文献速递胸部CT

基于形态学变化动态模式的胸部CT肺结节影像组学检测方法

A radiomics approach for lung nodule detection in thoracic CT images based on the dynamic patterns of morphological variation.
PubMed 文献 · Eur Radiol · 2022-01-12

研究提出并评估一组称为形态学动态特征的影像组学特征用于肺结节检测,该特征基于形态学变化的动态模式且无需精确病灶分割;在UH数据集上CAD-MD算法的AFROC曲线AUC在AL1和AL2分别为0.777和0.851,N-Net分别为0.478和0.472;在LIDC数据集上CAD-MD在AL1-AL4的敏感度分别为87.6%、89.2%、92.2%和95.0%(4 FPs/scan)。

要点

  • 形态学动态影像组学特征基于不同阈值下的形态变化模式,无需精确分割病灶。
  • 在UH数据集上,CAD-MD算法AFROC曲线AUC在AL1和AL2分别为0.777和0.851,高于N-Net的0.478和0.472。
  • 在LIDC数据集上,CAD-MD算法在AL1-AL4的敏感度分别为87.6%、89.2%、92.2%和95.0%,均为4 FPs/scan。

核心结论

  • 形态学动态影像组学特征可能作为肺结节检测的有效影像组学特征集。

研究设计与样本

  • 研究涉及大学医院(UH)和LIDC两个数据集,分别包含72次CT扫描(360个结节)和888次CT扫描(2230个结节),每个结节由多位放射科医生标注。

诊断标准与关键数值

  • 以至少k位放射科医生识别的结节类别记为ALk。
  • 在UH数据集AL1上,CAD-MD算法AFROC曲线AUC为0.777,N-Net为0.478。
  • 在UH数据集AL2上,CAD-MD算法AFROC曲线AUC为0.851,N-Net为0.472。
  • 在UH数据集AL1上,CAD-MD算法敏感度为84.4%(2.98 FPs/scan),N-Net为74.4%(3.90 FPs/scan)。
  • 在UH数据集AL2上,CAD-MD算法敏感度为91.4%(3.69 FPs/scan),N-Net为80.7%(4.49 FPs/scan)。

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 propose and evaluate a set of radiomic features, called morphological dynamics features, for pulmonary nodule detection, which were rooted in the dynamic patterns of morphological variation and needless precise lesion segmentation.

MATERIALS AND METHODS: Two datasets were involved, namely, university hospital (UH) and LIDC datasets, comprising 72 CT scans (360 nodules) and 888 CT scans (2230 nodules), respectively. Each nodule was annotated by multiple radiologists. Denoted the category of nodules identified by at least k radiologists as ALk. A nodule detection algorithm, called CAD-MD algorithm, was proposed based on the morphological dynamics radiomic features, characterizing a lesion by ten sets of the same features with different values extracted from ten different thresholding results. Each nodule candidate was classified by a two-level classifier, including ten decision trees and a random forest, respectively. The CAD-MD algorithm was compared with a deep learning approach, the N-Net, using the UH dataset.

RESULTS: On the AL1 and AL2 of the UH dataset, the AUC of the AFROC curves were 0.777 and 0.851 for the CAD-MD algorithm and 0.478 and 0.472 for the N-Net, respectively. The CAD-MD algorithm achieved the sensitivities of 84.4% and 91.4% with 2.98 and 3.69 FPs/scan and the N-Net 74.4% and 80.7% with 3.90 and 4.49 FPs/scan, respectively. On the LIDC dataset, the CAD-MD algorithm attained the sensitivities of 87.6%, 89.2%, 92.2%, and 95.0% with 4 FPs/scan for AL1-AL4, respectively.

CONCLUSION: The morphological dynamics radiomic features might serve as an effective set of radiomic features for lung nodule detection.

KEY POINTS: • Texture features varied with such CT system settings as reconstruction kernels of CT images, CT scanner models, and parameter settings, and so on. • Shape and first-order statistics were shown to be the most robust features against variation in CT imaging parameters. • The morphological dynamics radiomic features, which mainly characterized the dynamic patterns of morphological variation, were shown to be effective for lung nodule detection.

来源:Eur Radiol,查看原文。版权归原作者所有。

引用

  1. Lin, Chang, Huang, et al. A radiomics approach for lung nodule detection in thoracic CT images based on the dynamic patterns of morphological variation. Eur Radiol. 2022. PMID: 35020016. doi:10.1007/s00330-021-08456-x

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。