MRI影像组学对早期口腔舌鳞状细胞癌隐匿性颈淋巴结转移的预测价值  

Value of MRI radiomics for predicting occult cervical lymph nodes metastases in early-stage oral tongue squamous cell carcinoma

作　　者：任继亮[1] 宋庆博 袁瑛[1] 陶晓峰[1] Ren Jiliang;Song Qingbo;Yuan Ying;Tao Xiaofeng(Department of Radiology,Shanghai Ninth People′s Hospital,Shanghai Jiao Tong University School of Medicine,Shanghai 200011,China)

机构地区：[1]上海交通大学医学院附属第九人民医院放射科,上海200011

出　　处：《中华放射学杂志》2022年第1期30-35,共6页Chinese Journal of Radiology

基　　金：国家自然科学基金(91859202,81771901);上海市卫生健康委员会卫生行业临床研究专项(20194Y0104)。

摘　　要：目的:探讨基于术前常规MRI的影像组学对早期口腔舌鳞状细胞癌(OTSCC)隐匿性颈淋巴结转移的预测价值。方法:回顾性收集2015年1月至2019年12月上海交通大学医学院附属第九人民医院77例早期OTSCC患者(临床分期cT1~2N0M0)的术前MRI数据。所有患者均行原发灶切除及选择性颈淋巴结清扫术,且具有术后淋巴结病理报告。共计168个淋巴结(51个病理转移阳性和117个病理转移阴性)纳入研究,按照2∶1的比例以随机数字表法分为训练集( n=112)和测试集( n=56)。由2名放射医师采用ITK-SNAP软件于T 2WI和增强T 1WI上手动勾画淋巴结的三维感兴趣容积。使用三维slicer软件于每个序列上分别提取1 046个影像组学特征。通过观察者间一致性分析和单因素分析进行数据降维。采用最小绝对收缩和选择算子回归分析选择最佳特征子集并组建影像组学标签。采用Mann-Whitney U检验比较病理阳性与阴性淋巴结间淋巴结大小和影像组学分数的差异。应用受试者操作特征(ROC)曲线评估淋巴结大小、T 2WI影像组学标签及增强T 1WI影像组学标签对隐匿性颈淋巴结转移的预测效能。采用逐步逻辑回归筛选出独立的预测因子。 结果:经过特征筛选,分别有15个和10个最佳特征用于构建T 2WI和增强T 1WI影像组学标签。在训练集和验证集中,病理转移阳性与阴性淋巴结间短径、T 2WI影像组学分数、增强T 1WI影像组学分数差异均有统计学意义( P均<0.05)。三者于训练集的ROC曲线下面积(AUC)分别为0.67、0.83、0.82,于验证集的AUC分别为0.69、0.78、0.70。逐步逻辑回归显示,T 2WI影像组学标签在两数据集中均是隐匿性颈淋巴结转移的独立预测因子(训练集:OR=5.923, P<0.001;验证集:OR=2.534, P=0.012)。 结论:常规MRI影像组学对临床早期OTSCC隐匿性颈淋巴结转移具有一定的预测价值。Objective To explore the value of conventional MRI radiomics for predicting occult cervical lymph nodes(LNs)metastases in early-stage oral tongue squamous cell carcinoma(OTSCC).Methods The preoperative MRI data of 77 cases of early-stage OTSCCs(cT1-2N0M0)in Shanghai Ninth People′s Hospital from January 2015 to December 2019 were retrospectively analyzed.All patients underwent primary lesion resection with selective neck dissection and the pathologic reports of LNs couldal be obtained.In total,168 LNs(51 positive and 117 negative metastases)were enrolled and allocated into training set(n=112)and validation set(n=56)with a ratio of 2∶1 using random number table.The volumes of interest of LNs on T2WI and contrast enhanced T1WI(ceT1WI)were delineated by two doctors using ITK-SNAP software.The 1046 radiomics features of each sequence were extracted using 3D Slicer software.Data dimension reduction was done by inter-observer agreement analysis and univariate analysis.The least absolute shrinkage and selection operator regression analysis were used for selecting optimal feature subsets and constructing radiomics signature for each sequence.Mann-Whitney U test was used to compare the differences of node size and radiomics scores between the LNs with positive and negative metastases.The receiver operating characteristic(ROC)curve was used to explore the performance of LNs size,T2WI radiomics signature and ceT1WI radiomics signature in predicting occult LNs metastases.Stepwise logistic regression was used to determine the independent predictors.Results Fifteen and 10 optimal features were selected to construct radiomics signature for T2WI and ceT1WI respectively.The short diameter,T2WI radiomics signature and ceT1WI radiomics signature showed significant differences between LNs with positive and negative metastases in the both training and validation sets(all P<0.05),with the areas under the ROC curve of 0.67,0.83 and 0.82 in the training set,and 0.69,0.78 and 0.70 in the validation set,respectively.In the stepwise log

关 键 词：癌 鳞状细胞 舌肿瘤 磁共振成像 淋巴结 转移 影像组学 

分 类 号：R445.2[医药卫生—影像医学与核医学] R739.8[医药卫生—诊断学]