A systematic review of multiparametric magnetic resonance imaging radiomics in the prediction of brain invasion in meningioma

多参数磁共振成像放射组学在预测脑膜瘤脑侵犯中的系统评价

阅读:2

Abstract

BACKGROUND: Brain invasion plays an important role in determining the grade, prognosis, and recurrence of meningioma. There is an emerging trend to explore the feasibility of radiomics in prediction of brain invasion in meningiomas pre-operatively. This review aims to assess the role and quality of published magnetic resonance imaging (MRI) radiomics studies on brain invasion prediction. METHODS: A search for literature published between January 2019 and October 2024 across five databases was conducted following the 2020 PRISMA guidelines. The methodological quality and risk of bias of eligible studies were assessed by the Radiomics Quality Score (RQS) and the Quality Assessment of Diagnostic Accuracy Studies-2 (QUADAS-2). RESULTS: Six of 381 studies were included in the final review. All the included studies were retrospective in nature. The majority (5/6, 83.3%) of studies analyzed multisequence MRI for radiomics analysis. Reported validation area under the curve (AUC) ranged from 0.74 to 0.91. The best-performing models described in the included studies used both radiomics and semantic features to construct the final feature signature. The overall methodological quality was low, with a mean radiomics quality score (RQS) score of 12.91 (35.86%). The overall risk of bias was low in 4/6 (66.6%), high in 1/6 (16.7%), and unclear in 1/6 (16.7%) studies. CONCLUSIONS: Radiomics analysis may have potential for predicting brain invasion in meningioma, but the current body of evidence and the overall methodological quality of studies are limited. Future studies should incorporate complementary information from multiparametric MRI, and prioritise robust external validation. Addressing class imbalance, and providing comprehensive evaluations of model performance and clinical utility will be essential to determine the practical value of radiomics models in practice.

特别声明

1、本页面内容包含部分的内容是基于公开信息的合理引用;引用内容仅为补充信息,不代表本站立场。

2、若认为本页面引用内容涉及侵权,请及时与本站联系,我们将第一时间处理。

3、其他媒体/个人如需使用本页面原创内容,需注明“来源:[生知库]”并获得授权;使用引用内容的,需自行联系原作者获得许可。

4、投稿及合作请联系:info@biocloudy.com。