Maniar Krish M, Lassarén Philipp, Rana Aakanksha, Yao Yuxin, Tewarie Ishaan A, Gerstl Jakob V E, Recio Blanco Camila M, Power Liam H, Mammi Marco, Mattie Heather, Smith Timothy R, Mekary Rania A
Department of Neurosurgery, Computational Neurosciences Outcomes Center (CNOC), Harvard Medical School, Brigham and Women's Hospital, Boston, Massachusetts, United States.
Department of Neurosurgery, Computational Neurosciences Outcomes Center (CNOC), Harvard Medical School, Brigham and Women's Hospital, Boston, Massachusetts, United States; Department of Clinical Neuroscience, Karolinska Institutet, Stockholm, Sweden.
World Neurosurg. 2023 Nov;179:e119-e134. doi: 10.1016/j.wneu.2023.08.023. Epub 2023 Aug 12.
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.
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.
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.
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-.
脑膜瘤是常见的颅内肿瘤。机器学习（ML）算法正在兴起，以提高在四个主要领域的准确性：分类、分级、预后预测和分割。此类算法包括依赖手工特征的传统方法和利用自动特征提取的深度学习（DL）技术。本研究的目的是评估已发表的传统ML与DL算法在脑膜瘤分类、分级、预后预测和分割中的性能。
进行了系统综述和荟萃分析。检索主要数据库至2021年9月，以查找评估传统ML与DL模型在脑膜瘤管理方面的出版物。使用随机效应模型得出性能指标，包括合并敏感度、特异度、F1分数、受试者操作特征曲线下面积、阳性和阴性似然比（LR+，LR-）及其各自的95%置信区间（95%CI）。
筛选了534条记录，纳入43篇文章，涉及脑膜瘤的分类（3篇文章）、分级（29篇）、预后预测（7篇）和分割（6篇）。在报告分级的29项研究中，10项可与2个DL模型进行荟萃分析（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）以及8个传统ML模型（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）。报告的性能指标不足，无法对其他性能指标进行进一步的统计分析。
脑膜瘤的ML大多采用传统方法。对于脑膜瘤分级，传统ML方法的LR+通常较高，而DL模型的LR-较低。
