文献速递胸部CT

基于滤波直方图的纹理分析与基于CALIPER的模式分析作为特发性肺纤维化定量CT技术的头对头比较

Filtration-histogram based texture analysis and CALIPER based pattern analysis as quantitative CT techniques in idiopathic pulmonary fibrosis: head-to-head comparison.
PubMed 文献 · Br J Radiol · 2022-02-22

回顾性分析59例特发性肺纤维化患者的高分辨率CT,比较两种定量CT技术的预后评估性能。基于CALIPER的模式分析中,肺血管百分比是预测不良结局的最显著指标(p=0.009)。基于滤波直方图的纹理分析中,细纹理尺度(SSF2)的标准差是唯一独立生存预测因子(p<0.001),将其与总血管百分比加入GAP分期系统后预后预测改善(p=0.006)。

要点

  • 肺血管百分比是CALIPER模式分析中预测IPF患者不良结局的最显著指标(p=0.009)。
  • 细纹理尺度(SSF2)的标准差是唯一独立生存预测因子(p<0.001)。
  • 将总血管百分比和SSF2标准差加入GAP分期系统可改善预后预测(p=0.006)。

核心结论

  • 基于滤波直方图的纹理分析可作为特发性肺纤维化患者死亡率的独立预测因子,定量CT分析有助于在临床标志物之外对患者进行风险分层。

研究设计与样本

  • 回顾性分析59例特发性肺纤维化患者(年龄70.5±8.8岁)的高分辨率CT扫描,采用两种定量CT方法:基于CALIPER的分析将肺实质分为正常、磨玻璃、网状、透亮、蜂窝和肺血管六种模式;基于滤波直方图的纹理分析在不同空间尺度滤波器下提取纹理特征。采用单变量Kaplan-Meier生存分析评估各定量CT参数预测患者结局和优化标准GAP分期系统的性能,多变量Cox回归分析评估显著单变量预测因子的独立性。

关键影像表现/征象

  • 主要肺实质模式为网状影(16.6%±13.9)。
  • 肺血管百分比是预测患者不良结局的最显著指标(p=0.009)。

诊断标准与关键数值

  • 细纹理尺度(SSF2)下较高的标准差、熵和正像素均值,以及较低的偏度和峰度,是不良结局的最显著预测因子(p<0.001)。
  • 多变量Cox回归分析显示,SSF2标准差是唯一独立生存预测因子(p<0.001)。
  • 将总血管百分比和SSF2标准差加入GAP分期系统后,患者结局预测改善(p=0.006)。

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 assess the prognostic performance of two quantitative CT (qCT) techniques in idiopathic pulmonary fibrosis (IPF) compared to established clinical measures of disease severity (GAP index).

METHODS: Retrospective analysis of high-resolution CT scans for 59 patients (age 70.5 ± 8.8 years) with two qCT methods. Computer-aided lung informatics for pathology evaluation and ratings based analysis classified the lung parenchyma into six different patterns: normal, ground glass, reticulation, hyperlucent, honeycombing and pulmonary vessels. Filtration histogram-based texture analysis extracted texture features: mean intensity, standard deviation (SD), entropy, mean of positive pixels (MPPs), skewness and kurtosis at different spatial scale filters. Univariate Kaplan-Meier survival analysis assessed the different qCT parameters' performance to predict patient outcome and refine the standard GAP staging system. Multivariate cox regression analysis assessed the independence of the significant univariate predictors of patient outcome.

RESULTS: The predominant parenchymal lung pattern was reticulation (16.6% ± 13.9), with pulmonary vessel percentage being the most predictive of worse patient outcome (p = 0.009). Higher SD, entropy and MPP, in addition to lower skewness and kurtosis at fine texture scale (SSF2), were the most significant predictors of worse outcome (p < 0.001). Multivariate cox regression analysis demonstrated that SD (SSF2) was the only independent predictor of survival (p < 0.001). Better patient outcome prediction was achieved after adding total vessel percentage and SD (SSF2) to the GAP staging system (p = 0.006).

CONCLUSION: Filtration-histogram texture analysis can be an independent predictor of patient mortality in IPF patients.

ADVANCES IN KNOWLEDGE: qCT analysis can help in risk stratifying IPF patients in addition to clinical markers.

来源:Br J Radiol,查看原文。版权归原作者所有。

引用

  1. AlDalilah, Ganeshan, Endozo, et al. Filtration-histogram based texture analysis and CALIPER based pattern analysis as quantitative CT techniques in idiopathic pulmonary fibrosis: head-to-head comparison. Br J Radiol. 2022. PMID: 35191759. doi:10.1259/bjr.20210957

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。