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

Autor: Maniar KM; Department of Neurosurgery, Computational Neurosciences Outcomes Center (CNOC), Harvard Medical School, Brigham and Women's Hospital, Boston, Massachusetts, United States., Lassarén P; 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., Rana A; Department of Neurosurgery, Computational Neurosciences Outcomes Center (CNOC), Harvard Medical School, Brigham and Women's Hospital, Boston, Massachusetts, United States; McGovern Institute for Brain Research, Massachusetts Institute of Technology, Boston, Massachusetts, United States., Yao Y; Department of Pharmaceutical Business and Administrative Sciences, School of Pharmacy, Massachusetts College of Pharmacy and Health Sciences University, Boston, Massachusetts, United States., Tewarie IA; Department of Neurosurgery, Computational Neurosciences Outcomes Center (CNOC), Harvard Medical School, Brigham and Women's Hospital, Boston, Massachusetts, United States; Department of Neurosurgery, Haaglanden Medical Center, The Hague, The Netherlands; Faculty of Medicine, Erasmus University Rotterdam/Erasmus Medical Center Rotterdam, Rotterdam, The Netherlands., Gerstl JVE; Department of Neurosurgery, Computational Neurosciences Outcomes Center (CNOC), Harvard Medical School, Brigham and Women's Hospital, Boston, Massachusetts, United States., Recio Blanco CM; Department of Neurosurgery, Computational Neurosciences Outcomes Center (CNOC), Harvard Medical School, Brigham and Women's Hospital, Boston, Massachusetts, United States; Northeast National University, Corrientes, Argentina; Prisma Salud, Puerto San Julian, Santa Cruz, Argentina., Power LH; Department of Neurosurgery, Computational Neurosciences Outcomes Center (CNOC), Harvard Medical School, Brigham and Women's Hospital, Boston, Massachusetts, United States; School of Medicine, Tufts University, Boston, Massachusetts, United States., Mammi M; Neurosurgery Unit, S. Croce e Carle Hospital, Cuneo, Italy., Mattie H; Department of Biostatistics, Harvard TH Chan School of Public Health, Boston, Massachusetts, United States., Smith TR; Department of Neurosurgery, Computational Neurosciences Outcomes Center (CNOC), Harvard Medical School, Brigham and Women's Hospital, Boston, Massachusetts, United States; Department of Neurosurgery, Brigham and Women's Hospital, Harvard University, Boston, Massachusetts, United States., Mekary RA; Department of Neurosurgery, Computational Neurosciences Outcomes Center (CNOC), Harvard Medical School, Brigham and Women's Hospital, Boston, Massachusetts, United States; Department of Pharmaceutical Business and Administrative Sciences, School of Pharmacy, Massachusetts College of Pharmacy and Health Sciences University, Boston, Massachusetts, United States. Electronic address: rania.mekary@channing.harvard.edu.
Jazyk: angličtina
Zdroj: World neurosurgery [World Neurosurg] 2023 Nov; Vol. 179, pp. e119-e134. Date of Electronic Publication: 2023 Aug 12.
DOI: 10.1016/j.wneu.2023.08.023
Abstrakt: 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-.
(Copyright © 2023 Elsevier Inc. All rights reserved.)
Databáze: MEDLINE
Externí odkaz: