A systematic review of machine learning approaches for MRI-based brain tumor analysis
6 affiliations
- 1Department of Mathematical Modeling and Artificial Intelligence, Institute of Computer Science and Telecommunications, Peoples' Friendship University of Russia (RUDN University), Moscow, Russia
- 2Department of Automated Control Systems, National University of Science and Technology MISIS, Moscow, Russia
- 3Federal Research Center “Computer Science and Control” of the Russian Academy of Sciences (FRC CSC RAS), Moscow, Russia
- 4Department of Radiology and Radiosurgery, JSC “National Center for Neurosurgery”, Astana, Kazakhstan
- 5Brain Institute, Al-Farabi Kazakh National University, Almaty, Kazakhstan
- 6Department of Biophysics, Biomedicine and Neuroscience, Al-Farabi Kazakh National University, Almaty, Kazakhstan
Abstract
Machine learning is now widely applied to magnetic resonance imaging-based brain tumor analysis, with task-specific performance metrics: the Dice similarity coefficient (DSC) quantifies segmentation overlap, while the area under the curve (AUC) and accuracy measure classification performance. A PRISMA 2020 systematic review was conducted, searching Scopus, Web of Science, PubMed, and IEEE Xplore, and identified 213 eligible studies published between January 2018 and the final search date of March 16, 2026. Segmentation performance was synthesized by random-effects meta-analysis and classification performance was summarized descriptively. Classification, detection, and grading tasks dominated the literature, followed by segmentation; U-Net variants were the most frequent architectures, with transformer-based models growing fastest. The pooled mean DSC was 0.871 (95% CI: 0.852–0.889) with a 95% prediction interval of 0.7880.953, and heterogeneity was extreme (I2 = 99.9%), so the pooled mean should be read as a descriptive summary of the literature rather than a single underlying effect. The descriptive mean AUC across classification studies was 0.960. Methodological gaps were pervasive: only 18.8% of studies incorporated explainability, only 18.8% performed external validation, and none reported robustness metrics. Benchmark accuracy has outpaced clinical evidence: until models are validated on independent cohorts, evaluated for robustness under realistic acquisition shifts, and made interpretable to clinicians, reported performance is unlikely to translate into patient care.
Related
- Multimodal Machine Learning Approaches to Detect Attention-Deficit/Hyperactivity Disorder (ADHD) Using Physiological and Behavioural Biomarkers: A Systematic Review.
- Automated brain MRI image classification through machine learning and deep learning approaches
- Evidence synthesis on sex differences in mortality after traumatic brain injury: Systematic review integrating meta-analysis and explainable machine learning
- Preoperative Prediction of Difficult Laparoscopic Cholecystectomy: Evolution, Validation, and Emerging Machine-Learning Approaches-A Scoping Review.
- Deployability of machine-learning prediction models in elite and high-level team sports: a task-specific systematic review
BibTeX
@article{brak2026systematic,
title = {{A systematic review of machine learning approaches for MRI-based brain tumor analysis}},
author = {Ivan Viktorovich Brak and Merich Doruk Kaymakcioglu and Vasiliy Vladimirovich Belousov and Zhanibek Baiturlin and Daultay Azamatovich Batyrkhanov and Daniil Olegovich Mityagin and Manzura Zholdassova and Almira Melsovna Kustubayeva},
journal = {Frontiers in Computational Neuroscience},
year = {2026},
month = oct,
doi = {10.3389/fncom.2026.1937002},
url = {https://doi.org/10.3389/fncom.2026.1937002},
note = {CC BY 4.0},
}
RIS
TY - JOUR
TI - A systematic review of machine learning approaches for MRI-based brain tumor analysis
AU - Ivan Viktorovich Brak
AU - Merich Doruk Kaymakcioglu
AU - Vasiliy Vladimirovich Belousov
AU - Zhanibek Baiturlin
AU - Daultay Azamatovich Batyrkhanov
AU - Daniil Olegovich Mityagin
AU - Manzura Zholdassova
AU - Almira Melsovna Kustubayeva
PY - 2026
DA - 2026/10/12
JO - Frontiers in Computational Neuroscience
DO - 10.3389/fncom.2026.1937002
UR - https://doi.org/10.3389/fncom.2026.1937002
AB - Machine learning is now widely applied to magnetic resonance imaging-based brain tumor analysis, with task-specific performance metrics: the Dice similarity coefficient (DSC) quantifies segmentation overlap, while the area under the curve (AUC) and accuracy measure classification performance. A PRISMA 2020 systematic review was conducted, searching Scopus, Web of Science, PubMed, and IEEE Xplore, and identified 213 eligible studies published between January 2018 and the final search date of March 16, 2026. Segmentation performance was synthesized by random-effects meta-analysis and classification performance was summarized descriptively. Classification, detection, and grading tasks dominated the literature, followed by segmentation; U-Net variants were the most frequent architectures, with transformer-based models growing fastest. The pooled mean DSC was 0.871 (95% CI: 0.852–0.889) with a 95% prediction interval of 0.7880.953, and heterogeneity was extreme (I2 = 99.9%), so the pooled mean should be read as a descriptive summary of the literature rather than a single underlying effect. The descriptive mean AUC across classification studies was 0.960. Methodological gaps were pervasive: only 18.8% of studies incorporated explainability, only 18.8% performed external validation, and none reported robustness metrics. Benchmark accuracy has outpaced clinical evidence: until models are validated on independent cohorts, evaluated for robustness under realistic acquisition shifts, and made interpretable to clinicians, reported performance is unlikely to translate into patient care.
SN - 1662-5188
ER -