Search Results (276)

Objectives: Intracerebral hemorrhage (ICH) is a devastating form of stroke characterized by high morbidity and mortality, but effective treatment strategy remains in urgent demand. Notoginsenoside R1 (NGR1), a bioactive component extracted from the traditional herb Panax notoginseng has been widely applied in the therapy of cardiovascular diseases and neurological disorders. This study aims to investigate the effects of NGR1 on oxidative damage following ICH. Methods: NGR1 was administrated to a collagenase-induced ICH mouse model and hemin-stimulated primary astrocytes in vitro. Hematoma volume, brain water content and neurobehavioral outcomes were assessed in the ICH mice. Cell viability was evaluated using the Cell Counting Kit-8 (CCK-8) assay. In astrocytes pretreated with 25 μM NGR1 for 24 h followed by 30 μM hemin treatment for 24 h, levels of reactive oxygen species (ROS), malondialdehyde (MDA), and the glutathione (GSH)/oxidized glutathione (GSSG) ratio were measured. The expression of lipocalin-2 (LCN2), heme oxygenase-1 (HO-1), and glial fibrillary acidic protein (GFAP) was detected via immunofluorescence staining and Western blotting. Additionally, LCN2 and HO-1 were knocked down in astrocytes, using small interfering RNA (siRNA) transfection. Results: LCN2, HO-1, and GFAP expression was upregulated in the peri-lesional area of the brain following ICH. NGR1 alleviated brain injury and improved neurological function in the collagenase-induced ICH mouse model. Specifically, administration of 20 mg/kg NGR1 suppressed the upregulation of LCN2 and increased HO-1 expression post ICH. NGR1 enhanced cell viability and reversed hemin-induced toxicity in astrocytes in vitro. Treatment with 25 μM NGR1 reduced ROS and MDA levels and upregulated the GSH/GSSG ratio in astrocytes exposed to 30 μM hemin. Furthermore, 25 μM NGR1 inhibited LCN2 and GFAP expression while promoting HO-1 expression in hemin-treated astrocytes. The inhibitory effect of NGR1 on LCN2 was reversed by the Nrf-2/HO-1 inhibitor ML385. Moreover, LCN2 knockdown promoted HO-1 expression and suppressed ROS levels in astrocytes. Conversely, HO-1 knockdown increased LCN2 and GFAP expression, thereby reversing the protective effects of NGR1. Conclusions: This study demonstrates that NGR1 alleviates ICH-induced oxidative damage by promoting HO-1 expression and inhibiting LCN2 expression, thereby maintaining redox homeostasis. Full article

Background: Aneurysmal subarachnoid hemorrhage (aSAH) and spontaneous intracerebral hemorrhage (ICH) are associated with secondary brain injury. Impaired cerebral autoregulation (CA) is hypothesized to be associated with this pathophysiology, reflecting a transition toward a pressure-passive cerebrovascular state. Static clinical variables do not adequately capture this dynamic process, highlighting a potential role for continuous physiological monitoring. Objective: To systematically evaluate the prognostic utility of invasively monitored continuous pressure reactivity index (PRx) and deviation from optimal cerebral perfusion pressure (ΔCPPopt) in adult patients with aSAH and ICH. Methods: A PRISMA-compliant systematic review and meta-analysis was conducted across four major databases. Nineteen studies (13 aSAH, 6 ICH) utilizing continuous invasive monitoring were included. Primary endpoints were mortality and functional recovery; delayed cerebral ischemia (DCI) was a secondary outcome for aSAH. Data were synthesized using random-effects models. Results: In the ICH cohort, elevated mean PRx (Mean Difference [MD] = 0.18; p = 0.005) and deviations below optimal perfusion pressure (ΔCPPopt MD = −6.92 mmHg; p = 0.0001) were associated with unfavorable functional recovery. Furthermore, higher PRx values were significantly associated with mortality (MD = 0.21; p = 0.0006). For aSAH, higher PRx values correlated with poor functional outcomes (MD = 0.10; p = 0.04); however, this association was not robust to sensitivity analysis. Elevated PRx also correlated with DCI occurrence (MD = 0.05; p = 0.04), but the clinical magnitude of this difference remains uncertain. The GRADE certainty of evidence for all assessed outcomes was low, primarily due to the observational design of the included studies and the inherent risk of residual confounding. Conclusions: Low-certainty evidence suggests that continuous monitoring of PRx and ΔCPPopt may offer prognostic utility regarding ischemic complications and functional outcomes in spontaneous brain hemorrhage. While these findings support exploring individualized, autoregulation-guided neurocritical care, prospective multicenter validation remains necessary prior to routine clinical implementation. Full article

Objectives: The aim of this study was to determine the prevalence and distribution of intracranial arterial dolichoectasia (IADE) across the anterior and posterior circulations and assess its association with cerebral small vessel disease (CSVD) imaging markers in patients with spontaneous intracerebral hemorrhage (ICH). Methods: This retrospective cross-sectional study included 174 ICH patients. Three-dimensional vascular reconstruction was used to assess cavernous internal carotid artery morphology, vertebrobasilar dolichoectasia, and exploratory middle cerebral artery (MCA) tortuosity. IADE was defined by Type III–IV cavernous internal carotid artery morphology and/or vertebrobasilar dolichoectasia. Multivariable logistic regression was adjusted for age, sex, hypertension, diabetes mellitus, and previous stroke. Results: IADE was present in 52 patients (29.9%) and was observed more frequently in CSVD-related ICH than in macrovascular ICH (32.9% versus 14.3%; p = 0.049). Among patients with CSVD-related ICH, IADE was associated with deep cerebral microbleeds (adjusted odds ratio [OR], 3.42; 95% CI, 1.27–9.20), severe basal ganglia enlarged perivascular spaces (adjusted OR, 4.24; 95% CI, 1.72–10.46), and deep white matter hyperintensity grade ≥ 2 (adjusted OR, 3.71; 95% CI, 1.59–8.65). These associations were still significant after false discovery rate correction. No significant association was observed with lobar cerebral microbleeds. Exploratory analyses showed higher maximum and mean bilateral MCA tortuosity indices in patients with IADE. Conclusions: IADE was present in approximately one third of patients with ICH and was observed more frequently in CSVD-related than in macrovascular ICH in this cohort. Its association with deep CSVD imaging markers suggests a possible link between IADE and deep small-vessel disease, while the MCA findings remain exploratory. Full article

Background/Objectives: Clazosentan reduces cerebral vasospasm and delayed cerebral ischemia following aneurysmal subarachnoid hemorrhage (aSAH). However, concerns that clazosentan may cause cerebral edema and increase intracranial pressure (ICP) have discouraged its use in patients with poor-grade aSAH. Methods: This single-center retrospective study included 59 patients with aSAH who underwent continuous direct ICP monitoring, of whom 23 received clazosentan and 24 received fasudil. Most clazosentan-treated patients had poor-grade aSAH (WFNS 4–5, 95.7%). The primary outcome was the change in mean daily ICP in the clazosentan group between the pre-treatment and full treatment periods, with a secondary analysis restricted to the first 7 days and stratified by the presence of intracerebral hematoma (ICH). Cerebral perfusion pressure (CPP) changes were assessed as secondary outcomes, and the fasudil group served as an exploratory comparator. Results: Among 21 clazosentan-treated patients available for primary analysis, median ICP did not change significantly between the pre-treatment and treatment periods (6.4 vs. 8.4 mmHg; median ΔICP +0.5 mmHg, 95% CI −1.74 to +2.64; p = 0.708), a finding consistent in the first 7 days and across subgroups by ICH status. In contrast, CPP increased significantly between the pre-treatment and treatment periods (69.1 vs. 84.5 mmHg; median ΔCPP +14.0 mmHg, 95% CI +8.93 to +17.44; p < 0.001). Conclusions: In this retrospective single-center cohort, no statistically significant ICP elevation was observed during clazosentan administration under standard neurosurgical management. Although the small sample size limits statistical power and a false-negative result cannot be excluded, these findings may help inform clinical decision-making regarding clazosentan use in patients with poor-grade aSAH. Full article

Background: Early cardiovascular complications after non-traumatic intracerebral hemorrhage (ICH) contribute to short-term morbidity and mortality, yet reliable prognostic markers remain limited. We examined the association between admission serum albumin and 30-day cardiovascular complications after ICH, including dose–response patterns and consistency across subgroups. Methods: In this retrospective cohort study using the TriNetX US Collaborative Network, adults hospitalized with ICH (ICD-10-CM I61) and serum albumin measured within 24 h of admission were stratified into reduced (≤3.4 g/dL) and normal (≥3.5 g/dL) groups and balanced by 1:1 propensity score matching on demographics, cardiovascular comorbidities, ICH severity, neurosurgical procedures, and medications. The primary outcome was a 30-day composite of all-cause death, acute myocardial infarction, heart failure, atrial fibrillation or flutter, ventricular arrhythmias, and Takotsubo cardiomyopathy. Sensitivity analyses addressed age, sex, comorbidity burden, and chronic hypoalbuminemia. Results: Of 241,228 patients, 94,925 (39%) had reduced albumin; 79,751 were retained per group after matching. The composite outcome occurred in 40.4% versus 33.3% (HR 1.28, 95% CI 1.26–1.30; p < 0.0001). Reduced albumin was associated with higher all-cause mortality (HR 1.50), myocardial infarction (HR 1.36), heart failure (HR 1.22), ventricular arrhythmias (HR 1.41), and Takotsubo cardiomyopathy (HR 1.41; all p < 0.005). Atrial fibrillation or flutter did not differ (HR 1.02; p = 0.779). A dose–response was observed, with severe hypoalbuminemia conferring greater composite risk (HR 1.49) than mild (HR 1.16). Findings were consistent across all sensitivity analyses. Conclusions: Reduced admission serum albumin is independently associated with higher short-term mortality and cardiovascular complications after ICH and may aid early risk stratification. Prospective studies are needed to clarify its utility. Full article

Background: Arterial ischemic stroke (AIS) is not common in pediatric patients; however, it causes significant morbidity and mortality. Reperfusion therapies, including intravenous thrombolysis (IVT) and endovascular mechanical thrombectomy (EVT) are established standards of care in selected adults with acute ischemic stroke; however, their safety and functional outcomes in the pediatric population remain poorly defined. Objective: To assess the safety and functional outcomes of reperfusion therapies in children with AIS. Methods: A systematic search was conducted across major databases including PubMed, Medline, Scopus, Embase, Web of Science, and Cochrane Library. Studies reporting on pediatric patients aged 18 years or less treated with IVT, EVT, or both for acute AIS were included. The primary safety outcome was the risk of developing symptomatic intracerebral hemorrhage (sICH). Primary functional outcomes were 90-day functional independence, measured via the Pediatric Modified Rankin Scale (Ped-mRS ≤ 2) or Pediatric Stroke Outcome Measure (PSOM ≤ 1). Secondary outcomes measured included successful recanalization (Modified Thrombolysis in Cerebral Ischemia [mTICI] grade 2b/3), and death due to any cause at 90 days. Results: Successful angiographic recanalization evaluated across thrombectomy and bridging arm cohorts revealed high success rate with the pooled proportion of 87.4% (95% CI: 79.1–93.9%). Reperfusion therapies are associated with significant early neurological recovery and favorable 90-day functional outcomes (Ped-mRS 0–2 achieved in a substantial majority of treated cohorts), when compared to the best medical treatment (BMT) controls. The overall rate of sICH remains low (<2%), demonstrating a much better safety profile comparable to adult benchmarks. Conclusions: Acute reperfusion therapies in pediatric AIS are associated with high rates of recanalization and favorable functional outcomes and had low observed rates of symptomatic intracranial hemorrhage in selected pediatric observational cohorts. However, given the absence of randomized controlled trials, these findings reflect observational associations and must be interpreted with appropriate clinical caution. Therefore, there is need for further prospective international studies capable of generating higher-quality evidence to guide future pediatric stroke management. Full article

Spontaneous pediatric intracerebral hemorrhage (sICH) is a rare but devastating neurological emergency associated with high mortality and long-term disability. Existing prognostic scores rely on a reduced number of variables and have shown limited validation, highlighting the need for comprehensive tools. This study describes the protocol for the development and internal validation of the CLIMPOUT (Clinical, Laboratory, and Imaging Predictive Outcome) score, a multimodal model designed to improve early prognostic assessment in pediatric sICH. This single-center retrospective cohort study will include consecutive patients (1 month–18 years) admitted to a tertiary pediatric intensive care unit (PICU) with spontaneous sICH between 2018 and 2025. Predictor variables will be restricted to baseline information available at PICU admission, including demographics, clinical status, laboratory markers, and quantitative neuroimaging features. Hematoma and intraventricular hemorrhage volumes will be measured using standardized three-dimensional segmentation. The primary outcome will be poor neurological status at 12 months, defined by the Pediatric Stroke Outcome Measure (PSOM). We will develop a multivariable logistic regression model following contemporary recommendations, including prespecified predictor selection, multiple imputation for missing data, and internal validation by 1000 bootstrap resamples. The CLIMPOUT score is expected to identify independent predictors of poor neurological outcome and provide a standardized, multimodal risk stratification model with improved prognostic performance compared with currently available pediatric scores. This protocol establishes a rigorous framework for developing a clinically applicable prediction model that may support early individualized decision-making, optimize neurocritical care management, and provide the foundation for future multicenter validation. Full article

Background: Systemic inflammation plays a critical role in secondary brain injury after spontaneous intracerebral hemorrhage (ICH). The pan-immune-inflammation value (PIV) has recently emerged as a novel composite inflammatory biomarker; however, its prognostic significance in critically ill ICH patients remains unclear. Methods: This retrospective cohort study included 111 consecutive adult patients admitted to the intensive care unit (ICU) with spontaneous ICH between January 2020 and December 2024. PIV, neutrophil-to-lymphocyte ratio (NLR), platelet-to-lymphocyte ratio (PLR), and conventional clinical predictors were evaluated at ICU admission. The primary outcome was 28-day mortality, while the mechanical ventilation (MV) requirement was assessed as a secondary outcome. Receiver operating characteristic (ROC) analysis and logistic regression models were used to evaluate prognostic performance. Results: MV was required in 78 patients (70.3%), and 41 patients (36.9%) died within 28 days. Patients requiring MV had significantly higher PIVs than non-ventilated patients (p = 0.013), whereas PIVs did not differ significantly between survivors and non-survivors (p = 0.539). For predicting MV requirement, GCS score demonstrated the highest discriminative performance (AUC = 0.922), followed by ICH score (AUC = 0.874), procalcitonin (AUC = 0.861), and NLR (AUC = 0.832), whereas PIV showed modest discrimination (AUC = 0.650). For 28-day mortality, procalcitonin achieved the highest AUC (0.800), while PIV showed poor predictive performance (AUC = 0.535). In multivariable analysis, NLR and procalcitonin remained independently associated with both MV requirement and 28-day mortality. PIV was not included in the final multivariable models because of its overlap with NLR; moreover, it did not provide meaningful incremental prognostic value when added to the reference models. Conclusions: In this single-center cohort of ICU-admitted patients with spontaneous ICH, PIV did not add meaningful prognostic value beyond established clinical and inflammatory predictors. These findings do not support the routine use of PIV for early risk stratification in this specific population; simpler markers, particularly NLR and procalcitonin, may be preferred when interpreted alongside established clinical severity measures. Full article

Background/Objectives: Venous thromboembolism (VTE) is a common and potentially preventable complication after hemorrhagic stroke, yet the optimal timing of pharmacologic prophylaxis remains uncertain because of concern for hematoma expansion or rebleeding. Repeat neuroimaging is frequently used to assess hemorrhage stability before initiating deep vein thrombosis (DVT) chemoprophylaxis, although the value of radiographic stability alone remains unclear. This review evaluates the evidence supporting imaging-guided initiation of prophylaxis after intracerebral hemorrhage (ICH) and aneurysmal subarachnoid hemorrhage (aSAH). Methods: A narrative review of the literature was performed focusing on hemorrhage expansion, thrombotic risk, repeat neuroimaging, and timing of pharmacologic prophylaxis in spontaneous ICH and aSAH. Observational studies, limited randomized data, and current guideline recommendations were assessed. Results: In spontaneous ICH, hematoma expansion risk is greatest within the first 24 h, whereas thrombotic risk increases over subsequent days because of immobility and systemic inflammation. Available evidence suggests that early low-dose anticoagulant prophylaxis may be safe in selected patients with stable hemorrhage, although definitions of stability vary and no prospective study has validated repeat imaging as an independent decision trigger. In aSAH, rebleeding risk depends more heavily on aneurysm securement and procedural factors than on imaging appearance alone. Conclusions: Repeat neuroimaging provides important reassurance after hemorrhagic stroke but does not fully capture ongoing biological risks. Current evidence supports a cautious, individualized approach in which radiographic stability informs, but does not independently determine, the timing of pharmacologic VTE prophylaxis. Full article

Objectives: This study investigated the prognostic value of the CNS-LAND score in predicting Intensive Care Unit (ICU) mortality among patients admitted with spontaneous intracerebral hemorrhage (ICH). Methods: In this single-center, retrospective cohort study, 305 adult ICU patients with spontaneous ICH (September 2022–March 2026) were included. The primary endpoint was ICU mortality. Prognostic performance was evaluated using receiver operating characteristic (ROC) curve analysis and the bootstrap-based DeLong method. The independent contribution of CNS-LAND beyond the Glasgow Coma Scale (GCS) was assessed using partial correlation and logistic regression analyses. Results: ICU mortality occurred in 71 of 305 patients (23.3%; median age 66.0 years). CNS-LAND scores were significantly higher in non-survivors than survivors (median 6.0 vs. 3.0, p < 0.001). ROC analysis showed the highest discriminative performance for GCS (AUC: 0.925), followed by Sequential Organ Failure Assessment (SOFA) (AUC: 0.906), Acute Physiology and Chronic Health Evaluation II (APACHE II) (AUC: 0.840), and CNS-LAND (AUC: 0.816; p = 0.467 vs. APACHE II). At a cutoff of ≥5, CNS-LAND yielded 83.1% sensitivity, 70.9% specificity, and a negative predictive value of 93.3%. Spearman analysis revealed near-perfect collinearity between National Institutes of Health Stroke Scale (NIHSS) and GCS (rs = −0.964, p < 0.001). After controlling for GCS, CNS-LAND lost statistical significance (partial rs = −0.051, p = 0.373), and logistic regression confirmed no independent prognostic contribution beyond GCS (LRT: χ² = 0.121, p = 0.728). Conclusions: CNS-LAND demonstrated mortality prediction performance comparable to APACHE II in critically ill ICH patients. However, this apparent performance was almost entirely attributable to the score’s NIHSS component: NIHSS and GCS were near-perfectly collinear (rs = −0.964), and after adjustment for GCS, CNS-LAND was no longer significantly associated with mortality (partial rs = −0.051, p = 0.373; likelihood-ratio test p = 0.728; ΔAUC ≈ 0.000). CNS-LAND therefore provides essentially no independent prognostic information beyond GCS in this population, indicating that its discriminative performance is redundant with, rather than complementary to, standard neurological assessment. This redundancy is rooted in the parallel progression of neurological deficit and consciousness characteristic of severe ICH—a relationship fundamentally distinct from the acute ischemic stroke population in which CNS-LAND was originally derived. Full article

Intracerebral hemorrhage (ICH) is a devastating stroke subtype in which secondary brain injury is driven by oxidative stress, iron overload, ferroptosis, neuroinflammation, blood–brain barrier disruption, and defective hematoma clearance. Nrf2 is a redox-sensitive transcription factor that coordinates antioxidant defense, iron handling, inflammatory regulation, and neurovascular unit protection through downstream effectors such as HO-1, NQO1, GPX4, and SLC7A11. Plant-derived natural compounds have been widely investigated in experimental ICH models; however, increased Nrf2 expression or nuclear translocation alone does not establish Nrf2-dependent neuroprotection. Here, we critically appraise preclinical evidence linking plant-derived natural compounds to Nrf2-centered signaling in ICH and classify the evidence into three levels: causal Nrf2-dependent evidence, Nrf2-associated evidence, and indirect or context-transferred evidence. Representative flavonoids, phenolics, terpenoids, lignans, steroidal lactones, and other bioactive compounds are evaluated with attention to ICH-model relevance, causal pathway validation, pharmacokinetic limitations, brain exposure, and therapeutic window. Current evidence indicates that only a limited subset of compounds has been validated by genetic or pharmacological Nrf2 inhibition, whereas most remain supported by pathway association rather than causality, and preclinical studies rely predominantly on young healthy rodent models with early post-ICH intervention. Notably, no compound currently reaches relatively high translational priority because perihematomal brain exposure, delayed-treatment efficacy, and long-term safety evidence remain largely unavailable. We therefore propose an evidence-based prioritization framework integrating Nrf2 causality, ICH-specific efficacy, brain bioavailability, and translational readiness. This review clarifies the mechanistic boundaries of Nrf2-targeted natural compounds and outlines priorities for rigorous translational research in ICH. Full article

Background/Objectives: Spontaneous intracerebral hemorrhage (ICH) is associated with high mortality and disability. We aimed to identify clinical, laboratory, and imaging factors independently associated with 3-month functional outcome across non-contrast computed tomography (NCCT) morphological markers, laboratory biomarkers, and established clinical scoring systems. Methods: This retrospective cohort study included 337 consecutive patients with spontaneous ICH admitted between 2019 and 2022. Admission clinical findings, laboratory parameters, NCCT morphological markers (swirl, blend, black hole, island, hypodensities, and satellite signs), volumetrically segmented hematoma volumes, and prognostic scores (ICH and FUNC scores) were recorded. Poor functional outcome was defined as modified Rankin Scale (mRS) 3–6 at 3 months. Independent predictors were identified using a primary Firth penalized multivariable logistic regression model; discrimination (area under the ROC curve, AUC), calibration, and optimism-corrected performance (1000-resample bootstrap) were assessed, and incremental value over the ICH and FUNC scores was tested with the DeLong method. Results: Poor functional outcome occurred in 60.2% of patients, and 3-month mortality was 36.8%. In the primary penalized model, independent predictors of poor outcome were lower admission Glasgow Coma Scale, larger hematoma volume, NCCT hypodensities, history of hypertension, and lower low-density lipoprotein (LDL) cholesterol. The model showed good discrimination (apparent AUC 0.881; optimism-corrected 0.872) and calibration (slope 0.92) and significantly outperformed the ICH and FUNC scores (DeLong p = 0.009 and p < 0.001, respectively). Several laboratory and treatment variables reached significance only in an unpenalized model and were statistically unstable; these were treated as exploratory. Although swirl, blend, black hole, and island signs were associated with poor outcomes in univariable analysis, they did not remain independent predictors in the final model. The ICH and FUNC scores were significantly associated with poor functional outcome in univariable analysis. Conclusions: Poor 3-month functional outcome after spontaneous ICH is independently associated with neurological severity, hematoma volume, NCCT hypodensities, and selected clinical and laboratory factors. Integrating clinical, volumetric, and CT morphological parameters improved discrimination over established prognostic scores; however, these findings are associative and require prospective, multicenter validation before clinical implementation. Full article

Intracerebral hemorrhage (ICH) remains one of the most severe forms of stroke and is associated with high mortality, poor functional outcomes, and substantial healthcare burden worldwide. Despite advances in neurocritical care and minimally invasive surgical techniques, the management of ICH remains challenging because of disease heterogeneity, rapid neurological deterioration, and the lack of effective individualized treatment strategies. In recent years, artificial intelligence (AI) has emerged as a promising tool for improving the diagnosis, prognostic evaluation, and precision management of ICH. A systematic literature search was performed in PubMed, Web of Science, and Embase to identify studies on AI applications in ICH, with predefined inclusion criteria focusing on imaging analysis, prognostic prediction, clinical decision support, and minimally invasive surgery. This review summarizes the major clinical applications, limitations, and future directions of AI in ICH, including multimodal foundation models, intelligent surgical assistance, and personalized precision care. Recent studies have demonstrated that AI-based models can significantly improve the accuracy of hematoma segmentation, hematoma expansion prediction, and functional outcome prognostication compared with conventional approaches. Despite encouraging progress, several important barriers continue to limit clinical translation, including data heterogeneity, limited external validation, insufficient interpretability, ethical and regulatory concerns, and challenges in workflow integration. Overall, AI has the potential to transform ICH management from conventional experience-based practice to data-driven, personalized, and precision neurosurgical care. Full article

Computed tomography (CT) scan is a widely used, non-invasive, sensor-based imaging technique that provides critical intracranial information for rapid stroke assessment. Accurate segmentation of intracerebral hemorrhage (ICH) in sensor-derived CT images is vital for clinical decision-making. Effective intelligent analysis of CT images is key to achieving reliable computer-aided diagnosis. However, existing deep learning methods struggle with complex ICH lesions characterized by blurred boundaries, irregular shapes, and large-scale variations. To address these challenges, this paper proposes TransAMGNet, a hybrid U-shaped network with Transformer integration for ICH CT image segmentation. The network is built on a residual U-Net backbone and introduces a Transformer encoder to strengthen global context modeling, thereby improving the representation of complex lesion morphology. Specifically, in the encoding stage, we design an Adaptive Dual-branch Channel Attention Module (ADCAM), which jointly models global and local channel information to enhance the model’s sensitivity to important feature responses. In the skip-connection pathway, we introduce a Multi-scale Feature Enhancement Module (MFEM), which preserves high-resolution spatial details while supplementing multi-scale contextual information to improve shallow-deep feature fusion. During decoding, a Gate-enhanced Dynamic Upsampling Module (GDUM) is constructed to improve the recovery of lesion boundaries and fine-grained structures through the synergy of gated recalibration and content-aware upsampling. The proposed method is systematically evaluated through comparative experiments and ablation studies. Experimental results show that TransAMGNet outperforms competing methods across multiple evaluation metrics, achieving Dice, Recall, IoU, Precision, and HD95 values of 90.47 ± 0.58%, 87.83 ± 3.71%, 81.26 ± 0.78%, 91.13 ± 0.95%, and 32.94 ± 1.1, respectively. The ablation studies further verify the effectiveness of each module. These results demonstrate that TransAMGNet can effectively improve segmentation performance for complex ICH lesions. Full article

Herpes simplex virus encephalitis (HSVE) is the most common infectious encephalitis and is associated with high morbidity and mortality when not treated in time. Symptoms include fever, headache, fatigue, neurological deficits such as aphasia and epileptic seizures. While hemorrhagic transformation is a common complication in HSVE, intracerebral hematoma (ICH) as the initial or main presentation is rare. We present two patients with HSVE who displayed a large temporal hematoma as the main finding on cerebral imaging. We further conducted a systematic literature review to identify all published cases of ICH in HSVE. Forty-nine publications met the inclusion criteria, describing a total of 55 patients. In 38 of these, HSVE could be definitely confirmed by brain biopsy, autopsy or PCR. We analyzed these cases according to age, gender, lag from symptom onset to hospital admission, lag from hospital admission to detection of hemorrhage, location of encephalitis and hemorrhage, received treatment and outcome. With a median age of 45 years, this cohort is significantly younger than general HSVE populations described previously. In conclusion, our review shows that, albeit rare, awareness about ICH complicating HSVE is highly relevant as failure to recognize an atypical course of HVSE may result in a delay of effective antiviral treatment, which is related to an unfavorable or even fatal outcome. Full article