文献速递甲状腺与浅表头颈US

超声影像组学特征对细胞学不确定甲状腺结节恶性预测的意义

Implications of US radiomics signature for predicting malignancy in thyroid nodules with indeterminate cytology.
PubMed 文献 · Eur Radiol · 2021-01-18

回顾性纳入154例患者155个细胞学不确定(AUS/FLUS和FN/SFN)甲状腺结节,基于超声图像提取纹理特征构建影像组学评分,联合临床变量建立恶性预测模型;影像组学评分较高与恶性相关(OR=10.923,p<0.001),联合模型AUC 0.839,显著高于仅临床变量模型的0.583。

要点

  • 细胞学不确定甲状腺结节中,超声影像组学评分较高与恶性相关(OR=10.923,p<0.001)。
  • 临床变量联合影像组学评分的模型AUC 0.839,显著高于仅临床变量模型的0.583。
  • 除平均结节大小外,良恶性结节的临床特征无显著差异。

核心结论

  • 定量超声影像组学特征有助于预测细胞学不确定甲状腺结节的恶性。

研究设计与样本

  • 回顾性研究纳入154例患者共155个细胞学不确定甲状腺结节,均为因诊断目的接受初始超声引导下细针穿刺者。
  • 获取每个肿瘤的代表性超声图像,使用Windows 7画图程序绘制覆盖整个结节的方形ROI。
  • 采用MATLAB 2019b实现的内部纹理分析算法提取纹理特征,使用LASSO logistic回归模型选择最具预测价值的特征,并进行十折交叉验证。
  • 采用多变量logistic回归分析构建两个预测模型:一个基于临床变量,另一个基于临床变量联合影像组学评分;以ROC曲线AUC评估两个模型的可预测性。

关键影像表现/征象

  • 除平均结节大小外,良性与恶性结节的临床特征无显著差异。
  • 从单张超声图像生成的730个候选纹理特征中,筛选出15个特征。
  • 利用所选特征构建影像组学评分,并据此建立影像组学特征。

诊断标准与关键数值

  • 多变量logistic回归分析中,较高的影像组学评分与恶性相关(OR=10.923;p<0.001)。
  • 由临床变量联合影像组学评分构成的恶性预测模型AUC为0.839,显著高于仅由临床变量构成的模型AUC 0.583。
  • 细胞学不确定结节包括AUS/FLUS和FN/SFN两类。

局限性

  • 原文未报告局限性。

以上解读依据论文摘要(全文未开放获取或许可不允许翻译转载)。

英文原文(摘要)· 点击展开

OBJECTIVES: The purpose of this study was to evaluate the role of the radiomics score using US images to predict malignancy in AUS/FLUS and FN/SFN nodules.

METHODS: One hundred fifty-five indeterminate thyroid nodules in 154 patients who received initial US-guided FNA for diagnostic purposes were included in this retrospective study. A representative US image of each tumor was acquired, and square ROIs covering the whole nodule were drawn using the Paint program of Windows 7. Texture features were extracted by in-house texture analysis algorithms implemented in MATLAB 2019b. The LASSO logistic regression model was used to choose the most useful predictive features, and ten-fold cross-validation was performed. Two prediction models were constructed using multivariable logistic regression analysis: one based on clinical variables, and the other based on clinical variables with the radiomics score. Predictability of the two models was assessed with the AUC of the ROC curves.

RESULTS: Clinical characteristics did not significantly differ between malignant and benign nodules, except for mean nodule size. Among 730 candidate texture features generated from a single US image, 15 features were selected. Radiomics signatures were constructed with a radiomics score, using selected features. In multivariable logistic regression analysis, higher radiomics score was associated with malignancy (OR = 10.923; p < 0.001). The AUC of the malignancy prediction model composed of clinical variables with the radiomics score was significantly higher than the model composed of clinical variables alone (0.839 vs 0.583).

CONCLUSIONS: Quantitative US radiomics features can help predict malignancy in thyroid nodules with indeterminate cytology.

来源:Eur Radiol,查看原文。版权归原作者所有。

引用

  1. Yoon J, Lee E, Kang SW, et al. Implications of US radiomics signature for predicting malignancy in thyroid nodules with indeterminate cytology. Eur Radiol. 2021. PMID: 33459858. doi:10.1007/s00330-020-07670-3

供执业医师工作参考,不替代临床判断;数值与分级以指南原文为准。