Table 3.
Cross-validation analysis, best-performing features, and best-performing imaging modalities per each study.
| Author, Journal, Year | Cross-validation analysis | Best- performing features |
Best- performing imaging modalities |
|---|---|---|---|
| Bathla, European Radiology, 2021 (12) | Yes | NGTDM | CE-T1W |
| Chen, The International Journal of Neuroscience, 2018 (13) | Yes | NA | CE-T1W |
| Kang, Neuro-Oncology 2018 (14) | Yes | NA | DWI |
| Kim, Neuroradiology, 2018 (15) | Yes | Shape-based | NA |
| Kong, Neuroimage Clinical, 2019 (16) | Yes | GLRLM | 18F-FDG-PET |
| Lu, Frontiers in neurology, 2022 (17) | Yes | NA | CT scans |
| Lv, Journal of Neurosurgery, 2022 (18) | No | NA | CE-T1W |
| Priya, Neuroradiol J., 2021 (19) | Yes | First order | CE-T1W |
| Wu, IEE Transanctions On Medical Imaging, 2018 (20) | Yes | NA | CE-T1W |
| Xia, Journal of Magnetic Resonance Imaging, 2020 (21) | Yes | NA | CE-T1W |
| Xia, Journal of Magnetic Resonance Imaging, 2021 (22) | Yes | NA | CE-T1W |
NGTDM, neighboring gray tone difference matrix; GLRLM, gray level run length matrix; CE-T1W, contrast-enhanced T1-weighted image; DWI, diffusion-weighted imaging; 18F-FDG-PET/CT, fluorine-18 fluorodeoxyglucose positron emission tomography/computed tomography; CT, computed tomography; NA, Not Available.