文献速递泌尿生殖腹部CT

分割边缘对基于机器学习的高维定量CT纹理分析的影响:肾透明细胞癌的可重复性研究

Influence of segmentation margin on machine learning-based high-dimensional quantitative CT texture analysis: a reproducibility study on renal clear cell carcinomas.
PubMed 文献 · Eur Radiol · 2019-02-12

该回顾性研究纳入47例肾透明细胞癌患者,由两位放射科医生分别采用轮廓聚焦和边缘内缩2mm两种分割方式提取CT纹理特征,评估分割边缘对特征可重复性、选择和分类各步骤的影响。结果显示边缘内缩2mm分割获得更多具有极佳可重复性的特征(93.2% vs 86.2%),但轮廓聚焦分割的机器学习模型分类性能更好(AUC 0.865-0.984 vs 0.745-0.887),提示分割边缘的轻微变化即可影响机器学习纹理分析各步骤。

要点

  • 分割边缘内缩2mm较轮廓聚焦分割获得更多具有极佳可重复性的纹理特征(93.2% vs 86.2%)。
  • 轮廓聚焦分割的机器学习模型区分核分级的AUC为0.865-0.984,优于边缘内缩2mm分割的0.745-0.887。
  • 基于机器学习的定量CT纹理分析各步骤对2mm的分割边缘变化均敏感。

核心结论

  • 基于机器学习的高维定量CT纹理分析各步骤均易受分割边缘2mm微小变化的影响;尽管轮廓聚焦分割产生的具有极佳可重复性的特征较少,但其机器学习模型区分核分级的分类性能更好。

研究设计与样本

  • 回顾性研究,纳入来自公共数据库的47例肾透明细胞癌患者,由两位放射科医生对每个肿瘤进行轮廓聚焦和边缘内缩2mm两种分割,从原始、滤波和变换CT图像提取纹理特征,采用基于相关的算法进行特征选择,机器学习分类器为k近邻,分类时使用和不使用合成少数类过采样技术,参考标准为核分级(低级别 vs 高级别)。

诊断标准与关键数值

  • 以核分级(低级别 vs 高级别)为参考标准;边缘内缩2mm分割获得772/828(93.2%)个具有极佳可重复性(ICC≥0.9)的纹理特征,轮廓聚焦分割获得714/828(86.2%),p<0.0001;轮廓聚焦分割的机器学习模型AUC范围为0.865-0.984,边缘内缩2mm分割的AUC范围为0.745-0.887,p<0.05。

临床应用与阅片要点

  • 原文未据此给出推荐。

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

OBJECTIVE: To determine the possible influence of segmentation margin on each step (feature reproducibility, selection, and classification) of the machine learning (ML)-based high-dimensional quantitative computed tomography (CT) texture analysis (qCT-TA) of renal clear cell carcinomas (RcCCs).

MATERIALS AND METHODS: For this retrospective study, 47 patients with RcCC were included from a public database. Two segmentations were obtained by two radiologists for each tumour: (i) contour-focused and (ii) margin shrinkage of 2 mm. Texture features were extracted from original, filtered, and transformed CT images. Feature selection was done using a correlation-based algorithm. The ML classifier was k-nearest neighbours. Classifications were performed with and without using synthetic minority over-sampling technique. Reference standard was nuclear grade (low versus high). Intraclass correlation coefficient (ICC), Pearson's correlation coefficient, Wilcoxon signed-ranks test, and McNemar's test were used in the analysis.

RESULTS: The segmentation with margin shrinkage of 2 mm (772 of 828; 93.2%) yielded more texture features with excellent reproducibility (ICC ≥ 0.9) than contour-focused segmentation (714 of 828; 86.2%), p < 0.0001. The feature selection algorithms resulted in different feature subsets for two segmentation datasets with only one common feature. All ML-based models based on contour-focused segmentation (area under the curve [AUC] range, 0.865-0.984) performed better than those with margin shrinkage of 2 mm (AUC range, 0.745-0.887), p < 0.05.

CONCLUSIONS: Each step of the ML-based high-dimensional qCT-TA was susceptible to a slight change of 2 mm in segmentation margin. Despite yielding fewer features with excellent reproducibility, use of the contour-focused segmentation provided better classification performance for distinguishing nuclear grade.

KEY POINTS: • Each step of a machine learning (ML)-based high-dimensional quantitative computed tomography texture analysis (qCT-TA) is sensitive to even a slight change of 2 mm in segmentation margin. • Despite yielding fewer texture features with excellent reproducibility, performing the segmentation focusing on the outermost boundary of the tumours provides better classification performance in ML-based qCT-TA of renal clear cell carcinomas for distinguishing nuclear grade. • Findings of an ML-based high-dimensional qCT-TA may not be reproducible in clinical practice even using the same feature selection algorithm and ML classifier unless the possible influence of the segmentation margin is considered.

来源:Eur Radiol,查看原文。版权归原作者所有。

引用

  1. Kocak B, Ates E, Durmaz ES, et al. Influence of segmentation margin on machine learning-based high-dimensional quantitative CT texture analysis: a reproducibility study on renal clear cell carcinomas. Eur Radiol. 2019. PMID: 30747300. doi:10.1007/s00330-019-6003-8

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。