子宫内膜癌:基于MR成像纹理模型的术前风险分层——初步分析
本回顾性研究纳入137例最大径大于1 cm的子宫内膜癌患者,术前1.5-T MR成像提取纹理特征并建立随机森林模型,评估深肌层浸润、淋巴血管间隙浸润及高级别肿瘤。模型对深肌层浸润的AUC为0.84,与专科放射科医师视觉评估的准确率相当,但样本量相对特征数较小可能导致过拟合,需独立数据集验证。
要点
- 基于MR纹理特征的随机森林模型对深肌层浸润的AUC为0.84,与专科放射科医师视觉评估准确率相当。
- 模型对淋巴血管间隙浸润的AUC为0.80,对高级别肿瘤的AUC为0.83。
- 结果需谨慎解读,样本量相对提取特征数较小可能导致模型过拟合,需独立数据集验证。
核心结论
- 纳入MR成像纹理特征的数学模型与深肌层浸润、淋巴血管间隙浸润及高级别肿瘤的存在相关,对最大径大于1 cm的子宫内膜癌深肌层浸润的评估达到与专科放射科医师相当的准确率。
研究设计与样本
- 回顾性研究,纳入137例最大径大于1 cm的子宫内膜癌女性,于2011年1月至2015年12月间子宫切除术前接受1.5-T MR成像。
关键影像表现/征象
- 在T2加权、扩散加权、动态对比增强图像及表观扩散系数图上手动勾画肿瘤感兴趣区进行纹理分析。
- 共提取180个纹理特征,最终筛选出深肌层浸润11个、淋巴血管间隙浸润12个、高级别肿瘤16个特征用于随机森林建模。
诊断标准与关键数值
- 随机森林模型对深肌层浸润:AUC 0.84,敏感度79.3%,特异度82.3%,准确率81.0%,阳性预测值76.7%,阴性预测值84.4%。
- 随机森林模型对淋巴血管间隙浸润:AUC 0.80,敏感度80.9%,特异度72.5%,准确率76.6%,阳性预测值74.3%,阴性预测值79.4%。
- 随机森林模型对高级别肿瘤:AUC 0.83,敏感度81.0%,特异度76.8%,准确率78.1%,阳性预测值60.7%,阴性预测值90.1%。
- 视觉评估对深肌层浸润(阅片者3):敏感度84.5%,特异度82.3%,准确率83.2%,阳性预测值77.7%,阴性预测值87.8%。
临床应用与阅片要点
- 模型对最大径大于1 cm的子宫内膜癌深肌层浸润的评估达到与专科放射科医师视觉评估相当的准确率。
- 作者指出这些初步结果需谨慎解读,须经独立数据集验证后方可用于术前风险分层。
局限性
- 样本量相对提取的特征数较小,可能导致模型过拟合。
- 这些初步结果需谨慎解读,须经独立数据集验证。
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 To evaluate the associations among mathematical modeling with the use of magnetic resonance (MR) imaging-based texture features and deep myometrial invasion (DMI), lymphovascular space invasion (LVSI), and histologic high-grade endometrial carcinoma. Materials and Methods Institutional review board approval was obtained for this retrospective study. This study included 137 women with endometrial carcinomas measuring greater than 1 cm in maximal diameter who underwent 1.5-T MR imaging before hysterectomy between January 2011 and December 2015. Texture analysis was performed with commercial research software with manual delineation of a region of interest around the tumor on MR images (T2-weighted, diffusion-weighted, and dynamic contrast material-enhanced images and apparent diffusion coefficient maps). Areas under the receiver operating characteristic curve and diagnostic performance of random forest models determined by using a subset of the most relevant texture features were estimated and compared with those of independent and blinded visual assessments by three subspecialty radiologists. Results A total of 180 texture features were extracted and ultimately limited to 11 features for DMI, 12 for LVSI, and 16 for high-grade tumor for random forest modeling. With random forest models, areas under the receiver operating characteristic curve, sensitivity, specificity, accuracy, positive predictive value, and negative predictive value were estimated at 0.84, 79.3%, 82.3%, 81.0%, 76.7%, and 84.4% for DMI; 0.80, 80.9%, 72.5%, 76.6%, 74.3%, and 79.4% for LVSI; and 0.83, 81.0%, 76.8%, 78.1%, 60.7%, and 90.1% for high-grade tumor, respectively. Sensitivity, specificity, accuracy, positive predictive value, and negative predictive value of visual assessment for DMI were 84.5%, 82.3%, 83.2%, 77.7%, and 87.8% (reader 3). Conclusion The mathematical models that incorporated MR imaging-based texture features were associated with the presence of DMI, LVSI, and high-grade tumor and achieved equivalent accuracy to that of subspecialty radiologists for assessment of DMI in endometrial cancers larger than 1 cm. However, these preliminary results must be interpreted with caution until they are validated with an independent data set, because the small sample size relative to the number of features extracted may have resulted in overfitting of the models. © RSNA, 2017 Online supplemental material is available for this article.
引用
- Ueno Y, Forghani B, Forghani R, et al. Endometrial Carcinoma: MR Imaging-based Texture Model for Preoperative Risk Stratification-A Preliminary Analysis. Radiology. 2017. PMID: 28493790. doi:10.1148/radiol.2017161950
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。