Nicole Mariantonia Cancelliere

BACKGROUND AND OBJECTIVES: The Woven Endobridge (WEB) and the Contour Neurovascular System (Contour) are both intrasaccular devices used to treat cerebral aneurysms. We compared outcomes of these 2 devices using data from 2 large registries. METHODS: Data were sourced from the WorldWideWEB Consortium, which included 1363 cases treated with WEB from 2017, and a registry of 277 Contour cases from 10 European centers starting the same year. Patient demographics, aneurysm characteristics, procedural specifics, and outcomes were analyzed. Propensity score matching was applied for comparison. RESULTS: Before matching, the Contour group had more men (37.9% vs 30.8%), more asymptomatic cases (83.4% vs 70.3%), and fewer acute subarachnoid hemorrhage cases (10.8% vs 26.2%). After matching, no significant differences were found in demographics or aneurysm characteristics between groups. The median age was 60 years, and median aneurysm dimensions were comparable. Logistic regression showed no significant differences between WEB and Contour in achieving complete occlusion (odds ratio [OR] = 1.01, 95% CI, 0.67-1.52, P = .971), adequate occlusion (OR = 0.85, 95% CI, 0.41-1.76, P = .665), or achieving modified Rankin Scale 0 to 2 at last follow-up (OR = 0.48, 95% CI, 0.21-1.02, P = .064). Retreatment (OR = 2.23, P = .086), thromboembolic complications (OR = 0.75, P = .452), and adjunctive treatment use (OR = 1.93, P = .141) were also similar. CONCLUSION: The WEB and Contour demonstrated comparable clinical and angiographic outcomes in this large multicenter study comprised majority small, asymptomatic cerebral aneurysms.

BACKGROUND AND OBJECTIVES: Middle meningeal artery embolization (MMAE) is effective for chronic subdural hematoma (SDH), but failure rates vary and risk prediction tools are lacking. This study developed and validated a machine learning (ML) model to predict MMAE treatment failure for SDH. METHODS: We conducted an international, multi-institutional retrospective cohort study of patients who underwent MMAE for SDH between 2019 and 2025. The cohort was split into training and test sets, stratified by treatment failure, with all hematomas from each patient assigned to a single cohort to prevent data leakage. Multiple ML algorithms were evaluated using 5-fold cross-validation, with gradient boosting selected as the final model. The primary outcome was treatment failure, defined as rescue surgical evacuation or persistent/recurrent SDH requiring retreatment. Model performance was assessed using area under the curve-receiver operating characteristic. Patients were stratified into low-risk (15%) groups using a priori clinically defined thresholds. RESULTS: Among 692 treated hematomas in the test cohort, 64 (9.2%) experienced treatment failure. The gradient boosting model achieved an area under the curve-receiver operating characteristic of 0.856 (95% CI, 0.803-0.902) before calibration and 0.832 (95% CI, 0.766-0.889) after isotonic calibration, with excellent calibration (Brier score, 0.053). The most important predictors were age-platelet interaction, platelet-hemoglobin ratio, platelet count, SDH thickness, and age. Observed treatment failure was 1.6% (95% CI, 0.4%-5.7%) in the low-risk group (n = 124; 17.9%), 6.0% (95% CI, 4.3%-8.4%) in the medium-risk group (n = 516; 74.6%), and 59.6% (95% CI, 46.1%-71.8%) in the high-risk group (n = 52; 7.5%) ( P < .001 for trend), a 37.2-fold difference between high- and low-risk groups. CONCLUSION: This ML model stratified MMAE patients into risk groups with a 37.2-fold difference in treatment failure. High-risk patients had 59.6% failure, whereas low-risk patients had 1.6% failure. Risk stratification may improve patient selection and monitoring.

Background Middle meningeal artery embolisation (MMAE) reduces treatment failure in chronic subdural haematoma (cSDH), but it remains unclear whether to add surgery and which patients benefit. We examined whether adding surgery improves functional recovery, accounting for admission status. Methods We conducted a multicentre cohort study of 2075 patients with cSDH treated with MMAE across 33 sites. The primary outcome was excellent functional recovery (modified Rankin Scale (mRS) 0–1) at the last recorded assessment, the timepoint with highest ascertainment (n=1854); a pre-specified 90-day analysis tested whether the timepoint determined the result. The effect modifier was admission functional status (mRS ≥2 vs 0–1), with doubly robust adjustment for measured baseline differences. Results Among 797 patients impaired at admission, excellent recovery occurred in 111/364 (30%) with surgery plus MMAE versus 101/433 (23%) with MMAE alone (adjusted difference 8.2 percentage points; 95% CI 0.8 to 15.5); among 1057 independent patients, it was 3.1 (−3.8 to 9.9). At 90 days, the impaired-group estimate was similar but less precise (7.5; −4.7 to 19.7; n=436), so the finding did not depend on the timepoint. The difference was largest with haematoma volume >80 mL (17.6; 6.6 to 28.6) and was absent for functional independence, freedom from recurrence or reoperation and survival. Surgical complications occurred in 9/195 (4.6%) impaired patients undergoing evacuation. Conclusions Adding surgery was associated with greater excellent functional recovery among admission-impaired but not already independent patients, consistently at 90 days and confined to the excellent-recovery threshold. Randomised validation stratified by admission function is warranted.

Introduction: Nonacute subdural hematomas (nSDH) are common yet serious extra-axial hemorrhages that result in significant morbidity and mortality. Middle meningeal artery (MMA) embolization (MMAE) is a recent endovascular treatment that involves occlusion of the MMA, inducing hemostasis in and around the hematoma. While many aspects of MMAE have been explored, there is currently limited data on the optimal extent of embolization. Objective: To determine whether single or multiple pedicle embolization of the MMA is superior in inducing hemostasis in nSDH. Methods: We compared single versus multi pedicle embolization by a retrospective multicenter analysis of nSDH patients who underwent MMAE between 2019 and 2024 at participating centers in the MESH (MMA Embolization for Subdural Hematoma) Registry. 679 patients who received a liquid embolic agent with branch-level embolization data were included. Results: While multi-pedicle embolization hastened nSDH thinning at 1 month (5.7 vs. 3.3 mm reduction; difference 2.4 mm, 95% CI 1.0–3.8; P = .002), by 3 months thickness reduction had converged between groups (8.2 vs. 8.4 mm; P = .91). Among 679 patients (456 multi-pedicle, 223 single-pedicle), favorable functional outcome (mRS 0–2) was more frequent with multi-pedicle embolization (53.5% vs. 43.0%; adjusted OR 1.81, 95% CI 1.26–2.60; P = .001), whereas recurrence, rescue surgery, and treatment failure did not differ. Conclusion: Future, multi-center randomized prospective trials are warranted to address confounding variables that limit this observational study. Follow-up beyond 3 months was limited, so durability is unknown.

Purpose: Deep learning (DL) denoising may improve cone-beam CT (CBCT) image quality for point-of-care stroke assessment in the interventional suite. The purpose of this study was to evaluate the impact of a DL-based denoising algorithm on objective and subjective image quality in brain CBCT using both standard circular and advanced dual-axis trajectories. Methods: We retrospectively analyzed 20 noncontrast brain CBCT acquisitions (Karolinska: 10 standard circular; St Michael's: 10 dual-axis). A DL-based denoising algorithm was applied at three strengths (Minimal, Medium, High) and compared to standard images with no additional denoising. Objective metrics (noise, signal-to-noise ratio (SNR), contrast-to-noise ratio (CNR), artifact indices) were measured using standardized ROIs. Six experts rated subjective image quality on 5-point Likert scales. Paired tests with Bonferroni correction were used for comparisons. Results: High-level DL denoising significantly improved all objective metrics (noise, SNR, CNR, artifact indices) for both thin and thick slices (all p <.001). It doubled gray–white matter CNR (thin slices: 2.31 vs. 1.08), reduced noise, and improved subcalvarial and posterior fossa artifact indices. Subjectively, high-level denoising yielded higher median ratings for noise, texture, sharpness, brain parenchyma visualization, CSF spaces, and confidence in assessing ischemia and hemorrhage (all p <.001). Improvements were consistent for both acquisition techniques, and perceived artifact severity did not differ ( p >.99). Inter-reader agreement was substantial. Conclusion: The DL-based denoising algorithm significantly improved objective and subjective brain CBCT image-quality; no difference in perceived artifact severity was detected. These findings support further evaluation of deep learning-enhanced CBCT denoising for brain imaging in the interventional suite.