The diagnosis and classification of meningiomas have evolved significantly with the introduction of new criteria and methodologies. A pivotal study by Rebchuk examined the impact of brain invasion criteria on the incidence and distribution of WHO grade 1, 2, and 3 meningiomas, revealing that the 2016 WHO criteria led to a notable shift in the classification of these tumors, particularly in the incidence of grade 2 meningiomas (ref: Rebchuk doi.org/10.1093/neuonc/). Meanwhile, Bayley’s research highlighted the limitations of traditional histopathological grading, demonstrating that DNA methylation and RNA-sequencing approaches provided a more accurate classification of aggressive tumors, suggesting the existence of three biological subtypes of meningiomas (ref: Bayley doi.org/10.1126/sciadv.abm6247/). Additionally, the study by Arsene explored the viral oncogenesis in CNS tumors, finding a significant association between HPV presence and meningiomas, which raises questions about the etiology of these tumors (ref: Arsene doi.org/10.1111/jcmm.17064/). The integration of machine learning techniques for the segmentation of HE-stained pathological images, as demonstrated by Wu, indicates a shift towards more automated and precise diagnostic methods, although challenges remain in fully automating this process (ref: Wu doi.org/10.1371/journal.pone.0263006/). Zhang's work on a radiomic model for differentiating transitional from atypical meningiomas further emphasizes the importance of imaging in preoperative assessments, revealing significant differences in radiomic features that could guide surgical decisions (ref: Zhang doi.org/10.3389/fonc.2022.811767/).