Table 1 Recent brain tumor grading studies via traditional ML and DL methods, as well as statistical modeling methods on brain MRI images.
From: Stochastic differential equation modeling approach for grading astrocytomas on brain MRI images
References | Year | Data | Method | Application | |
|---|---|---|---|---|---|
Machine Learning Methods | Noviandy et al.11 | 2025 | Glioma | Light Gradient Boosting Machine | Distinguishing low grade tumors with grade IV (Acc. = 0.89) |
Kumar et al.7 | 2023 | Glioma | Radiomics features with SVM, RF, Gradient Boost, Naïve Bayes, and AdaBoost classifiers | Grading of tumor into high and low grades (Acc. = 0.83) | |
Vijithananda et al.8 | 2023 | Glioma | Texture features with Logistic Regression, LDA, Decision Tree, Gaussian Naïve Bayes, SVM, KNN, and RF classifiers | Grading of tumor into II, III, and IV (Acc. = 0.88) | |
Chen et al.4 | 2021 | Astrocytoma | Radiomics features with SVM, RF, and LDA classifiers | Distinguishing grade I and II from III (Acc. = 0.77) | |
Tian et al.9 | 2019 | Astrocytoma | Texture features with LDA classifier | Distinguishing grade III from IV (Acc. = 0.97) | |
Dong et al.10 | 2018 | Astrocytoma | Quantitative radiomic features with Decision Tree classifier | Distinguishing grade I from IV (Acc. = 0.87) | |
DeepLearning Methods | Goceri et al.17 | 2025 | Glioma | A network combination of both Convolutional Neural Networks (CNNs) and transformers | Grading of tumor into high and low grades (Acc. = 0.99) |
Usuzaki et al.29 | 2024 | Glioma | variable Vision Transformer (vViT) | Grading of tumor into II, III, and IV (Acc. = 0.84) | |
Wu et al.30 | 2024 | Glioma | An end-to-end multi-task deep learning (MDL) pipeline | Grading of tumor into II, III, and IV (Acc. = 0.83) | |
Vale et al.31 | 2024 | Glioma | Resnet50 | Grading of tumor into II, III, and IV (Acc. = 0.62) | |
Shargunam et al.13 | 2023 | Glioma | A novel Convolutional neural network-based SVM | Grading of tumor into high and low grades (Acc. = 0.99) | |
Trong et al.32 | 2023 | Glioma | combination of complex network and U-Net | Grading of tumor into high and low grades (Acc. = 0.99) | |
Gilanie et al.5 | 2020 | Astrocytoma | CNN | Grading of tumor into I, II, III, and IV (Acc. = 0.96) | |
Gutta et al.14 | 2020 | Glioma | Deep CNN | Grading of tumor into I, II, III, and IV (Acc. = 0.87) | |
Naser et al.15 | 2020 | Glioma | CNN | Distinguishing grade II from III (Acc. = 0.89) | |
George et al.1 | 2019 | Astrocytoma | Deep Learning Neural Network | Grading of tumor into I, II, III, and IV (Acc. = 0.91) | |
Lo et al.6 | 2019 | Glioma | Deep CNN | Grading of tumor into II, III, and IV (Acc. = 0.97) | |
Statistical Modeling | Bian et al.20 | 2022 | Normal | Improved gaussian Mixture model | Brain tissue segmentation and classification |
Cheng et al.21 | 2022 | Normal | Finite Skew student’s-t Mixture model | Brain tissue segmentation | |
Togao et al.33 | 2020 | Brain tumor | Gamma Distribution (GD) model | Differentiation of primary central nervous system lymphomas and glioblastomas | |
Pravitasari et al.22 | 2020 | Brain tumor | Bayesian Neo-Normal Mixture model | Brain Tumor Segmentation | |
Pravitasari et al.23 | 2019 | Brain tumor | Fernandez-Steel Skew Normal Mixture model | Brain Tumor Segmentation | |
Peis et al.24 | 2017 | Normal | Hidden Markov random fields with alpha-stable distributions | Brain tissue segmentation | |
Xia et al.25 | 2016 | Normal | Local variational Gaussian mixture models | Brain tissue segmentation | |
Chua et al.26 | 2015 | Multiple Sclerosis | Linear mixed models | Modeling whole brain lesion volume and atrophy | |
Balafar et al.27 | 2014 | Normal | Gaussian Mixture model | Brain tissue segmentation | |
Salas-Gonzalez et al.34 | 2013 | Normal | Bayesian alpha-stable mixture model | Brain tissue segmentation | |
Vadaparthi et al.35 | 2011 | Normal | Skew Gaussian Distribution | Brain tissue segmentation | |
