Table 1.
Overview of meningioma radiomics studies.
| Author | Year | Number of Patients | MR Sequences | Aim | Radiomics Analysis | ROI | Outcome |
|---|---|---|---|---|---|---|---|
| AlKubeyyer et al. [4] | 2020 | 31 | T2 | Characterization | Machine learning | 2D | Tumor firmness |
| Brabec et al. [5] | 2022 | 30 | DTI | Characterization | Histogram analysis | 2D | Tumor firmness and presurgical grading |
| Cepeda et al. [6] | 2021 | 18 | CE-T1 | Characterization | Machine learning | 3D | Tumor firmness |
| Chen et al. [7] | 2019 | 150 | CE-T1 | Characterzation | Machine learning | 3D | Presurgical grading |
| Chu et al. [8] | 2020 | 98 | CE-T1 | Characterization | Machine learning | 3D | Presurgical grading |
| Fan et al. [9] | 2022 | 220 | CE-T1, T2 | Characterization | Clinic-radiomic model | 3D | Differential diagnosis of intracranial hemangiopericytoma and angiomatous meningioma |
| Hamerla et al. [10] | 2019 | 138 | CE-T1, T2, ADC, FLAIR, subtraction maps | Characterization | Machine learning | 3D | Presurgical grading |
| Kanazawa et al. [11] | 2018 | 43 | CE-T1, ADC | Characterization | Texture analysis | 3D | Differential diagnosis of intracranial hemangiopericytoma and angiomatous meningioma |
| Ko et al. [12] | 2021 | 128 | CE-T1, T2 | Prognosis | Radiomic features | 3D | Recurrence |
| Laukamp et al. [13] | 2018 | 211 | CE-T1, FLAIR | Segmentation | Deep learning | 3D | Segmentation |
| Li et al. [14] | 2019 | 67 | CE-T1, ADC, FLAIR | Characterization | Machine learning | 3D | Differential diagnosis of intracranial hemangiopericytoma and angiomatous meningioma |
| Lu et al. [15] | 2018 | 152 | ADC | Detection | Machine learning | 3D | Diagnosis |
| Morin et al. [16] | 2019 | 303 | CE-T1 | Characterization and prognosis | Radiological-radiomic model | 3D | Grading, local failure, survival |
| Park et al. [17] | 2018 | 136 | CE-T1, ADC, DTI | Characterization | Machine learning | 3D | Grading and histological type |
| Speckter et al. [18] | 2018 | 32 | CE-T1, T2, T1, DTI | Prognosis | Texture analysis | 3D | Treatment response after radiosurgery |
| Tian et al. [19] | 2020 | 127 | CE-T1, T2 | Characterization | Texture analysis | 3D | Differential diagnosis between craniopharyngioma and meningioma |
| Wei et al. [20] | 2020 | 292 | CE-T1, T2, T1 | Characterization | Clinic-radiological data and radiomics signature | 3D | Distinction of intracranial hemangiopericytoma from meningioma |
| Yan et al. [21] | 2017 | 131 | CE-T1 | Characterization | Machine learning | 3D | Presurgical grading |
| Yang et al. [22] | 2022 | 132 | CE-T1 | Characterization | Deep learning | 3D | Presurgical grading |
| Zhai et al. [23] | 2021 | 172 | CE-T1 | Characterization | Machine learning | 3D | Meningioma consistency |
| Zhang et al. [24] | 2019 | 60 | T2, ADC | Prognosis | Radiomic classification | 3D | Recurrence in skull base meningiomas |
| Zhang et al. [25] | 2020 | 235 | CE-T1 | Characterization | Machine learning | 3D | Discrimination of lesions located in the anterior skull base |
| Zhu et al. [26] | 2019 | 222 | CE-T1 | Characterization | Deep learning | Not reported | Presurgical grading |
MR: magnetic resonance; ROI: region of interest; CE: contrast-enhanced; FLAIR: fluid attenuated inversion recovery; ADC: apparent diffusion coefficient; DTI: diffusion tensor imaging.