In recent years, there has been a significant surge in discussions surrounding artificial intelligence (AI), along with a corresponding increase in its practical applications in various facets of everyday life, including the medical industry. Notably, even in the highly specialized realm of neurosurgery, AI has been utilized for differential diagnosis, pre-operative evaluation, and improving surgical precision. Many of these applications have begun to mitigate risks of intraoperative and postoperative complications and post-operative care. This article aims to present an overview of the principal published papers on the significant themes of tumor, spine, epilepsy, and vascular issues, wherein AI has been applied to assess its potential applications within neurosurgery. The method involved identifying high-cited seminal papers using PubMed and Google Scholar, conducting a comprehensive review of various study types, and summarizing machine learning applications to enhance understanding among clinicians for future utilization. Recent studies demonstrate that machine learning (ML) holds significant potential in neuro-oncological care, spine surgery, epilepsy management, and other neurosurgical applications. ML techniques have proven effective in tumor identification, surgical outcomes prediction, seizure outcome prediction, aneurysm prediction, and more, highlighting its broad impact and potential in improving patient management and outcomes in neurosurgery. This review will encompass the current state of research, as well as predictions for the future of AI within neurosurgery.

In patients with one to three brain metastases who undergo resection, options for post-operative treatments include whole-brain radiotherapy (WBRT) or stereotactic radiosurgery (SRS) of the resection cavity. In this meta-analysis, we sought to compare the efficacy of each post-operative radiation modality with respect to tumor recurrence and survival. Pubmed, Embase and Cochrane databases were searched through June 2016 for cohort studies reporting outcomes of SRS or WBRT after metastasis resection. Pooled effect estimates were calculated using fixed-effect and random-effect models for local recurrence, distant recurrence, and overall survival. Eight retrospective cohort studies with 646 patients (238 with SRS versus 408 with WBRT) were included in the analysis. Comparing SRS to WBRT, the overall crude risk ratio using the fixed-effect model was 0.59 for local recurrence (95%-CI: 0.32–1.09, I2: 3.35%, P-heterogeneity = 0.36, 3 studies), 1.09 for distant recurrence (95%-CI: 0.74–1.60, I2: 50.5%, P-heterogeneity = 0.13; 3 studies), and 2.99 for leptomeningeal disease (95% CI 1.55–5.76; I2: 14.4% p-heterogeneity: 0.28; 2 studies). For the same comparison, the risk ratio for median overall survival was 0.47 (95% CI: 0.41–0.54; I2: 79.1%, P-heterogeneity < 0.01; 4 studies) in a fixed-effect model, but was no longer significant (0.63; 95%-CI: 0.40–1.00) in a random-effect model. SRS was associated with a lower risk of leukoencephalopathy (RR: 0.15, 95% CI: 0.07–0.33, 1 study), yet with a higher risk of radiation-necrosis (RR: 19.4, 95% CI: 1.21–310, 1 study). Based on retrospective cohort studies, the results of this study suggest that SRS of the resection cavity may offer comparable survival and similar local and distant control as adjuvant WBRT, yet may be associated with a higher risk for developing leptomeningeal disease. Future research on SRS should focus on achieving a better understanding of the various factors that may favor SRS over WBRT.

Brain-infiltrating tumour cells from high-grade glioma remain shielded from drug treatments by the blood-brain barrier, leading to inevitable recurrence. Microbubble-enhanced transcranial focused ultrasound (MB-FUS) enables controlled blood-brain barrier opening (BBBO), permitting localised drug delivery. We aimed to assess safety and feasibility of MB-FUS plus standard-of-care chemotherapy for individuals with high-grade glioma. BT008NA was an open-label, single-arm, phase 1/2 trial conducted at five sites in the USA and Canada (part of the ReFOCUSED Consortium). Key eligibility criteria were participants with newly diagnosed high-grade glioma (glioblastoma as per WHO 2016 classification), aged 18-80 years, with normal organ function, a baseline Karnofsky Performance Status score of 70 or higher, who had received maximal safe resection and 6-week chemoradiotherapy and were to start standard-of-care monthly adjuvant temozolomide chemotherapy (150 mg/m² of body surface area). MRI-guided, 220 kHz transcranial MB-FUS treatments were delivered in periresectional (tumour-infiltrative) regions, on any of the first 3 days of a 28-day temozolomide cycle, for up to six cycles. Primary outcomes were safety (adverse events) and feasibility (BBBO: new contrast enhancement on post-procedure T1-weighted MRI). Protocol-prespecified secondary outcomes were overall survival and progression-free survival. Analyses were done in the intention-to-treat population. This trial is registered at ClinicalTrials.gov, NCT03551249 (USA) and NCT03616860 (Canada), and is closed to enrolment. Between Oct 16, 2018, and March 9, 2022, we enrolled 34 participants, all evaluable for prespecified primary and secondary endpoints, with a mean age of 51·5 years (SD 13·0) and median follow-up 44·5 months (95% CI 34·9-57·3). By self-reporting, 18 (53%) participants were female and 16 (47%) male, 28 (82%) were White, and 34 (100%) were non-Hispanic. 176 adverse events were captured: 54 (31%) chemotherapy-related, 10 (6%) disease-related, 87 (49%) related to undergoing MB-FUS (40 [46%] grade 1, 46 [53%] grade 2, and one [1%] grade 3), and 25 (14%) unrelated. Two (1%) of the adverse events were grade 5 (disease-related deaths), three (2%) grade 4 (temozolomide-related haematological abnormalities), and eight (5%) grade 3 (three [2%] temozolomide-related, one [1%] MB-FUS-related, three [2%] disease-related, and one [1%] unrelated); these occurred across seven (21%) of 34 participants. No treatment-related deaths occurred during the trial. BBBO was visualised in all treatments. Median overall survival was 31·3 months (95% CI 21·1-not reached) and median progression-free survival was 13·5 months (9·9-26·9) with patient-specific disease courses found concordant with trajectories of MB-FUS-enriched plasma cell-free DNA. MB-FUS plus temozolomide is a safe combinatorial therapeutic approach for individuals with high-grade glioma, with the potential to improve survival and enable non-invasive plasma biomarker-based disease surveillance (sono-liquid biopsy), warranting randomised controlled trials. National Institutes of Health and Insightec.

Glioblastoma is the most common and lethal central nervous system malignancy with a median survival after progression of only 6–9 months. Major biochemical mechanisms implicated in glioblastoma recurrence include aberrant molecular pathways, a recurrence-inducing tumor microenvironment, and epigenetic modifications. Contemporary standard-of-care (surgery, radiation, chemotherapy, and tumor treating fields) helps to control the primary tumor but rarely prevents relapse. Cytoreductive treatment such as surgery has shown benefits in recurrent glioblastoma; however, its use remains controversial. Several innovative treatments are emerging for recurrent glioblastoma, including checkpoint inhibitors, chimeric antigen receptor T cell therapy, oncolytic virotherapy, nanoparticle delivery, laser interstitial thermal therapy, and photodynamic therapy. This review seeks to provide readers with an overview of (1) recent discoveries in the molecular basis of recurrence; (2) the role of surgery in treating recurrence; and (3) novel treatment paradigms emerging for recurrent glioblastoma.

Oncolytic virotherapy is a rapidly progressing field that uses oncolytic viruses (OVs) to selectively infect malignant cells and cause an antitumor response through direct oncolysis and stimulation of the immune system. Despite demonstrated pre-clinical efficacy of OVs in many cancer types and some favorable clinical results in glioblastoma (GBM) trials, durable increases in overall survival have remained elusive. Recent evidence has emerged that tumor-associated macrophage/microglia (TAM) involvement is likely an important factor contributing to OV treatment failure. It is prudent to note that the relationship between TAMs and OV therapy failures is complex. Canonically activated TAMs (i.e., M1) drive an antitumor response while also inhibiting OV replication and spread. Meanwhile, M2 activated TAMs facilitate an immunosuppressive microenvironment thereby indirectly promoting tumor growth. In this focused review, we discuss the complicated interplay between TAMs and OV therapies in GBM. We review past studies that aimed to maximize effectiveness through immune system modulation—both immunostimulatory and immunosuppressant—and suggest future directions to maximize OV efficacy.

World Health Organization (WHO) grade 4 gliomas of the cerebellum are rare entities whose understanding trails that of their supratentorial counterparts. Like supratentorial high-grade gliomas (sHGG), cerebellar high-grade gliomas (cHGG) preferentially affect males and prognosis is bleak; however, they are more common in a younger population. While current therapy for cerebellar and supratentorial HGG is the same, recent molecular analyses have identified features and subclasses of cerebellar tumors that may merit individualized targeting. One recent series of cHGG included the subclasses of (1) high-grade astrocytoma with piloid features (HGAP, ~31% of tumors); (2) H3K27M diffuse midline glioma (~8%); and (3) isocitrate dehydrogenase (IDH) wildtype glioblastoma (~43%). The latter had an unusually low-frequency of epidermal growth factor receptor (EGFR) and high-frequency of platelet-derived growth factor receptor alpha (PDGFRA) amplification, reflecting a different composition of methylation classes compared to supratentorial IDH-wildtype tumors. These new classifications have begun to reveal insights into the pathogenesis of HGG in the cerebellum and lead toward individualized treatment targeted toward the appropriate subclass of cHGG. Emerging therapeutic strategies include targeting the mitogen-activated protein kinases (MAPK) pathway and PDGFRA, oncolytic virotherapy, and immunotherapy. HGGs of the cerebellum exhibit biological differences compared to sHGG, and improved understanding of their molecular subclasses has the potential to advance treatment.