文献速递腹部泌尿生殖MR

动态对比增强MRI参数图的统计聚类及关联决策树模型用于T1b实性透明细胞肾细胞癌无创肿瘤分级

Statistical clustering of parametric maps from dynamic contrast enhanced MRI and an associated decision tree model for non-invasive tumour grading of T1b solid clear cell renal cell carcinoma.
PubMed 文献 · Eur Radiol · 2017-07-05

这项前瞻性研究纳入18例实性T1b透明细胞肾细胞癌患者,术前行动态对比增强MRI,用模糊C均值算法对Ktrans、Kep和iAUC参数图进行统计聚类,将肿瘤分割为低、中、高活性区,比较各区百分比及肿瘤大小与病理分级的关系,并构建决策树模型。结果高级别肿瘤的高活性区百分比较高(p=0.0154),该特征被决策树模型选中,诊断准确率78%、敏感度86%、特异度73%、阳性预测值67%、阴性预测值89%。

要点

  • T1b透明细胞肾细胞癌中肿瘤大小与病理分级不相关。
  • 高活性区百分比较高与高级别组织学相关(p=0.0154),是决策树模型唯一选中的特征。
  • 决策树模型鉴别高/低级别T1b透明细胞肾细胞癌的准确率78%、敏感度86%、特异度73%。

核心结论

  • 模糊C均值聚类整合多个DCE-MRI衍生参数图,识别具有独特药代动力学特征的肿瘤区域,基于高活性区百分比构建的决策树模型可用于预测T1b透明细胞肾细胞癌的病理分级。

研究设计与样本

  • 前瞻性、经机构审查委员会批准、符合《健康保险可携性与责任法案》的研究,纳入18例实性T1b透明细胞肾细胞癌患者,术前行动态对比增强MRI,以组织病理学分级为参考标准。

关键影像表现/征象

  • 高活性区百分比较高与高级别组织学相关(p=0.0154)。
  • 肿瘤大小与肿瘤分级不相关。
  • 通过模糊C均值算法将每个肿瘤分割为低、中、高活性区三个区域。

诊断标准与关键数值

  • 决策树模型以高活性区百分比为唯一选中参数,诊断性能为准确率78%、敏感度86%、特异度73%、阳性预测值67%、阴性预测值89%。

临床应用与阅片要点

  • 作者提出一种超越肿瘤大小的决策树模型,用于预测T1b透明细胞肾细胞癌的肿瘤分级。
  • 模糊C均值聚类可分析DCE-MRI参数所反映的肿瘤异质性。

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: To apply a statistical clustering algorithm to combine information from dynamic contrast-enhanced (DCE) magnetic resonance imaging (MRI) into a single tumour map to distinguish high-grade from low-grade T1b clear cell renal cell carcinoma (ccRCC).

METHODS: This prospective, Institutional Review Board -approved, Health Insurance Portability and Accountability Act -compliant study included 18 patients with solid T1b ccRCC who underwent pre-surgical DCE MRI. After statistical clustering of the parametric maps of the transfer constant between the intravascular and extravascular space (K trans ), rate constant (K ep ) and initial area under the concentration curve (iAUC) with a fuzzy c-means (FCM) algorithm, each tumour was segmented into three regions (low/medium/high active areas). Percentages of each region and tumour size were compared to tumour grade at histopathology. A decision-tree model was constructed to select the best parameter(s) to predict high-grade ccRCC.

RESULTS: Seven high-grade and 11 low-grade T1b ccRCCs were included. High-grade histology was associated with higher percent high active areas (p = 0.0154) and this was the only feature selected by the decision tree model, which had a diagnostic performance of 78% accuracy, 86% sensitivity, 73% specificity, 67% positive predictive value and 89% negative predictive value.

CONCLUSIONS: The FCM integrates multiple DCE-derived parameter maps and identifies tumour regions with unique pharmacokinetic characteristics. Using this approach, a decision tree model using criteria beyond size to predict tumour grade in T1b ccRCCs is proposed.

KEY POINTS: • Tumour size did not correlate with tumour grade in T1b ccRCC. • Tumour heterogeneity can be analysed using statistical clustering via DCE-MRI parameters. • High-grade ccRCC has a larger percentage of high active area than low-grade ccRCCs. • A decision-tree model offers a simple way to differentiate high/low-grade ccRCCs.

来源:Eur Radiol,查看原文。版权归原作者所有。

引用

  1. Xi Y, Yuan Q, Zhang Y, et al. Statistical clustering of parametric maps from dynamic contrast enhanced MRI and an associated decision tree model for non-invasive tumour grading of T1b solid clear cell renal cell carcinoma. Eur Radiol. 2017. PMID: 28681074. doi:10.1007/s00330-017-4925-6

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。