World Neurosurg. 2023 Aug 11:S1878-8750(23)01126-9. doi: 10.1016/j.wneu.2023.08.023. Online ahead of print.
ABSTRACT
BACKGROUND: Meningiomas are common intracranial tumors. Machine learning (ML) algorithms are emerging to improve accuracy in four primary domains: classification, grading, outcome prediction, and segmentation. Such algorithms include both, traditional approaches that rely on hand-crafted features and deep learning techniques that utilize automatic feature extraction.
OBJECTIVE: To evaluate the performance of published traditional ML vs. deep learning 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 vs. deep learning models on meningioma management. Performance measures including pooled sensitivity, specificity, F1-score, area under the receiver-operating characteristic curve (AUC), positive and negative likelihood ratios (LR+, LR-) along with their respective 95% confidence intervals (95%CIs) were derived using random-effects models.
RESULTS: 534 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 two deep learning 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 eight 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.
CONCLUSION: Machine learning on meningiomas is mostly carried out with traditional methods. For meningioma grading, traditional machine learning methods generally had a higher LR+, while deep learning models a lower LR-.
PMID:37574189 | DOI:10.1016/j.wneu.2023.08.023
