CT重建算法对影像组学模型诊断性能的影响:针对肺亚实性结节的基于任务的方法
本研究回顾性纳入60例患者共69个肺亚实性结节,术前CT分别用滤波反投影(FBP)和基于模型的迭代重建(MBIR)重建,提取860个影像组学特征并构建支持向量机(SVM)与集成模型鉴别浸润性肺腺癌(IPA)。随着数据集中MBIR重建结节比例增加,模型ROC AUC和诊断准确率显著下降,关系符合三次函数(SVM的R²=0.993和0.926;集成模型的R²=0.993和0.975;p<0.001),AUC变异幅度均为0.39。结论认为将MBIR重建的CT纳入影像组学建模可显著降低鉴别IPA的诊断性能。
要点
- MBIR重建结节比例增加会显著降低影像组学模型鉴别浸润性肺腺癌的AUC和准确率。
- SVM与集成模型的AUC随MBIR比例变化幅度均为0.39。
- 建模时应关注CT重建算法异质性对影像组学诊断性能的影响。
核心结论
- 将MBIR重建的CT扫描纳入影像组学建模可显著降低鉴别浸润性肺腺癌的诊断性能。
研究设计与样本
- 回顾性研究纳入60例患者(23男37女,平均年龄61.4岁)的69个肺亚实性结节(54个部分实性、15个纯磨玻璃结节),术前CT均行FBP和MBIR重建,从整个结节体积提取860个影像组学特征,制备70个MBIR特征比例递增(从0/69到69/69)的重采样结节数据集,经邻域成分分析筛选特征后以支持向量机(SVM)和集成模型作为分类器鉴别浸润性肺腺癌。
诊断标准与关键数值
- SVM模型ROC AUC和诊断准确率随MBIR特征结节数增加而显著下降,关系符合三次函数(AUC的R²=0.993、准确率的R²=0.926;p<0.001);集成模型同样显著下降(AUC的R²=0.993、准确率的R²=0.975;p<0.001);因重建算法异质性导致的AUC变异幅度SVM为0.39、集成模型为0.39。
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: We investigated whether the diagnostic performance of machine learning-based radiomics models for the discrimination of invasive pulmonary adenocarcinomas (IPAs) among subsolid nodules (SSNs) was affected by the proportion of images reconstructed with filtered back projection (FBP) and model-based iterative reconstruction (MBIR) in datasets used for feature extraction.
MATERIALS AND METHODS: This retrospective study included 60 patients (23 men and 37 women; mean age, 61.4 years) with 69 SSNs (54 part-solid and 15 pure ground-glass nodules). Preoperative CT scans were reconstructed with both FBP and MBIR. A total of 860 radiomics features were obtained from the entire nodule volume, and 70 resampled nodule datasets with an increasing proportion of nodules with MBIR-derived features (from 0/69 to 69/69) were prepared. After feature selection using neighborhood component analysis, support vector machines (SVMs) and an ensemble model were used as classifiers for the differentiation of IPAs. The diagnostic performances of all blending proportions of reconstruction algorithms were calculated and analyzed.
RESULTS: The ROC AUC and the diagnostic accuracy of the radiomics models decreased significantly as the number of nodules with MBIR-derived features increased, and this relationship followed cubic functions (R2 = 0.993 and 0.926 for SVM; R2 = 0.993 and 0.975 for the ensemble model; p < 0.001). The magnitude of variation in AUC due to the reconstruction algorithm heterogeneity was 0.39 for SVM and 0.39 for the ensemble model.
CONCLUSION: Inclusion of CT scans reconstructed with MBIR for radiomics modeling can significantly decrease diagnostic performance for the identification of IPAs.
引用
- Kim H, Park CM, Gwak J, et al. Effect of CT Reconstruction Algorithm on the Diagnostic Performance of Radiomics Models: A Task-Based Approach for Pulmonary Subsolid Nodules. AJR Am J Roentgenol. 2018. PMID: 30476456. doi:10.2214/AJR.18.20018
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。