Search Results (514)

Accurate and automated segmentation of ischemic stroke lesions from magnetic resonance imaging (MRI) data is crucial for rapid clinical diagnosis, treatment planning, and patient prognosis. This study presents a comprehensive evaluation of various deep learning architectures for segmenting acute and subacute ischemic lesions using the multicenter ISLES 2022 dataset. We compare traditional 3D U-Net models, attention mechanisms, and modern hybrid architectures, specifically Swin-UNETR (Swin Transformer-based UNet TRansformer). Our experiments utilize multimodal MRI data, including diffusion-weighted images (DWI) and apparent diffusion coefficient (ADC) maps. Results demonstrate that the Swin-UNETR architecture, combined with a specialized pad or crop preprocessing pipeline, advanced data augmentation using the TorchIO library, and a combined Dice–Cross Entropy (DiceCE) loss function, provides competitive performance. The best Swin-UNETR model achieved a Dice of 0.717, precision of 0.793, recall of 0.708, and HD95 of 12.24 mm on the validation set, with a loss of 0.26. The baseline 3D U-Net achieved a comparable Dice of 0.726, while Swin-UNETR showed higher precision, recall, and lower HD95. This study highlights the effectiveness of integrating hierarchical transformers with convolutional decoders for extracting both local and global contextual information in complex medical imaging tasks. Full article

We present interesting diagnostic images from a 77-year-old man with chronic coronary artery disease, a history of coronary artery bypass grafting (CABG), and no documented history of myocardial infarction who underwent coronary computed tomography angiography (CCTA) to assess graft patency. No operative report, previous medical documentation, or earlier cardiac imaging studies were available. CCTA demonstrated patent grafts from the left internal mammary artery to the left circumflex coronary artery (LIMA–LCx) and from the ascending aorta to a diagonal branch (aorto-diagonal graft). A stump-like protrusion of the ascending aorta was considered most consistent with the residual proximal segment of an occluded saphenous vein graft, presumably previously directed to the right coronary artery. In addition, an incidental broad-necked, partially lobulated, contrast-filled outpouching measuring approximately 28 × 17 × 29 mm was identified within the basal membranous interventricular septum. Multiplanar and multiphase reconstructions demonstrated a subannular neck communicating directly with the left ventricular outflow tract (LVOT), preservation of the muscular interventricular septum, separation from the sinus of Valsalva, and phase-dependent rightward protrusion toward the basal right ventricle. These anatomical features favored an interventricular membranous septal aneurysm (IVMSA). Because no CMR was performed, remote clinically silent ischemic injury could not be completely excluded. Overall, the lesion was considered most consistent with IVMSA; its congenital or developmental origin and temporal evolution could not be established in the absence of prior imaging and clinical documentation. This case highlights the diagnostic value of thin-section, multiphase CCTA for characterizing a septal outpouching and distinguishing IVMSA morphology from a sinus of Valsalva aneurysm and acquired postoperative or ischemic alternatives. Full article

Background: Postoperative peritoneal adhesions arise from a dysregulated wound-healing response in which macrophages may have context-dependent effects. We investigated the contribution of macrophage-rich peritoneal and mesenteric compartments, the origin of macrophage-like cells in ischemic lesions, and the association between CCR2-dependent recruitment and postoperative inflammatory and reparative gene expression. Methods: Using a murine ischemic-button model, we assessed the effects of clodronate liposome treatment, bone marrow chimerism, and global CCR2 deficiency. Adhesion formation, F4/80+ cell accumulation, donor-marker expression, and selected inflammatory and wound-healing-associated transcripts were analyzed at predefined postoperative time points. Results: Clodronate liposome treatment was associated with reduced adhesion formation and substantial depletion of F4/80+ cells in peritoneal lavage and mesenteric tissue. However, F4/80+ cell numbers within ischemic buttons at postoperative day 3 were not significantly reduced, indicating that the depletion experiment does not establish selective depletion of all lesional macrophages. Bone marrow chimera experiments identified donor-marker-positive, F4/80+ cells within ischemic buttons, supporting recruitment of hematopoietic cells with a macrophage-like phenotype. CCR2 deficiency reduced F4/80+ cell accumulation in ischemic buttons and was associated with increased adhesion scores and altered expression of inflammatory and wound-healing-associated genes. These findings identify differential associations of clodronate-sensitive macrophage-rich compartments and CCR2-dependent hematopoietic recruitment with postoperative adhesion formation. Conclusions: Depletion of macrophage-rich peritoneal and mesenteric compartments was associated with reduced adhesion formation, whereas global CCR2 deficiency was associated with fewer lesional F4/80+ cells and greater adhesion severity. Because clodronate depletion, F4/80 staining, bone marrow chimerism, and global CCR2 deficiency do not provide cell-specific or fate-mapped resolution, these data do not establish distinct resident versus infiltrating macrophage functions or a reparative phenotype of CCR2-dependent cells. Cell-specific and temporally resolved validation is required to define the contributions and temporal relationships of individual macrophage subsets. Full article

Stroke is one of the leading causes of mortality and long-term neurological disability worldwide, and early diagnosis through accurate disease classification directly affects treatment success. Rapid differentiation of hemorrhagic and ischemic stroke on computed tomography (CT) images, together with accurate determination of the acute and chronic phase in ischemic cases, is of critical importance in the clinical decision-making process. In this study, StrokeCT-2C5K a two-center dataset comprising 5000 cranial CT images, was assembled specifically for this work. The images were reviewed by radiology specialists and assigned to one of four diagnostic categories: normal, hemorrhagic stroke, acute ischemic stroke, or chronic ischemic stroke. A Squeeze-and-Excitation (SE-Attention) mechanism was then integrated into DenseNet-121, ResNet-50, and EfficientNet-B3. From a biomimetic perspective, this channel-recalibration process provides a functional analogy to biological selective attention by giving greater weight to informative responses while reducing the influence of less relevant ones. All models were trained under the same training, validation, and test protocol; the standard CNN architectures were compared with their SE-Attention-enhanced counterparts. The results showed that the SE-Attention mechanism enables more effective learning of lesion-specific discriminative features by adaptively recalibrating channel-wise information, yielding an average classification accuracy improvement of 0.93 percentage points across all three architectures. The most pronounced improvements were observed in distinguishing ischemic from hemorrhagic stroke, as well as in distinguishing acute from chronic ischemic stroke. These findings show that a selective-information-processing strategy functionally analogous to biological attention can improve multi-class stroke classification across different CNN backbones. Full article

Background and Objectives: Biological correlates of baseline clinical responsiveness remain incompletely characterized in older adults with acute ischemic stroke treated with intravenous thrombolysis. We evaluated associations between admission Glasgow Coma Scale (GCS) and pre-thrombolysis hematologic, inflammatory, iron-status, and micronutrient parameters. Materials and Methods: This retrospective single-center cohort included 95 unique patients aged ≥65 years, all treated with intravenous alteplase between 2020 and 2024. Admission GCS ranged from 11 to 14. Spearman correlations used original GCS scores. Principal proportional odds models used ordered GCS categories of 11–12, 13, and 14, and were adjusted for age, sex, and admission National Institutes of Health Stroke Scale (NIHSS), with false discovery rate corrections. Sensitivity analyses additionally considered clinician-documented aphasia, congestive heart failure, atrial fibrillation, and reperfusion status for 24 h GCS change. Results: Admission GCS correlated most strongly with RDW-CV (rho = −0.843; 95% bootstrap CI, −0.892 to −0.774) and MCV (rho = 0.779; 95% CI, 0.668 to 0.866). Principal adjusted odds ratios per one-SD increase were 5.68 for hemoglobin, 3.01 for log-transformed ferritin, 4.71 for serum iron, 4.71 for log-transformed vitamin B12, 0.20 for C-reactive protein, and 0.019 for RDW-CV (all FDR-adjusted p < 0.001). Association directions remained consistent in sensitivity analyses. MCV showed an exploratory nonlinear association. No biomarker was associated with the direction of 24 h GCS change after FDR correction, including reperfusion-adjusted models. Conclusions: Pre-thrombolysis biological parameters were concurrently associated with baseline GCS within this single-center cohort and restricted GCS range. These associations do not establish causality, independence from unmeasured lesion location or infarct volume, predictive utility, or early neurological recovery. Prospective external validation is required. Full article

Background: Pediatric inflammatory multisystem syndrome (PIMS), also referred to as multisystem inflammatory syndrome in children (MIS-C), is a rare but serious post-infectious complication of severe acute respiratory syndrome coronavirus 2 (SARS-CoV-2) infection characterized by systemic hyperinflammation and multiorgan involvement. New-onset neurological and psychiatric symptoms have emerged as critical clinical features, occurring in approximately 12–27% of pediatric patients aged 2–15 years (median age, 10 years) and often indicating a more severe disease course. This narrative review aims to provide a comprehensive overview of the current literature regarding the neurological and psychiatric manifestations of PIMS/MIS-C, focusing on epidemiology, pathophysiology, clinical presentation, neuroimaging findings, biomarkers, treatment strategies, and outcomes. Methods: A narrative literature review was conducted to synthesize current evidence on the neurological and psychiatric spectrum of PIMS/MIS-C. Evaluated parameters included clinical presentations ranging from common symptoms (such as headache, encephalopathy, altered mental status, and seizures) to rare complications (such as ischemic stroke, acute disseminated encephalomyelitis, Guillain–Barré syndrome, and cerebral edema), alongside associated psychiatric disturbances, diagnostic findings, and therapeutic approaches. Results: Neurological and psychiatric manifestations significantly impact the clinical trajectory of PIMS/MIS-C. Acute symptoms include headache, encephalopathy, seizures, and psychiatric disturbances like behavioral changes, hallucinations, delirium, anxiety, and sleep disorders. Neuroimaging in many cases reveals reversible lesions of the splenium of the corpus callosum, while electroencephalography typically demonstrates diffuse slowing consistent with encephalopathy. Early recognition and prompt administration of immunomodulatory therapy—primarily intravenous immunoglobulin and corticosteroids—correlate with favorable neurological recovery in the majority of patients. However, current evidence remains largely observational and heterogeneous, precluding definitive causal conclusions regarding this treatment–outcome relationship. Affected children more frequently require intensive care unit admission and remain at risk for persistent cognitive, behavioral, and psychiatric sequelae. Conclusions: Neurological and psychiatric complications in PIMS/MIS-C are clinically significant indicators of disease severity that require vigilant monitoring and early immunomodulatory intervention. Continued multidisciplinary follow-up and prospective studies are essential to elucidate the long-term neurodevelopmental and psychiatric consequences and to optimize therapeutic strategies for these patients. Full article

Background/Objectives: Horizontal aorta, characterized by a high aortic angle, represents a challenging anatomical feature during transcatheter aortic valve replacement (TAVR), but its association with cerebral ischemic injury remains unclear. This study investigated the association between horizontal aorta and diffusion-weighted magnetic resonance imaging (DW-MRI)-detected cerebral infarctions after TAVR. Methods: We retrospectively enrolled 411 consecutive patients with severe aortic stenosis undergoing transfemoral self-expanding TAVR between March 2017 and May 2022. Aortic angle was defined as the angle between the aortic annular plane and the horizontal plane on preprocedural computed tomography, and horizontal aorta was defined as an aortic angle > 60°. Patients were categorized into horizontal aorta and non-horizontal aorta groups. The incidence, number, and volume of new DW-MRI lesions were compared between groups. Results: The median age was 74.0 years (interquartile range [IQR]: 69.0 to 79.0); 54.5% were male, and the median Society of Thoracic Surgeons score was 3.83% (IQR: 2.29 to 6.39). Horizontal aorta was present in 69 patients (16.8%). Procedural complications were infrequent and comparable between groups. Although the incidence of new cerebral infarctions was similar between groups (89.9% vs. 83.0%; p = 0.157), patients with horizontal aorta had more cerebral infarction lesions (median, 4.0 vs. 3.0; p = 0.031), larger total lesion volume (320.0 vs. 180.0 mm³; p = 0.017), and larger lesion volume per infarction (70.0 vs. 51.7 mm³; p = 0.036). Multivariable analysis identified horizontal aorta as an independent predictor of the number of post-TAVR cerebral infarctions. Conclusions: Horizontal aorta is relatively common among patients undergoing TAVR and is independently associated with a greater burden of DW-MRI-detected subclinical cerebral ischemic injury. Full article

Atherosclerosis (AS) is a lipid-driven chronic inflammatory disease and the principal pathological basis of coronary artery disease, ischemic stroke, and peripheral artery disease. Despite advances in lipid-lowering, antiplatelet, anti-inflammatory, and revascularization strategies, current treatments do not selectively modulate the heterogeneous cellular and inflammatory microenvironments within individual plaques. Cell membrane-coated nanoparticles (CMNs) have therefore emerged as biomimetic delivery platforms that combine the functional versatility of synthetic nanocores with selected biological properties of donor-cell membranes. This review summarizes the fabrication of CMNs and critically compares platelet-, macrophage-, neutrophil-, monocyte-, erythrocyte-, and hybrid membrane-coated nanoplatforms, together with emerging T-cell-targeted nanotherapeutic strategies. Particular attention is given to membrane-source selection, receptor–ligand interactions, immune evasion, lesion-directed accumulation, stimulus-responsive cargo release, and the modulation of inflammation, oxidative stress, lipid metabolism, and defective efferocytosis. We further discuss major translational barriers, including donor- and activation-state-dependent membrane heterogeneity, incomplete or unstable coating, manufacturing reproducibility, scalability, thrombogenicity, immunogenicity, and the limited predictive value of short-term small-animal models. A pathology-matched and minimum-sufficient-complexity framework is proposed to guide the rational development of safer, more reproducible, and clinically relevant biomimetic nanotherapies for AS. Full article

Accurate delineation of infarct core and ischemic penumbra in acute ischemic stroke primarily relies on computed tomography perfusion (CTP), where the arterial input function (AIF) is essential for reliable perfusion quantification. However, reliable and fast AIF selection remains challenging in clinical practice due to noise, vascular heterogeneity, and inter-patient variability in bolus dynamics. In this study, we propose TriAIF-RWKV, a three-stage framework for robust and automated AIF extraction. Specifically, ACSANet is first employed for spatial vascular localization using axial and channel-aware attention mechanisms, thereby narrowing the candidate arterial region and reducing the AIF search space. Then, a Dilated-RWKV network is introduced to model temporal intensity dynamics from a global sequence perspective, allowing robust identification of AIF-consistent patterns. Finally, a physiology-informed scoring strategy is used to select the optimal AIF by evaluating baseline stability, peak enhancement, and washout characteristics. Extensive experiments on CTP datasets were conducted from multiple perspectives, including AIF waveform fidelity, perfusion parameter estimation, and lesion-level analysis. The results demonstrate that the proposed method achieved high agreement with expert-selected AIFs, with a global waveform PCC of 0.973, peak correlation of 0.942, and TTP correlation of 0.973 with a mean error of 0.923 s. Furthermore, the proposed method provides more consistent downstream perfusion quantification, achieving higher consistency of CTP-derived parameters and improved lesion-to-normal tissue discrimination compared with existing approaches. These results highlight its potential for reliable clinical perfusion assessment. Full article

Background/Objectives: Computed tomography perfusion is widely used in acute ischemic stroke, but its performance is less reliable for lacunar and infratentorial infarcts. This technical review examines the acquisition and processing factors that influence their detectability. Methods: A targeted technical review of PubMed/MEDLINE, Scopus, and Web of Science was performed, focusing on acquisition, reconstruction, vascular input selection, deconvolution, filtering, spatial sampling, automated classification, posterior circulation stroke, and lacunar infarction. Results: Detectability depends on lesion size and contrast, posterior fossa artifacts, spatial and temporal resolution, vascular curve quality, mathematical stabilization, and automated thresholds. Larger cerebellar infarcts may remain visible, whereas brainstem, deep cerebellar, and perforator lesions are more vulnerable. Temporal maps and direct review of parametric images may reveal abnormalities absent from automated summaries. Conclusions: This technical review shows that computed tomography perfusion should be interpreted as a derived estimate rather than a direct representation of cerebral hemodynamics. Negative automated findings do not exclude lacunar or infratentorial infarction when clinical suspicion remains high. Full article

Background and Objectives: Identification of obstructive coronary artery disease (CAD) in patients presenting with a dilated cardiomyopathy phenotype is clinically important because it may influence etiologic classification, prognosis, and subsequent management. However, real-world angiography-based data on the prevalence and angiographic severity of obstructive CAD in this setting remain limited, particularly in regional single-center cohorts. Materials and Methods: This retrospective single-center cohort study included consecutive patients presenting with a newly diagnosed dilated cardiomyopathy (DCM) phenotype of initially unknown etiology who underwent first-time diagnostic invasive coronary angiography at St. Marina University Hospital, Varna, Bulgaria, between January 2010 and December 2025. Obstructive CAD was defined as stenosis >70% in a major epicardial coronary artery with a reference vessel diameter >2.5 mm. Patients were categorized as having non-obstructive or no significant coronary stenoses, single-vessel disease, two-vessel disease, or three-vessel disease. Additional descriptive analysis assessed severe occlusive coronary lesions, defined as chronic total occlusions or subtotal stenoses. The primary endpoint was the prevalence of obstructive CAD. Secondary analyses included angiographic disease extent, vessel-level coronary involvement, severe occlusive lesions, and coronary revascularization. Results: A total of 107 patients were included. Mean age was 55.4 ± 10.9 years, and 97 patients (90.7%) were male. Obstructive CAD was identified in 19 patients (17.8%; 95% confidence interval [CI], 11.7–26.1%), whereas 88 patients (82.2%) had non-obstructive or no significant coronary stenoses. Among patients with obstructive CAD, 3 (15.8%) had single-vessel disease, 4 (21.1%) had two-vessel disease, and 12 (63.2%) had three-vessel disease. Severe occlusive coronary lesions were present in 10 of 19 patients (52.6%); 8 (42.1%) had at least one chronic total occlusion and 5 (26.3%) had at least one subtotal stenosis. Conclusions: In this retrospective single-center cohort of patients presenting with a dilated cardiomyopathy phenotype and referred for coronary angiography, obstructive CAD was present in fewer than one in five patients. In contrast, most had non-obstructive or no significant epicardial coronary stenoses. However, when obstructive CAD was present, three-vessel disease and severe occlusive lesions were frequent. These findings indicate that obstructive epicardial CAD was uncommon in this selected angiography-referred cohort while underscoring the clinical role of coronary angiography when an ischemic or mixed etiology is clinically suspected. Full article

Neonatal hypoxic–ischemic encephalopathy (HIE) remains one of the leading causes of neonatal mortality and long-term neurodevelopmental disability despite therapeutic hypothermia, which provides only partial neuroprotection. Among adjunctive therapies, magnesium sulfate (MgSO₄) has emerged as one of the most biologically plausible neuroprotective agents because of its ability to modulate glutamate-mediated excitotoxicity, intracellular calcium influx, oxidative stress, neuroinflammation, and apoptotic pathways. Nevertheless, encouraging molecular and preclinical findings have not translated into consistent clinical benefit. This narrative review critically examines the translational gap between the molecular mechanisms of magnesium sulfate and its clinical performance in neonatal HIE. Evidence from experimental models, clinical studies and recent meta-analyses was integrated to identify the biological and methodological factors potentially responsible for this discrepancy. We discuss the evolving pathophysiology of HIE across the primary, latent, secondary and tertiary phases of brain injury and analyze how the timing of intervention, lesion heterogeneity and inadequate biological stratification may influence therapeutic responsiveness. Current clinical research has largely evaluated broad neurological outcomes, particularly cerebral palsy, despite the heterogeneous neuropathological substrates underlying neonatal brain injury. We argue that this strategy may dilute genuine treatment effects by grouping together distinct lesion phenotypes with different biological mechanisms. Accordingly, we propose the “Neuroprotection per Effective Therapy (NET)” framework, a conceptual translational model integrating molecular targets, experimental evidence, MRI-defined lesion phenotypes, methodological quality, and advanced statistical approaches to improve patient stratification and outcome selection. Rather than questioning the biological efficacy of magnesium sulfate itself, this review suggests that future progress will depend on aligning molecular mechanisms with clinically meaningful phenotypes. Precision-based translational strategies may ultimately allow magnesium sulfate and other neuroprotective therapies to better reveal their therapeutic effects in biologically appropriate patient subgroups. Full article

Background/Objectives: Pediatric Takayasu arteritis (PTA) is a rare large-vessel vasculitis with limited data regarding neurological involvement. This study aimed to evaluate neurological manifestations and associated neuroimaging findings in a cohort of children with PTA. Methods: In this retrospective observational study, 22 patients diagnosed with PTA and followed at a tertiary center between January 2000 and April 2025 were included. Neurological symptoms, examination findings, and neuroimaging data were reviewed. Angiographic involvement was classified according to the Numano classification. Results: Neurological involvement was identified in 5 patients (22.7%), including ischemic stroke (n = 3) and hypertensive encephalopathy (n = 2). Neurological symptoms were present in 15 patients (68.2%), with headache being the most common manifestation (54%). Other symptoms included dizziness, paresthesia, visual disturbances, syncope, and seizures. Neuroimaging revealed ischemic lesions in a subset of patients, as well as nonspecific white matter changes. Angiographic evaluation showed a predominance of extensive disease patterns, particularly Type V and Type IV involvement. Conclusions: Neurological manifestations in pediatric Takayasu arteritis are common but often nonspecific. However, severe complications such as stroke and hypertensive encephalopathy may occur and can be the initial presentation. Careful neurological evaluation and the use of neuroimaging are essential for early detection and appropriate management. Full article

Cerebral venous sinus thrombosis (CVST) is an uncommon cerebrovascular disorder with heterogeneous manifestations and may occasionally precede the diagnosis of an underlying malignancy. We report the case of a 24-year-old man who presented with recurrent fever, headache, pharyngodynia, and systemic inflammation initially attributed to a sinonasal or odontogenic infectious process. He subsequently developed binocular horizontal diplopia, left abducens nerve palsy, papilledema, severe headache, and nausea. Neuroimaging demonstrated extensive CVST involving the left internal jugular vein, bilateral transverse sinuses, and superior sagittal sinus, without ischemic, hemorrhagic, or tumoral brain parenchymal lesions. Thrombophilia testing identified heterozygous prothrombin G20210A as the only established inherited thrombophilic factor. Despite initial neurological stabilization, the patient developed a rapidly recurrent frontal calvarial, epicranial, and cranio-dural lesion extending toward the superior sagittal sinus, without brain parenchymal involvement or imaging evidence of leptomeningeal disease. Initial morphological assessment suggested Langerhans cell histiocytosis. However, comprehensive histopathological and immunohistochemical reassessment demonstrated diffuse strong CD30 expression, nuclear and cytoplasmic ALK positivity, CD43 expression, and focal epithelial membrane antigen and granzyme B positivity, while CD1a and S100 were negative. These findings established the diagnosis of systemic ALK-positive anaplastic large cell lymphoma with secondary extra-axial cranio-dural involvement. Systemic staging demonstrated disseminated nodal disease and a noncontiguous cranio-dural extranodal lesion, consistent with stage IV disease. Treatment with anticoagulation and six cycles of brentuximab vedotin combined with cyclophosphamide, doxorubicin, and prednisone resulted in a favorable neurological and oncological outcome, with no metabolically active or residual enhancing disease on follow-up imaging. This case emphasizes the importance of continued etiological investigation in young patients with extensive CVST and an atypical clinical course, even when plausible infectious and inherited thrombotic risk factors coexist. Full article

Background/Objectives: Malignant cerebral edema (MCE) is an infrequent but devastating complication of acute ischemic stroke (AIS). Early, reliable identification of patients at risk remains a major clinical challenge. The purpose of this study was to evaluate SCR-U1.8, a single automated imaging biomarker integrating stroke lesion burden and cerebrospinal fluid reserve, for exploratory risk stratification of MCE after AIS. Methods: In this retrospective study, consecutive patients with AIS who underwent diffusion-weighted imaging (DWI) between January 2019 and October 2022 were screened. Stroke lesions were automatically segmented on initial DWI using an ADC threshold of <1.8 × 10⁻³ mm²/s to derive U1.8 lesion volume. Cerebrospinal fluid volume (CSFV) was automatically estimated within the intracranial compartment, and SCR-U1.8 was calculated as U1.8/CSFV. Four low-complexity prediction strategies were evaluated: U1.8 > 82 mL, U1.8 > 145 mL, single-predictor U1.8 logistic regression, and single-predictor SCR-U1.8 logistic regression. Performance was evaluated across 100 repeated stratified patient-level train–test splits. Random undersampling was restricted to the training data, and no synthetic samples were generated. Model performance was assessed by accuracy, sensitivity, specificity, precision, negative predictive value (NPV), F1 score, receiver operating characteristic area under the curve (ROC-AUC), and average precision (AP) as appropriate. Results: A total of 530 patients were included, comprising 198 women and 332 men (mean age, 68 ± 14 years); a total of 12 patients developed MCE. Across 100 repeated stratified train–test splits, SCR-U1.8-LR achieved the highest accuracy (0.990 ± 0.006), precision (0.759 ± 0.150), specificity (0.992 ± 0.005), F1 score (0.806 ± 0.131), ROC-AUC (0.998 ± 0.002), and average precision (0.935 ± 0.062). Compared with the U1.8 > 82 mL threshold, SCR-U1.8-LR achieved significantly higher accuracy, precision, specificity, and F1 score, although sensitivity decreased from 1.000 to 0.900 and NPV decreased slightly from 1.000 to 0.998. Conclusions: SCR-U1.8 may provide a simple and physiologically interpretable measure of stroke lesion burden relative to CSF reserve. The findings remain exploratory because only 12 independent MCE events were available and require external validation. Full article