Background: Large language models (LLMs) have gained popularity in medicine, however, their roles in neuroradiology remain underexplored. This study aimed to evaluate the current landscape, identify evidence gaps, and propose future directions for LLMs in neuroradiology. Methods: A systematic literature search of PubMed, Embase, Web of Science, and Scopus was conducted to identify relevant studies published between January 1, 2010, and October 1, 2024. Two reviewers screened eligible studies and selected original research applying LLMs in neuroradiology for inclusion. Included studies were evaluated using thematic and geographical analyses to identify trends. Results: Of 287 identified studies, 57 met the inclusion criteria. Findings revealed a significant upward trend in publications since 2018, with an annual growth rate of 78.2%. Three main themes emerged: Operational Workflow Optimization (n=26, 45.6%), Diagnostic Decision Support (n=20, 35.1%), and Education and Training (n=11, 19.3%). Geographically, most studies originated from North America (n=23, 40.4%), Europe (n=19, 33.3%), and Asia (n=12, 21.1%), with limited contribution from other regions (n=3, 5.3%). Key knowledge gaps included strategies to mitigate hallucinations, enhance transparency, and safeguard patient privacy. Conclusions: LLMs are being applied in neuroradiology to support diagnostics, streamline workflows, and enhance education. Future research should prioritize clinical validation, promote ethical practices, and expand global involvement.