文献速递神经儿科影像MR

基于MRI的人工智能预测儿童髓母细胞瘤分子亚型:系统综述与荟萃分析

Predicting molecular subtypes of pediatric medulloblastoma using MRI-based artificial intelligence: A systematic review and meta-analysis.
PubMed 文献 · Neuroradiology · 2025-09-12

该系统综述与荟萃分析评估基于MRI的人工智能检测儿童髓母细胞瘤分子亚型的诊断性能,纳入8项研究共1195例患者,WNT、SHH、Group 3和Group 4的合并AUC分别为0.80、0.85、0.88和0.86,但所有纳入研究均为回顾性设计,需外部验证数据集进一步研究。

要点

  • 基于MRI的AI对儿童髓母细胞瘤分子亚型检测显示较高诊断性能,各亚型合并AUC为0.80至0.88。
  • WNT亚型合并敏感度0.73、特异度0.94;SHH亚型合并敏感度0.64、特异度0.84。
  • Group 3合并敏感度0.89、特异度0.70;Group 4合并敏感度0.77、特异度0.91。

核心结论

  • 基于MRI的人工智能在检测儿童髓母细胞瘤分子亚型方面显示出高诊断性能,但所有纳入研究均为回顾性设计,可能引入潜在偏倚,需要更多使用外部验证数据集的研究来确认结果并评估其临床适用性。

研究设计与样本

  • 系统综述与荟萃分析,检索PubMed、Embase和Web of Science截至2024年10月前发表的相关研究,最终纳入8项研究共1195例患者,采用双变量随机效应模型计算合并敏感度和特异度及其95%CI,使用I2统计量评估研究异质性。

诊断标准与关键数值

  • WNT亚型:基于MRI的AI合并敏感度0.73(95%CI:0.61-0.83,I2=19%),合并特异度0.94(95%CI:0.79-0.99,I2=93%),AUC为0.80(95%CI:0.77-0.83)。
  • SHH亚型:合并敏感度0.64(95%CI:0.51-0.75,I2=69%),合并特异度0.84(95%CI:0.80-0.88,I2=54%),AUC为0.85(95%CI:0.81-0.88)。
  • Group 3亚型:合并敏感度0.89(95%CI:0.52-0.98,I2=82%),合并特异度0.70(95%CI:0.62-0.77,I2=44%),AUC为0.88(95%CI:0.84-0.90)。
  • Group 4亚型:合并敏感度0.77(95%CI:0.64-0.87,I2=54%),合并特异度0.91(95%CI:0.68-0.98,I2=80%),AUC为0.86(95%CI:0.83-0.89)。

局限性

  • 所有纳入研究均采用回顾性设计,可能引入潜在偏倚。
  • 需要更多使用外部验证数据集的研究来确认结果并评估其临床适用性。

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

BACKGROUND: This meta-analysis aims to assess the diagnostic performance of artificial intelligence (AI) based on magnetic resonance imaging (MRI) in detecting molecular subtypes of pediatric medulloblastoma (MB) in children.

METHODS: A thorough review of the literature was performed using PubMed, Embase, and Web of Science to locate pertinent studies released prior to October 2024. Selected studies focused on the diagnostic performance of AI based on MRI in detecting molecular subtypes of pediatric MB. A bivariate random-effects model was used to calculate pooled sensitivity and specificity, both with 95% confidence intervals (CI). Study heterogeneity was assessed using I2 statistics.

RESULTS: Among the 540 studies determined, eight studies (involving 1195 patients) were included. For the wingless (WNT), the combined sensitivity, specificity, and receiver operating characteristic curve (AUC) based on MRI were 0.73 (95% CI: 0.61-0.83, I2 = 19%), 0.94 (95% CI: 0.79-0.99, I2 = 93%), and 0.80 (95% CI: 0.77-0.83), respectively. For the sonic hedgehog (SHH), the combined sensitivity, specificity, and AUC were 0.64 (95% CI: 0.51-0.75, I2 = 69%), 0.84 (95% CI: 0.80-0.88, I2 = 54%), and 0.85 (95% CI: 0.81-0.88), respectively. For Group 3 (G3), the combined sensitivity, specificity, and AUC were 0.89 (95% CI: 0.52-0.98, I2 = 82%), 0.70 (95% CI: 0.62-0.77, I2 = 44%), and 0.88 (95% CI: 0.84-0.90), respectively. For Group 4 (G4), the combined sensitivity, specificity, and AUC were 0.77 (95% CI: 0.64-0.87, I2 = 54%), 0.91 (95% CI: 0.68-0.98, I2 = 80%), and 0.86 (95% CI: 0.83-0.89), respectively.

CONCLUSIONS: MRI-based artificial intelligence shows high diagnostic performance in detecting molecular subtypes of pediatric MB. However, all included studies employed retrospective designs, which may introduce potential biases. More researches using external validation datasets are needed to confirm the results and assess their clinical applicability.

来源:Neuroradiology,查看原文。版权归原作者所有。

引用

  1. Liu J, Zou Z, He Y, et al. Predicting molecular subtypes of pediatric medulloblastoma using MRI-based artificial intelligence: A systematic review and meta-analysis. Neuroradiology. 2025. PMID: 40938375. doi:10.1007/s00234-025-03759-y

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。