文献速递乳腺MR

浸润性导管乳腺癌:基于ADC图影像组学术前预测Ki-67指数

Invasive ductal breast cancer: preoperative predict Ki-67 index based on radiomics of ADC maps.
PubMed 文献 · Radiol Med · 2019-11-06

本研究纳入128例经临床病理确诊的浸润性导管乳腺癌患者,其中Ki-67阴性(增殖指数<14%)32例、阳性(≥14%)96例,均术前接受3.0T MRI扩散加权成像。从ADC图提取1029个影像组学特征,经LASSO筛选出11个特征构建逻辑回归模型,训练集AUC为0.75±0.08、准确率0.71,测试集准确率0.72与0.70。作者认为基于ADC图的影像组学模型是预测Ki-67指数的可行手段,三维影像特征可作为术前无创预测Ki-67指数的候选生物标志物。

要点

  • ADC图影像组学模型可术前无创预测浸润性导管乳腺癌Ki-67指数,训练集AUC为0.75±0.08。
  • Ki-67阳性(≥14%)96例、阴性(<14%)32例,模型从1029个特征中筛选11个构建逻辑回归模型。
  • 作者提出ADC图三维影像特征可作为术前预测Ki-67指数的候选生物标志物。

核心结论

  • 基于ADC图的影像组学模型是预测浸润性导管乳腺癌患者Ki-67指数的可行手段。
  • 作者提出ADC图的三维影像特征可作为术前无创预测Ki-67指数的候选生物标志物。

研究设计与样本

  • 本研究为影像组学研究,共纳入128例经临床病理确诊的浸润性导管乳腺癌患者。
  • 按Ki-67增殖指数分组:阴性(<14%)32例,阳性(≥14%)96例。
  • 所有患者术前均于3.0T MRI扫描仪行扩散加权成像(DWI)检查。
  • 从DWI-MRI获得的ADC图中提取影像组学特征。
  • 80%的患者分为训练集用于构建影像组学模型,其余分为测试集评估模型性能。

诊断标准与关键数值

  • 从ADC图提取定量影像特征共1029个,筛选出11个特征构建逻辑回归模型。
  • ADC影像组学模型训练集AUC为0.75±0.08、准确率为0.71。
  • 测试集准确率为0.72与0.70。

临床应用与阅片要点

  • 作者提出ADC图的三维影像特征可作为术前无创预测浸润性导管乳腺癌Ki-67指数的候选生物标志物。

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

PURPOSE: The purpose of this study is to develop a radiomics model for predicting the Ki-67 proliferation index in patients with invasive ductal breast cancer through magnetic resonance imaging (MRI) preoperatively.

MATERIALS AND METHODS: A total of 128 patients who were clinicopathologically diagnosed with invasive ductal breast cancer were recruited. This cohort included 32 negative Ki67 expression (Ki67 proliferation index < 14%) and 96 cases with positive Ki67 expression (Ki67 proliferation index ≥ 14%). All patients had undergone diffusion-weighted imaging (DWI) MRI before surgery on a 3.0T MRI scanner. Radiomics features were extracted from apparent diffusion coefficient (ADC) maps which were obtained by DWI-MRI from patients with invasive ductal breast cancer. 80% of the patients were divided into training set to build radiomics model, and the rest into test set to evaluate its performance. The least absolute shrinkage and selection operator (LASSO) was used to select radiomics features, and then, the logistic regression (LR) model was established using fivefold cross-validation to predict the Ki-67 index. The performance was evaluated by receiver-operating characteristic (ROC) analysis, accuracy, sensitivity and specificity.

RESULTS: Quantitative imaging features (n = 1029) were extracted from ADC maps, and 11 features were selected to construct the LR model. Good identification ability was exhibited by the ADC-based radiomics model, with areas under the ROC (AUC) values of 0.75 ± 0.08, accuracy of 0.71 in training set and 0.72, 0.70 in test set.

CONCLUSIONS: The ADC-based radiomics model is a feasible predictor for the Ki-67 index in patients with invasive ductal breast cancer. Therefore, we proposed that three-dimensional imaging features from ADC maps could be used as candidate biomarker for preoperative prediction the Ki-67 index noninvasively.

来源:Radiol Med,查看原文。版权归原作者所有。

引用

  1. Zhang Y, Zhu Y, Zhang K, et al. Invasive ductal breast cancer: preoperative predict Ki-67 index based on radiomics of ADC maps. Radiol Med. 2019. PMID: 31696388. doi:10.1007/s11547-019-01100-1

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。