文献速递神经肿瘤

传统机器学习方法与深度学习用于脑膜瘤分类、分级、结局预测和分割的比较:系统综述与Meta分析

Traditional Machine Learning Methods versus Deep Learning for Meningioma Classification, Grading, Outcome Prediction, and Segmentation: A Systematic Review and Meta-Analysis.
PubMed 文献 · World Neurosurg · 2023-08-12

该系统综述与Meta分析检索至2021年9月的文献,纳入43篇评估传统机器学习与深度学习在脑膜瘤分类、分级、结局预测和分割中性能的研究。分级方面可合并10项研究,深度学习模型2个(敏感度0.89,特异度0.91),传统机器学习8个(敏感度0.74,特异度0.93);传统方法LR+较高,深度学习LR-较低。

要点

  • 脑膜瘤机器学习研究以传统方法为主,共纳入43篇文献。
  • 分级Meta分析中深度学习敏感度0.89,传统机器学习敏感度0.74。
  • 传统方法LR+较高(10.5 vs 10.1),深度学习LR-较低(0.12 vs 0.28)。

核心结论

  • 脑膜瘤的机器学习研究大多采用传统方法。
  • 对于脑膜瘤分级,传统机器学习方法通常具有较高的LR+,而深度学习模型具有较低的LR-。

研究设计与样本

  • 系统综述与Meta分析,检索主要数据库至2021年9月,评估传统机器学习与深度学习模型在脑膜瘤管理中的性能。
  • 共筛选534条记录,纳入43篇文章,涉及分类(3篇)、分级(29篇)、结局预测(7篇)和分割(6篇)。
  • 采用随机效应模型合并敏感度、特异度、F1分数、受试者工作特征曲线下面积、阳性与阴性似然比及其95%CI。

主要发现

  • 29篇报告分级的研究中,10篇可进行Meta分析,包括2个深度学习模型和8个传统机器学习模型。
  • 深度学习模型:敏感度0.89(95%CI:0.74-0.96),特异度0.91(95%CI:0.45-0.99),LR+ 10.1(95%CI:1.33-137),LR- 0.12(95%CI:0.04-0.59)。
  • 传统机器学习:敏感度0.74(95%CI:0.62-0.83),特异度0.93(95%CI:0.79-0.98),LR+ 10.5(95%CI:2.91-39.5),LR- 0.28(95%CI:0.17-0.49)。
  • 其他性能指标因报告不足未能进一步统计分析。

关键数值与推荐

  • 深度学习模型分级:敏感度0.89(95%CI:0.74-0.96),特异度0.91(95%CI:0.45-0.99),LR+ 10.1(95%CI:1.33-137),LR- 0.12(95%CI:0.04-0.59)。
  • 传统机器学习分级:敏感度0.74(95%CI:0.62-0.83),特异度0.93(95%CI:0.79-0.98),LR+ 10.5(95%CI:2.91-39.5),LR- 0.28(95%CI:0.17-0.49)。

局限性

  • 其他性能指标因报告不足未能进一步统计分析。

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)。

原文

BACKGROUND: Meningiomas are common intracranial tumors. Machine learning (ML) algorithms are emerging to improve accuracy in 4 primary domains: classification, grading, outcome prediction, and segmentation. Such algorithms include both traditional approaches that rely on hand-crafted features and deep learning (DL) techniques that utilize automatic feature extraction. The aim of this study was to evaluate the performance of published traditional ML versus DL algorithms in classification, grading, outcome prediction, and segmentation of meningiomas. METHODS: A systematic review and meta-analysis were conducted. Major databases were searched through September 2021 for publications evaluating traditional ML versus DL models on meningioma management. Performance measures including pooled sensitivity, specificity, F1-score, area under the receiver-operating characteristic curve, positive and negative likelihood ratios (LR+, LR-) along with their respective 95% confidence intervals (95% CIs) were derived using random-effects models. RESULTS: Five hundred thirty-four records were screened, and 43 articles were included, regarding classification (3 articles), grading (29), outcome prediction (7), and segmentation (6) of meningiomas. Of the 29 studies that reported on grading, 10 could be meta-analyzed with 2 DL models (sensitivity 0.89, 95% CI: 0.74-0.96; specificity 0.91, 95% CI: 0.45-0.99; LR+ 10.1, 95% CI: 1.33-137; LR- 0.12, 95% CI: 0.04-0.59) and 8 traditional ML (sensitivity 0.74, 95% CI: 0.62-0.83; specificity 0.93, 95% CI: 0.79-0.98; LR+ 10.5, 95% CI: 2.91-39.5; and LR- 0.28, 95% CI: 0.17-0.49). The insufficient performance metrics reported precluded further statistical analysis of other performance metrics. CONCLUSIONS: ML on meningiomas is mostly carried out with traditional methods. For meningioma grading, traditional ML methods generally had a higher LR+, while DL models a lower LR-.

来源:World Neurosurg,查看原文。版权归原作者所有。

引用

  1. Maniar KM, Lassarén P, Rana A, et al. Traditional Machine Learning Methods versus Deep Learning for Meningioma Classification, Grading, Outcome Prediction, and Segmentation: A Systematic Review and Meta-Analysis. World Neurosurg. 2023. PMID: 37574189. doi:10.1016/j.wneu.2023.08.023

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。