Background/Objectives: Artificial intelligence (AI) has rapidly expanded across medical imaging with proposed applications in diagnosis, prognostication, and surgical planning. Concerns remain regarding methodological robustness and clinical readiness for many published models. This systematic review aimed to conduct a methodological audit of AI imaging studies relevant to contemporary neurosurgical practice—including intracranial, cerebrovascular, spinal, and connectomics-based applications—published in 2025. Methods: Following PRISMA guidelines and PROSPERO registration (CRD420261284068), PubMed was searched for studies published in 2025 evaluating machine learning or deep learning applications in MRI- or CT-based imaging. Three reviewers independently extracted data on validation strategy, data leakage risk, human comparator use, calibration reporting, and CLAIM/TRIPOD-AI adherence. Risk of bias was assessed using PROBAST+AI. Results: Of 1776 screened records, 91 studies met the inclusion criteria. China led contributions (54.9%), oncology was the most common domain (37.4%), and MRI was the predominant modality (67.0%). External validation was reported in 75.8% of studies, and 66.0% used multicenter cohorts. Data leakage risk was low in 93.4%. However, only 18.7% included human comparators, calibration was reported in 30.8%, and none achieved full CLAIM/TRIPOD-AI compliance. Conclusions: AI imaging studies published in 2025 demonstrate encouraging progress in multicenter design and external validation. However, persistent gaps in human benchmarking, calibration, and reporting suggest further methodological development is needed.

Background: Data extraction for systematic reviews is highly resource-intensive. This study evaluated four frontier large language models (LLMs) on complex structured metadata extraction from specialized neuroimaging artificial intelligence (AI) literature to determine their performance in automated evidence synthesis. Methods: We compared Google Gemini 3 Pro Preview, Anthropic Claude Opus 4.5, Perplexity Sonar Pro, and OpenAI GPT 5.2. Using a standardized prompt, each model extracted 22 variables from 91 peer-reviewed neuroimaging AI articles. The variables were stratified into low-, medium-, and high-complexity tiers. The performance was measured via the exact-match accuracy against a consensus-based expert ground truth. Results: The overall exact-match accuracy was moderate. Gemini 3 Pro Preview achieved the highest overall rate (56.4%), followed by Sonar Pro (52.1%), Claude Opus 4.5 (51.3%), and GPT 5.2 (46.5%). Gemini significantly outperformed all other models (p < 0.001). The performance declined dramatically as the variable complexity increased. Across models, the accuracy was 88.9–92.9% for low-complexity categorical fields, 47.0–63.3% for medium-complexity text extraction, and 2.7–15.5% for high-complexity variables requiring clinical judgment or multi-section synthesis. The most common type of error was misclassification. All four models scored 0% on the main performance metric, but this reflected a representational mismatch with the ground truth rather than extraction failure, indicating that the exact-match accuracy underestimates the true semantic performance. Conclusions: Frontier LLMs can effectively automate the retrieval of simple categorical data, but have serious difficulties with methodological variables that are complex. Although extraction can be fully automated for low-complexity fields, human review remains essential for context-dependent variables that require clinical judgment.

Objectives: Anterior midline skull base meningiomas, such as olfactory groove meningiomas (OGMs), planum sphenoidale meningiomas, and tuberculum sellae meningiomas pose significant surgical challenges due to their proximity to neurovascular and olfactory structures. The widespread use of the vascularized nasoseptal flap (NSF) has expanded the role of the endoscopic endonasal approach (EEA). This systematic review compares outcomes of EEA and the transcranial approach (TCA) in the NSF era. Methods: PubMed, Embase, and Scopus were searched following PRISMA guidelines for studies published January 2010 and August 2025 comparing EEA and TCA for OGMs and tuberculum sellae/planum sphenoidale (TS/PS) meningiomas with NSF reconstruction. Thirty-five studies (1866 patients) were included and outcomes were stratified by tumor subtype. Results: Gross total resection (GTR) exceeded 90% across both approaches. EEA was associated with superior visual improvement in TS/PS meningiomas, particularly with optic canal involvement, while TCA resulted in better olfactory preservation in OGMs. Cerebrospinal fluid (CSF) leak rates have declined substantially with vascularized NSF reconstruction, especially for TS/PS meningiomas. Conclusions: Both EEA and TCA achieve high GTR rates for anterior midline skull base meningiomas. EEA provides advantages for visual outcomes in TS/PS meningiomas, whereas TCA are favored for olfactory preservation in OGMs. Approach selection should be individualized based on tumor anatomy and functional priorities.

Background: The reliable integration of large language models (LLMs) into neuroimaging data extraction workflows remains unresolved. Prior benchmarking shows that exact-match accuracy underestimates LLM extraction performance, but whether inter-model consensus and variable complexity can guide automation remains unclear. We evaluated whether inter-model consensus can serve as a confidence signal for human–artificial intelligence (AI) extraction and can guide complexity-stratified workflow triage. Methods: Four frontier LLMs were queried via OpenRouter with an identical zero-shot structured prompt to extract 22 predefined variables from 91 peer-reviewed neuroimaging AI articles, yielding 2002 article–variable items per model. Variables were stratified a priori into low- (n = 7), medium- (n = 8), and high-complexity (n = 7). Performance was compared with an expert reference using exact-match and semantic-equivalence accuracy. Item-level consensus and five triage strategies characterized the efficiency–accuracy trade-off. Results: Semantic-equivalence accuracy converged to 80.5–83.4% across models despite approximately ten percentage-point exact-match differences. Unanimous 4/4 consensus occurred in 45.6% (910/1994) of items, with exact-match accuracy of 85.8%, rising to 95.3% after semantic normalization; however, 14.2% still failed to match the reference. Reliability was complexity-dependent: 96.6% for low-complexity variables, 73.2% for medium-complexity variables, and 38.1% for high-complexity variables. A hybrid strategy auto-accepting 4/4 items and routing 3/4 items to rapid verification reduced estimated review effort by approximately 59%. Conclusions: Inter-model consensus is useful, but it is incomplete and depends on variable complexity. We show that LLM-assisted extraction in neuroimaging AI is a complexity-stratified workflow design problem: low-complexity neuroimaging variables may be selectively automated, while medium-complexity variables require rapid verification, and high-complexity methodological variables should remain human-led.

Background/Objectives: Distant metastasis to the infratemporal fossa (ITF) is rare and can mimic primary skull-base tumors. We systematically reviewed reported distant ITF metastases. Methods: Following PRISMA 2020 (PROSPERO CRD420261422546), PubMed, Scopus, and Web of Science were searched through 12 June 2026, for reports of ITF metastasis from a distant primary tumor; direct extension from adjacent tumors was excluded. Data were summarized descriptively, and reports were appraised with the JBI Critical Appraisal Checklist for Case Reports. Results: Seventeen reports (17 patients) were included (median age 59 years). The lung was the most frequent primary site (n = 4), followed by the kidney, colorectum, and thyroid (n = 3 each); adenocarcinoma was the most common histology (n = 7). Facial pain (n = 9) and numbness (n = 6) predominated. Bone destruction was reported in 12 patients, and the maxillary sinus (n = 7), orbit (n = 6), pterygopalatine fossa (n = 5), middle cranial fossa (n = 5), and cavernous sinus (n = 4) were involved. The median reported interval to ITF metastasis was 36 months; 11 metastases were metachronous, and 11 patients had other metastatic disease during the reported course. Five patients underwent regional resection or debulking; radiotherapy was reported in eight, radioiodine in three, and systemic drug treatment in nine. At last follow-up, 11 patients were alive, four had died, and status was unknown in two. Conclusions: Distant ITF metastases may present with facial pain and cranial neuropathies. Prognosis is insufficiently characterized, and management should be individualized within a multidisciplinary team. The evidence is limited to case reports with incomplete reporting. No external funding was received.