Traditional Machine Learning Methods versus Deep Learning for Meningioma Classification, Grading, Outcome Prediction, and Segmentation: A Systematic Review and Meta-Analysis

被引：6

作者：

Maniar, Krish M. ^{[1
]}

Lassaren, Philipp ^{[1
,2
]}

Rana, Aakanksha ^{[1
,3
]}

Yao, Yuxin ^{[4
]}

Tewarie, Ishaan A. ^{[1
,5
,6
]}

Gerstl, Jakob V. E. ^{[1
]}

Blanco, Camila M. Recio ^{[1
,7
,8
]}

Power, Liam H. ^{[1
,9
]}

Mammi, Marco ^{[10
]}

Mattie, Heather ^{[11
]}

Smith, Timothy R. ^{[1
,12
]}

Mekary, Rania A. ^{[1
,4
]}

机构：

[1] Harvard Med Sch, Brigham & Womens Hosp, Computat Neurosci Outcomes Ctr CNOC, Dept Neurosurg, Boston, MA 02115 USA

[2] Karolinska Inst, Dept Clin Neurosci, Stockholm, Sweden

[3] MIT, McGovern Inst Brain Res, Boston, MA USA

[4] Massachusetts Coll Pharm & Hlth Sci Univ, Sch Pharm, Dept Pharmaceut Business & Adm Sci, Boston, MA 02115 USA

[5] Haaglanden Med Ctr, Dept Neurosurg, The Hague, Netherlands

[6] Erasmus Univ, Fac Med, Erasmus Med Ctr Rotterdam, Rotterdam, Netherlands

[7] Northeastern Natl Univ, Corrientes, Argentina

[8] Prisma Salud, Puerto San Julian, Santa Cruz, Argentina

[9] Tufts Univ, Sch Med, Boston, MA USA

[10] S Croce & Carle Hosp, Neurosurg Unit, Cuneo, Italy

[11] Harvard TH Chan Sch Publ Hlth, Dept Biostat, Boston, MA USA

[12] Harvard Univ, Brigham & Womens Hosp, Dept Neurosurg, Boston, MA USA

来源：

WORLD NEUROSURGERY | 2023年 / 179卷

关键词：

Deep learning; Grading; Machine learning; Meningioma; Segmentation; Traditional statistics; RADIOMICS; FEATURES; MODEL; PERFORMANCE;

D O I：

10.1016/j.wneu.2023.08.023

中图分类号：

R74 [神经病学与精神病学];

学科分类号：

摘要：

- 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 clas-sification (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 pre-cluded 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-.

引用

页码：E119 / E134

页数：16

共 70 条

[1] A multiresolution clinical decision support system based on fractal model design for classification of histological brain tumours [J].