model (AUC=0.892) and radiomics model (AUC=0.901).ConclusionThe integrated model had the best predictive ability for the pathological grading of PanNETs, which is to provide better reference significance for clinicians in the individualized treatment of patients with pancreatic neuroendocrine neoplasm.

参考文献/References:

[1]Dasari A, Shen C, Halperin D, et al. Trends in the Incidence, Prevalence, and Survival Outcomes in Patients With Neuroendocrine Tumors in the UnitedStates[J]. JAMA Oncol,2017,3(10):1335-1342.
[2]Zhou C, Zhang J, Zheng Y, et al. Pancreatic neuroendocrine tumors: a comprehensive review[J]. Int J Cancer,2012,131(5):1013-1022.
[3]Rindi G, Klimstra DS, Abedi-Ardekani B, et al. A common classification framework for neuroendocrine neoplasms: an InternationalAgency for Research on Cancer (IARC) and World Health Organization (WHO) expert consensus proposal[J]. Mod Pathol,2018,31(12):1770-1786.
[4]Ohmoto A, Rokutan H, Yachida S. Pancreatic Neuroendocrine Neoplasms: Basic Biology, Current TreatmentStrategiesand Prospects for the Future[J]. Int J Mol Sci,2017,18(1):143. doi: 10.3390/ijms18010143.
[5]Cives M, Strosberg JR. Gastroenteropancreatic NeuroendocrineTumors[J]. CA Cancer J Clin,2018,68(6):471-487.
[6]Awe AM, Rendell VR, Lubner MG, et al. Texture Analysis: An Emerging Clinical Tool for Pancreatic Lesions[J]. Pancreas,2020,49(3):301-312.
[7]彭娜，秘建威，赵东强. 超声内镜在胰腺神经内分泌肿瘤诊治中的进展[J]. 中华超声影像学杂志,2020,29(1):87-90.
[8]Hewitt MJ, Mcphail MJ, Possamai L, et al. EUS-guided FNA for diagnosis of solid pancreatic neoplasms: a meta-analysis[J]. Gastrointest Endosc,2012,75(2):319-331.
[9]Gillies RJ, Kinahan PE, Hricak H. Radiomics: Images Are More than Pictures, They AreData[J]. Radiology,2016,278(2):563-577.
[10]宋涛，陆建平，张倩雯. 人工智能医学影像技术在胰腺神经内分泌肿瘤分级中的应用[J]. 第二军医大学学报,2020,41(4):433-438.
[11]Inzani F, Petrone G, Rindi G. The New World Health Organization Classification for Pancreatic Neuroendocrine Neoplasia[J]. Endocrinol Metab Clin North Am,2018,47(3):463-470.
[12]李斯婕，曹凯，陆建平. 胰腺神经内分泌瘤的CT与MRI影像特征[J]. 医学研究生学报,2016,29(8):853-857.
[13]宋茜，王化，孙琳，等. 胰腺神经内分泌肿瘤的多层螺旋CT表现及与不同病理分级的相关性[J]. 中国医学影像学杂志,2017,25(11):807-810.
[14]Kim DW, Kim HJ, Kim KW, et al. Neuroendocrine neoplasms of the pancreas at dynamic enhanced CT: comparison between grade 3 neuroendocrine carcinoma and grade 1/2 neuroendocrine tumour[J]. Eur Radiol,2015,25(5):1375-1383.
[15]Belousova E, Karmazanovsky G, Kriger A, et al. Contrast-enhanced MDCT in patients with pancreatic neuroendocrine tumours: correlation with histological findings and diagnostic performance in differentiation between tumourgrades[J]. Clin Radiol,2017,72(2):150-158.
[16]Gu D, Hu Y, Ding H, et al. CT radiomics may predict the grade of pancreatic neuroendocrine tumors: a multicenter study[J]. Eur Radiol,2019,29(12):6880-6890.
[17]Canellas R, Burk KS, Parakh A, et al. Prediction of Pancreatic Neuroendocrine Tumor Grade Based on CT Features and Texture Analysis[J]. AJR Am J Roentgenol,2018,210(2):341-346.
[18]Auernhammer CJ, Spitzweg C, Angele MK, et al. Advanced neuroendocrine tumours of the small intestine and pancreas: clinical developments, controversies, and future strategies[M]. 2018：404-415.
[19]傅德良，李恒超. 胰腺神经内分泌肿瘤诊治要点[J]. 肝胆外科杂志,2020,28(3):174-178.
[20]许朱定，张海斌，沈翔，等. 胰十二指肠切除术198例疗效分析[J]. 东南国防医药,2013,15(5):436-438.

相似文献/References:

备注/Memo

备注/Memo:
基金项目：国家重点研发计划“变革性技术关键科学问题”重点专项（2020YFA0713800）
更新日期/Last Update: 2021-10-11