文献速递泌尿生殖骨肌MR

基于影像组学列线图预测初诊前列腺癌患者骨转移

A Radiomics nomogram for predicting bone metastasis in newly diagnosed prostate cancer patients.
PubMed 文献 · Eur J Radiol · 2020-04-19

研究纳入116例初诊前列腺癌患者(训练组81例、验证组35例),基于弥散加权、轴位T2加权脂肪抑制和动态对比增强T1加权MRI提取影像组学特征,结合独立临床危险因素构建列线图。列线图在训练组AUC为0.93(95%CI 0.86–0.99)、验证组AUC为0.92(95%CI 0.84–0.99),决策曲线分析显示其具有临床使用价值。

要点

  • 基于多参数MRI的12个影像组学特征与骨状态显著相关,训练组和验证组P均<0.001。
  • 影像组学列线图结合影像组学特征与独立临床危险因素,训练组AUC 0.93(95%CI 0.86–0.99)。
  • 验证组AUC 0.92(95%CI 0.84–0.99),决策曲线分析显示模型具有临床使用价值。

诊断标准与关键数值

  • 由12个所选特征构成的影像组学特征与骨状态显著相关,训练组和验证组P均<0.001。
  • 影像组学列线图在训练组AUC为0.93(95%CI 0.86–0.99),在验证组AUC为0.92(95%CI 0.84–0.99)。
  • 决策曲线分析显示影像组学模型具有临床使用价值。

临床应用与阅片要点

  • 作者认为,结合多参数MRI影像组学特征和临床危险因素的列线图可方便地用于促进初诊前列腺癌患者骨转移的个体化预测。

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: To establish and validate a radiomics nomogram for predicting bone metastasis (BM) in patients with newly diagnosed prostate cancer (PCa).

METHOD: One-hundred and sixteen patients (training cohort: n = 81; validation cohort: n = 35) who underwent prostate MR imaging and confirmed by pathology with newly diagnosed PCa from January 2014 to January 2019 were enrolled. Radiomic features were extracted from diffusion-weighted, axial T2-weighted fat suppression, and dynamic contrast-enhanced T1-weighted MRI of each patient. Dimension reduction, feature selection, and radiomics feature construction were performed using the least absolute shrinkage and selection operator (LASSO) regression. Combined with independent clinical risk factors, a multivariate logistic regression model was used to establish a radiomics nomogram. Nomogram calibration and discrimination were evaluated in training cohort and verified in the validation cohort. Finally, the clinical usefulness of the nomogram was estimated through decision curve analysis (DCA).

RESULTS: Radiomics signature consisting of 12 selected features was significantly correlated with bone status (P < 0.001 for both training and validation sets). The radiomics nomogram combined a radiomics signature from multiparametric MR images with independent clinic risk factors. The model showed good discrimination and calibration in the training cohort (AUC 0.93, 95% CI, 0.86 to 0.99) and the validation cohort (AUC 0.92, 95% CI, 0.84 to 0.99). DCA also demonstrated the clinical use of the radiomics model.

CONCLUSION: The radiomics nomogram, which incorporates the multiparametric MRI-based radiomics signature and clinical risk factors, can be conveniently used to promote individualized prediction of BM in patients with newly diagnosed PCa.

来源:Eur J Radiol,查看原文。版权归原作者所有。

引用

  1. Zhang W, Mao N, Wang Y, et al. A Radiomics nomogram for predicting bone metastasis in newly diagnosed prostate cancer patients. Eur J Radiol. 2020. PMID: 32371181. doi:10.1016/j.ejrad.2020.109020

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。