Background: Spheno-orbital meningiomas (SOMs) are rare tumors arising from the meninges surrounding the sphenoid bone and orbital structures. Surgical resection is the primary treatment approach for SOMs. Several surgical approaches have been described during the decades, including microsurgical transcranial (MTAs), endoscopic endonasal (EEAs), endoscopic transorbital (ETOAs), and combined approaches, and the choice of surgical approach remains a topic of debate. Purpose: This systematic review and meta-analysis aim to compare the clinical and surgical outcomes of different surgical approaches used for the treatment of SOMs, discussing surgical techniques, outcomes, and factors influencing surgical decision making. Methods: A comprehensive literature review of the databases PubMed, Ovid MEDLINE, and Ovid EMBASE was conducted for articles published on the role of surgery for the treatment of SOMs until 2023. The systematic review was performed according to the Preferred Reporting Items for Systematic Reviews and Meta-Analysis guidelines. Meta-analysis was performed to estimate pooled event rates and assess heterogeneity. Fixed- and random-effects were used to assess 95% confidential intervals (CIs) of presenting symptoms, outcomes, and complications. Results: A total of 59 studies comprising 1903 patients were included in the systematic review and meta-analysis. Gross total resection (GTR) rates ranged from 23.5% for ETOAs to 59.8% for MTAs. Overall recurrence rate after surgery was 20.7%. Progression-free survival (PFS) rates at 5 and 10 years were 75.5% and 49.1%, respectively. Visual acuity and proptosis improvement rates were 57.5% and 79.3%, respectively. Postoperative cranial nerve (CN) focal deficits were observed in 20.6% of cases. The overall cerebro-spinal fluid (CSF) leak rate was 3.9%, and other complications occurred in 13.9% of cases. MTAs showed the highest GTR rates (59.8%, 95%CI = 49.5–70.2%; p = 0.001) but were associated with increased CN deficits (21.0%, 95%CI = 14.5–27.6%). ETOAs had the lowest GTR rates (23.5%, 95%CI = 0.0–52.5%; p = 0.001), while combined ETOA and EEA had the highest CSF leak rates (20.3%, 95%CI = 0.0–46.7%; p = 0.551). ETOAs were associated with better proptosis improvement (79.4%, 95%CI = 57.3–100%; p = 0.002), while anatomical class I lesions were associated with better visual acuity (71.5%, 95%CI = 63.7–79.4; p = 0.003) and proptosis (60.1%, 95%CI = 38.0–82.2; p = 0.001) recovery. No significant differences were found in PFS rates between surgical approaches. Conclusion: Surgical treatment of SOMs aims to preserve visual function and improve proptosis. Different surgical approaches offer varying rates of GTR, complications, and functional outcomes. A multidisciplinary approach involving a skull base team is crucial for optimizing patient outcomes.

Background: Radiomics offers quantitative, high-dimensional data from conventional imaging and holds promise for improving diagnosis and treatment of pituitary adenomas (PAs). This systematic review aimed to synthesize current clinical applications of radiomics in PAs, focusing on diagnostic, predictive, and prognostic modeling. Methods: This review followed the PRISMA 2020 guidelines. A systematic search was performed in PubMed, Scopus, and Web of Science on 10 January 2024, and updated on 5 March 2024, using predefined keywords and MeSH terms. Studies were included if they evaluated radiomics-based models using MRI for diagnosis, classification, consistency, invasiveness, treatment response, or recurrence in human PA populations. Data extraction included study design, sample size, MRI sequences, feature types, machine learning algorithms, and model performance metrics. Study quality was assessed via the Newcastle-Ottawa Scale. Descriptive statistics summarized study characteristics; no meta-analysis was performed due to heterogeneity. Results: Out of 341 identified articles, 49 studies met inclusion criteria, encompassing a total of more than 9350 patients. The majority were retrospective (43 studies, 88%). MRI sequences used included T2-weighted imaging (35 studies, 71%), contrast-enhanced T1WI (34 studies, 69%), and T1WI (21 studies, 43%). PyRadiomics was the most common feature extraction tool (20 studies, 41%). Machine learning was employed in 43 studies (88%), predominantly support vector machines (16 studies, 33%), random forests (9 studies, 18%), and logistic regression (9 studies, 18%). Deep learning methods were applied in 17 studies (35%). Regarding diagnostic performance, 22 studies (45%) reported an (AUC) ≥0.85 in test datasets. External validation was performed in only 6 studies (12%). Radiomics applications included histological subtype prediction (14 studies, 29%), surgical outcome prediction (13 studies, 27%), invasiveness assessment (7 studies, 15%), tumor consistency evaluation (8 studies, 16%), and response to medical or radiotherapy treatments (3 studies, 6%). One study (2%) addressed automated segmentation and volumetry. Conclusions: Radiomics enables high-performance, noninvasive prediction of PA subtypes, consistency, invasiveness, treatment response, and recurrence, with 22 studies (45%) reporting AUC ≥0.85. Despite promising results, clinical translation remains limited by methodological heterogeneity, low external validation (6 studies, 12%), and lack of standardization.