背景:在一个中心的数据上训练的Radiomics模型通常在应用于外部中心的数据时表现出性能下降,阻碍他们引入大规模的临床实践。当前的专家建议建议仅使用通过多扫描仪测试-重新测试实验分离的可重现的影像组学特征。这可能有助于克服对外部数据的泛化能力有限的问题。
目的:为了评估仅使用稳健的影像组学特征子集的影响,在先前的体内多MRI扫描仪测试重测研究中定义,关于影像组学模型的性能和泛化性。
方法:回顾性。
方法:单克隆浆细胞疾病患者。训练集(来自中心1的117个MRI);内部测试集(来自中心1的42个MRI);外部测试集(来自中心2-8的143个MRI)。
■1.5T和3.0T;T1加权涡轮自旋回波。
结果:影像组学模型的任务是预测浆细胞浸润,通过骨髓活检确定,从MRI无创地检查。Radiomics机器学习模型,包括线性回归量,支持向量回归量(SVR),和随机森林回归器(RFR),接受了来自中心1的数据培训,使用所有的影像组学功能,或仅使用可重现的影像组学功能。在内部(中心1)和多中心外部数据集(中心2-8)上测试模型。
方法:预测和实际浆细胞浸润之间的Pearson相关系数r和平均绝对误差(MAE)。费希尔的z变换,Wilcoxon符号秩检验,Wilcoxon秩和检验;显著性水平P<0.05。
结果:当与所有特征相比仅使用可再现的特征时,SVR在外部测试集上的性能显著提高(r=0.43vs.r=0.18和MAE=22.6vs.MAE=28.2)。对于RFR,当只使用可重现的而不是所有的影像组学功能时,外部测试集上的性能会下降(r=0.33vs.r=0.44,P=0.29,MAE=21.9vs.MAE=20.5,P=0.10)。
结论:仅使用可重复的影像组学功能可提高某些影像组学的外部性能,但不是所有的机器学习模型,并且没有自动导致整体最佳影像组学模型的外部性能的改善。
方法:
■阶段2.
BACKGROUND: Radiomics models trained on data from one center typically show a decline of performance when applied to data from external centers, hindering their introduction into large-scale clinical practice. Current expert recommendations suggest to use only reproducible radiomics features isolated by multiscanner test-retest experiments, which might help to overcome the problem of limited
generalizability to external data.
OBJECTIVE: To evaluate the influence of using only a subset of robust radiomics features, defined in a prior in vivo multi-MRI-scanner test-retest-
study, on the performance and
generalizability of radiomics models.
METHODS: Retrospective.
METHODS: Patients with monoclonal plasma cell disorders. Training set (117 MRIs from center 1); internal test set (42 MRIs from center 1); external test set (143 MRIs from center 2-8).
UNASSIGNED: 1.5T and 3.0T; T1-weighted turbo spin echo.
RESULTS: The task for the radiomics models was to predict plasma cell infiltration, determined by bone marrow biopsy, noninvasively from MRI. Radiomics machine learning models, including linear regressor, support vector regressor (SVR), and random forest regressor (RFR), were trained on data from center 1, using either all radiomics features, or using only reproducible radiomics features. Models were tested on an internal (center 1) and a multicentric external data set (center 2-8).
METHODS: Pearson correlation coefficient r and mean absolute error (MAE) between predicted and actual plasma cell infiltration. Fisher\'s z-transformation, Wilcoxon signed-rank test, Wilcoxon rank-sum test; significance level P < 0.05.
RESULTS: When using only reproducible features compared with all features, the performance of the SVR on the external test set significantly improved (r = 0.43 vs. r = 0.18 and MAE = 22.6 vs. MAE = 28.2). For the RFR, the performance on the external test set deteriorated when using only reproducible instead of all radiomics features (r = 0.33 vs. r = 0.44, P = 0.29 and MAE = 21.9 vs. MAE = 20.5, P = 0.10).
CONCLUSIONS: Using only reproducible radiomics features improves the external performance of some, but not all machine learning models, and did not automatically lead to an improvement of the external performance of the overall best radiomics model.
METHODS: UNASSIGNED: Stage 2.