Purpose: To better define the overall performance of the current radiomics-based models for the discrimination of pediatric posterior fossa tumors. Methods: A comprehensive literature search of the databases PubMed, Ovid MEDLINE, Ovid EMBASE, Web of Science, and Scopus was designed and conducted by an experienced librarian. We estimated overall sensitivity (SEN) and specificity (SPE). Event rates were pooled across studies using a random-effects meta-analysis, and the χ2test was performed to assess the heterogeneity. Results: Overall SEN and SPE for differentiation between MB, PA, and EP were found to be promising, with SEN values of 93% (95% CI = 0.88–0.96), 83% (95% CI = 0.66–0.93), and 85% (95% CI = 0.71–0.93), and corresponding SPE values of 87% (95% CI = 0.82–0.90), 95% (95% CI = 0.90–0.98) and 90% (95% CI = 0.84–0.94), respectively. For MB, there is a better trend for LR classifiers, while textural features are the most used and the best performing (ACC 96%). As for PA and EP, a synergistic employment of LR and NN classifiers, accompanied by geometrical or morphological features, demonstrated superior performance (ACC 94% and 96%, respectively). Conclusions: The diagnostic performance is high, making radiomics a helpful method to discriminate these tumor types. In the forthcoming years, we expect even more precise models.
目的：旨在更准确地评估当前基于影像组学的模型在鉴别儿童后颅窝肿瘤方面的整体性能。方法：由经验丰富的文献检索专员设计并系统检索PubMed、Ovid MEDLINE、Ovid EMBASE、Web of Science及Scopus数据库。我们评估了总体敏感度（SEN）与特异度（SPE），采用随机效应模型对研究数据进行荟萃分析合并事件率，并通过χ²检验评估异质性。结果：髓母细胞瘤（MB）、毛细胞星形细胞瘤（PA）和室管膜瘤（EP）的鉴别诊断总体敏感度与特异度表现良好：敏感度分别为93%（95% CI = 0.88–0.96）、83%（95% CI = 0.66–0.93）和85%（95% CI = 0.71–0.93），对应特异度分别为87%（95% CI = 0.82–0.90）、95%（95% CI = 0.90–0.98）和90%（95% CI = 0.84–0.94）。对于MB，逻辑回归分类器呈现更优趋势，其中纹理特征应用最广且性能最佳（准确度96%）。对于PA与EP，逻辑回归与神经网络分类器的协同应用结合几何或形态学特征展现出更优性能（准确度分别为94%和96%）。结论：影像组学模型具有较高的诊断效能，可作为鉴别此类肿瘤类型的有效辅助手段。未来我们期待开发出更精准的预测模型。
肿瘤(癌症)患者之家