Growing interest in perivascular spaces (PVS) quantification has highlighted the need for accurate and robust methods, particularly in magnetic resonance imaging (MRI). The Frangi filter is widely used to enhance tubular structures, including PVS, however its performance is highly dependent on scale selection. In the context of computer vision, "scale" refers to the size of the structures or features being detected by a filter or detector. In multiscale filtering, multiple scales are used to capture structures of varying sizes, and an optimal scale corresponds to the size at which a structure of interest is best enhanced or detected. Despite advancements in multiscale filtering techniques, determining an optimal scale for PVS quantification remains an open challenge. We introduce SCALR, a machine learning-based approach for scale selection in Frangi filtering to improve PVS quantification. A linear regression model, trained on synthetic and real MRI data, is used to infer an optimal scale based on a range of noise levels and voxel sizes across various imaging conditions. The findings indicate that SCALR enhances PVS detection, particularly in low signal-to-noise ratio MRI. By automating scale selection, SCALR increases the reliability of quantification and provides a scalable solution for integrating Frangi-based PVS analysis into clinical and research workflows.

Spatial navigation deficits emerge early in Alzheimer's disease and related dementias (ADRD), yet their potential as a training target and source of digital biomarkers remains underexplored. We evaluated a smartphone-based, unsupervised wayfinding training in 58 cognitively unimpaired older adults and characterized multi-day learning trajectories derived from digital behavioral readouts in relation to neurobiological risk and reserve markers. Participants completed six training sessions navigating to points-of-interest on a university campus, with continuous GPS and app interaction recording. Compared with walking-only controls, participants improved in a pointing task and map drawing, but not in a visuospatial memory task. Higher MTL tau was associated with reduced improvements in navigation efficiency in individuals with greater hippocampal vessel distance. Higher cerebrovascular dysfunction was linked to attenuated learning on readouts reflecting information-processing demands. These findings demonstrate that real-world digital navigation training improves spatial cognition and multi-day learning trajectories show domain-specific associations with ADRD-related biomarkers.

Preserving cognitive and brain health is central for healthy aging. Cognitive reserve (CR) and brain maintenance (BM) support resilience against age- and disease-related cognitive decline. Physical fitness represents a plausible pathway to both CR and BM, yet the underlying neurobiological mechanisms remain insufficiently understood. This study examined how fitness relates to Alzheimer’s pathology and whether it moderates or mediates the pathology–cognition relationship. Data were obtained from 345 cognitively unimpaired older adults (mean age = 73.11 ± 8.03 years; 177 females) participating in the ongoing SFB1436 study. We assessed global cognition and delayed verbal memory performance, aerobic fitness (VO₂max), and muscular capacity. Blood biomarkers included plasma Aβ₁₋₄₂/Aβ₁₋₄₀, p-tau217, and GFAP (glial fibrillary acidic protein), and serum BDNF (brain-derived neurotrophic factor), VEGF (vascular endothelial growth factor), and Cathepsin-B. Neuroimaging measures comprised medial temporal lobe (MTL) tau burden ([¹⁸F]PI-2620 PET), MRI-derived hippocampal volumes, white matter hyperintensities, perivascular spaces (PVS) in basal ganglia (BG) and centrum semiovale, gray matter volume (GMV), and MTL thickness. To examine BM, we tested associations between fitness and brain pathology. To examine CR, we conducted moderation analyses assessing whether fitness attenuated the negative impact of pathology on cognition. Mediation analyses further evaluated whether hippocampal volume, total GMV, or MTL thickness mediated a potential association between fitness and cognition. All models controlled for age and sex (and education in mediation analyses), and multiple comparisons were FDR-corrected. Physical fitness was not related to cognitive performance. Higher muscular capacity was associated with lower BG PVS volumes, while higher aerobic fitness was related to higher MTL thickness and total GMV. Elevated MTL tau burden was associated with poorer verbal memory performance. Although physical fitness did not significantly moderate the tau–memory relationship, model comparison provided weak evidence for CR effects (p = .015). Muscular capacity was linked to lower BG PVS volumes, supporting resistance against pathology, while aerobic fitness related to preserved cortical integrity and tended to act as a CR proxy against MTL tau pathology. Physical fitness may support cerebrovascular and glymphatic function, thereby promoting cognitive resilience and extending healthspan by sustaining functional brain health and mitigating tau-related cognitive decline. The study was retrospectively registered in the German Clinical Trials Register (DRKS00032449; date of registration: 2025-05-07; recruiting ongoing).

BACKGROUND:Centrum semiovale perivascular spaces (CSO PVS) are common to different cerebral small vessel disease (CSVD) subtypes, yet their enlargement to the point of visibility on magnetic resonance imaging is thought to occur through distinct mechanisms. In cerebral amyloid angiopathy (CAA), CSO PVS are thought to reflect impaired perivascular Aβ (amyloid-β) drainage, whereas in deep perforator arteriopathy (DPA) they may result from microangiopathy-related arterial stiffening and altered fluid dynamics. The extent to which this can be confirmed in vivo remains unclear. METHODS:We retrospectively analyzed 186 patients with CSVD and cerebrospinal fluid (CSF) Aβ biomarkers (n=111 probable CAA, n=75 DPA). CSO PVS were counted on axial T2-weighted images. Associations between CSO PVS and CSF biomarkers were assessed via Pearson correlation and multivariable linear regression, including an interaction term between CSF Aβ and CSVD subtype, adjusted for demographics and neuroimaging markers of CSVD. RESULTS:Patients with higher CSO PVS counts were generally younger, had lower white matter hyperintensity burden, higher basal ganglia PVS counts, and were more frequently affected by cortical superficial siderosis. CSO PVS counts were similar in patients with CAA and DPA. The association between CSF Aβ42/40 ratio and CSO PVS burden was observed in patients with CAA, but not in those with DPA (interaction term between CSF Aβ42/40 ratio and CAA: β=-0.27; P=0.016), independent of demographics and other neuroimaging markers of CSVD. CSF Aβ40 showed no association with CSO PVS counts in any model. CONCLUSIONS:Our findings strengthen the pathophysiological link between CSO PVS and Aβ pathology in CAA but not in DPA. These results extend previous histopathologic and neuroimaging work and underscore the need to interpret CSO PVS in the context of underlying CSVD subtype.

Chronic psychosocial stress (CPS) is associated with adverse brain and mental health outcomes. Effects on the cerebral microvasculature have been proposed as an underlying mechanism, although this remains to be established. Here, we examined the association between CPS and an early marker of microvascular dysfunction, magnetic resonance imaging (MRI)-visible perivascular spaces (PVS). Analyses were conducted in two cohorts of healthy young adults (N = 61; ages 18-43 years; 88% male) using high-resolution 3T MRI and an automated PVS quantification pipeline. CPS was assessed using the Perceived Stress Scale (PSS-10). We applied a two-step meta-analytic framework and controlled for known allostatic factors impacting PVS, including age, body mass index and mean arterial pressure. In accordance with our hypothesis, individuals with higher CPS had significantly higher fractional PVS volumes in the centrum semiovale (CSO), in particular in the frontal and occipital lobes (pFDR < .05). No such effect was found in the basal ganglia, or in the CSO subdivision, parietal, and temporal lobes (pFDR > .09). Our findings indicate that CPS may contribute to subtle, centrum semiovale specific microvascular alterations even in healthy young adults. Future multimodal research including inflammatory marker and blood-brain barrier measures may help to elucidate mechanistic pathways. ### Competing Interest Statement MW is a member of the following advisory boards and gave presentations to the following companies: Boehringer Ingelheim, Germany; and Biologische Heilmittel Heel GmbH, Germany. MW has further conducted studies with institutional research support from Biologische Heilmittel Heel GmbH and Janssen Pharmaceutical Research unrelated to this investigation. VE is a member of the advisory board of Biologische Heilmittel Heel GmbH, Germany. LH is currently employed by Biologische Heilmittel Heel GmbH. All companies had no role in the design, conduct, or reporting of this study. All other authors report no biomedical financial interests or other potential conflicts of interest. ### Funding Statement The present work was supported by: for LC Interdisciplinary Center of Clinical Research of the Medical Faculty Jena (AMS-21), Federal Ministry for Research, Technology and Aeronautics through German Center for Mental Health (01EE2507F); for MW Eberhard Karls University Tuebingen Fortune Projekt (nr. 2394-0-0), BMFTR (16SV8590), BMFTR through DZPG (01EE2305A/01EE2305F; 01EE2505A/01EE2505F; 01EE2507F). Computational PVS quantification was supported by The Galen and Hilary Weston Foundation under the Novel Biomarkers 2019 scheme (ref UB190097) administered by the Weston Brain Institute and the Row Fogo Centre for Research into Ageing and the Brain (AD.ROW4.35. BRO-D.FID3668413). It is also funded by UK Dementia Research Institute funded by UKDRI Ltd which received its funding from the UK Medical Research Council, Alzheimer Society and Alzheimer's Research UK (DRIEdi17/18, UKDRI-4002 UKDRI-4205). Funding sources had no role in the study design, data collection, analysis, and interpretation, the writing of the report, and the decision to submit the article for publication. Open Access funding enabled and organized by Project DEAL. We acknowledge support by the German Research Foundation Projekt-Nr. 512648189 and the Open Access Publication Fund of the Thueringer Universitaets- und Landesbibliothek Jena. ### Author Declarations I confirm all relevant ethical guidelines have been followed, and any necessary IRB and/or ethics committee approvals have been obtained. Yes The details of the IRB/oversight body that provided approval or exemption for the research described are given below: Study 1 was approved by the Ethical committee of Jena University Hospital (2022-2718-1-BO). Study 2 was approved by the Ethical committee of Medical Faculty of Eberhard Karls University Tuebingen (578/2016B01). All participants gave written informed consent and were reimbursed for their participation. I confirm that all necessary patient/participant consent has been obtained and the appropriate institutional forms have been archived, and that any patient/participant/sample identifiers included were not known to anyone (e.g., hospital staff, patients or participants themselves) outside the research group so cannot be used to identify individuals. Yes I understand that all clinical trials and any other prospective interventional studies must be registered with an ICMJE-approved registry, such as ClinicalTrials.gov. I confirm that any such study reported in the manuscript has been registered and the trial registration ID is provided (note: if posting a prospective study registered retrospectively, please provide a statement in the trial ID field explaining why the study was not registered in advance). Yes I have followed all appropriate research reporting guidelines, such as any relevant EQUATOR Network research reporting checklist(s) and other pertinent material, if applicable. Yes All data produced in the present study are available upon reasonable request to the authors.

MRI-visible perivascular spaces (PVS) are increasingly recognised as markers of compromised brain health, but their quantitative use requires segmentation methods that remain reliable beyond the datasets on which they were developed. Whether current methods meet this requirement remains unclear. To address this gap, we organised the Domain Randomisation PVS (DoRA-PVS) Challenge, a no-data-shared benchmark designed to evaluate out-of-sample PVS segmentation in two settings: an open method track for previously published methods, and a domain randomisation track for new strategies trained exclusively on synthetic data. The testbed comprised 285 images from 12 cohorts, capturing substantial heterogeneity in scanner vendors, field strengths, sequences, imaging protocols, image quality, and participant characteristics. Four teams competed in the first DoRA-PVS Challenge: two in the open method track, one in the domain-randomisation track, and one in both tracks. Preliminary results show that external generalisation is achievable. Across tracks, most methods achieved AUPRC values above random-classifier performance on unseen data, indicating that they could segment PVS beyond their development cohorts. However, this generalisation was not consistent: performance varied substantially across cohorts and evaluation metrics. These preliminary findings shift the central question from whether PVS segmentation methods can generalise at all to whether they can generalise reliably across heterogeneous data. The DoRA-PVS Challenge therefore establishes a rigorous benchmark for assessing out-of-sample robustness and provides a framework for developing PVS segmentation methods that are more consistent across acquisition protocols, populations, and anatomical regions.

Background: Blood-brain barrier (BBB) dysfunction is increasingly recognized as a feature of cerebral amyloid angiopathy (CAA) and has been linked to hemorrhagic imaging manifestations such as cortical superficial siderosis. However, it remains unclear whether neurovascular barrier dysfunction can be captured by routinely available fluid biomarkers and whether such markers identify clinically relevant hemorrhage-prone CAA phenotypes. The CSF/serum albumin quotient (QAlb) is an established marker of neurovascular barrier dysfunction. We investigated QAlb levels in CAA and their association with imaging markers of disease severity. Methods: We included 225 participants (115 with CAA, 72 with Alzheimers disease [AD], 38 healthy controls) with CSF biomarkers and standardized MRI evaluation. Pathologic QAlb levels were identified via the age-corrected Reiber-formula. Group differences and determinants of pathological QAlb were assessed using uni- and multivariable regression analyses. The diagnostic relevance was assessed by receiver operating characteristic analysis. Results: QAlb levels were higher in CAA than in controls (ratio of means [RoM] 1.43, 95% CI 1.28-1.58) and patients with AD (RoM 1.22, 95% CI 1.10-1.35; both p<0.001). Pathological QAlb was independently associated with CAA compared with controls (OR 12.16, 95% CI 2.56-57.86) and AD (OR 2.14, 95% CI 1.07-4.28). Despite these associations, QAlb showed only moderate discrimination between CAA and controls (AUC 0.75, 95% CI 0.67-0.82) and low discrimination between CAA and AD (AUC 0.63, 95% CI 0.55-0.71). Within the CAA cohort, pathological QAlb was independently associated with disseminated cortical superficial siderosis (OR 3.92, 95% CI 1.31-11.72; p=0.014), a marker of advanced hemorrhage-prone disease. Conclusion: QAlb is elevated in patients with CAA and is associated with disseminated cortical superficial siderosis, the strongest predictor of future intracerebral hemorrhage. These findings support an association between neurovascular barrier dysfunction and the hemorrhage-prone phenotype of CAA. ### Competing Interest Statement The authors have declared no competing interest. ### Author Declarations I confirm all relevant ethical guidelines have been followed, and any necessary IRB and/or ethics committee approvals have been obtained. Yes The details of the IRB/oversight body that provided approval or exemption for the research described are given below: The local Clinical Ethics Committee approved this retrospective study (Ethikkommission, Otto-von-Guericke-Universität Magdeburg; no. 07/17, addendum 11/2021). The study was performed in accordance with the relevant local and national guidelines and regulations I confirm that all necessary patient/participant consent has been obtained and the appropriate institutional forms have been archived, and that any patient/participant/sample identifiers included were not known to anyone (e.g., hospital staff, patients or participants themselves) outside the research group so cannot be used to identify individuals. Yes I understand that all clinical trials and any other prospective interventional studies must be registered with an ICMJE-approved registry, such as ClinicalTrials.gov. I confirm that any such study reported in the manuscript has been registered and the trial registration ID is provided (note: if posting a prospective study registered retrospectively, please provide a statement in the trial ID field explaining why the study was not registered in advance). Yes I have followed all appropriate research reporting guidelines, such as any relevant EQUATOR Network research reporting checklist(s) and other pertinent material, if applicable. Yes All data produced in the present study are available upon reasonable request to the authors

[18F]PI-2620 is a second-generation tau PET tracer that may detect early tau accumulation in aging. We investigated whether temporal lobe [18F]PI-2620 binding is associated with age, sex, genetic Alzheimer disease (AD) risk, plasma biomarkers of AD (plasma phosphorylated tau 217 [p-tau217], Aβ1-42/Aβ1-40), astrogliosis (glial fibrillary acidic protein), and domain-specific cognition in cognitively unimpaired (CU) older adults. Methods: In this study, 166 CU older adults (mean age, 72 ± 7 y; females, 46%; apolipoprotein ϵ4 [APOE4] carriers, 23%) and 13 young adults underwent extensive cognitive testing, blood sampling, MRI, and dynamic [18F]PI-2620 PET (0-60 min postinjection). Associations of regional [18F]PI-2620 distribution volume ratio (DVR) with age, sex, APOE4 genotype, and plasma biomarkers were examined using region-of-interest and voxelwise analyses. Additional imaging markers of age-related pathology included hippocampal volume, medial temporal lobe thickness, white matter (WM) hyperintensities, perivascular spaces, and hippocampal perfusion (R1-derived maps). Associations among temporal lobe DVR, other imaging markers, and domain-specific cognitive performance (from factor analysis) were tested. Results: In older adults, temporal [18F]PI-2620 binding was higher in women (β = 0.543, P < 0.001) and APOE4 carriers (β = 0.395, P = 0.030) and was positively associated with plasma p-tau217 (β = 0.22, P = 0.008). Voxelwise analyses showed age-related increases in basal ganglia signal, whereas WM signal was higher in younger adults. In a multiple regression model, higher temporal DVR (β = -0.36, P = 0.003) and lower hippocampal volume (β = 0.22, P = 0.007) predicted worse episodic memory and, together with demographic factors, explained approximately 30% of the variance. Conclusion: Temporal [18F]PI-2620 binding is associated with genetic AD risk, plasma p-tau217, female sex, and episodic memory deficits in CU older adults, supporting its sensitivity to early tau pathology, while highlighting the need to consider potential WM binding.

White matter hyperintensities (WMH) are a highly prevalent finding on FLAIR MRI scans and a prominent feature of white matter pathology across cerebrovascular and neurodegenerative diseases. Currently, WMH are assessed with visual rating scales such as the Fazekas scale or with their volume, as calculated from automatic or manual segmentations. Both methods have limitations: Visual rating scales are rater-dependent and coarse, while WMH volume does not take the confluence of lesions into account and thus disregards their spatial organisation. As an alternative, here we propose a novel automated method for quantifying the confluence of white matter hyperintensities on a continuous standardised scale between 0 and 1. The metric is based on WMH segmentations from routine MRI and quantifies the extent to which individual WMH merge into coherent lesions, independently of total lesion volume. We apply the method to QMIN-MC, a large UK memory clinic cohort, and show associations of the confluence metric with age, cognitive performance across domains, and Fazekas ratings. Participants with vascular and mixed dementia showed higher confluence than other diagnostic groups, whereas cognitively unimpaired participants showed lower confluence. However, confluence did not explain additional cognitive variance after accounting for log-transformed WMH volume. Findings were validated in DELCODE, an independent cohort of individuals with neurodegenerative disorders, replicating our original results. In this validation cohort, periventricular WMH confluence remained associated with cognition after adjustment for WMH volume. These findings introduce WMH confluence as a reproducible, automated, and fine-grained measure of lesion spatial organisation. It provides complementary information about morphological WMH severity beyond volume and is an alternative to visual rating scales. Although related to WMH volume in memory-clinic populations, confluence captures clinically interpretable information and may complement existing WMH measures for improved lesion characterisation in studies of white matter disease, ageing, and cognitive impairment.

Perivascular spaces (PVS), when abnormally enlarged and visible in magnetic resonance imaging (MRI) structural sequences, are important imaging markers of cerebral small vessel disease and potential indicators of neurodegenerative conditions. Despite their clinical significance, automatic enlarged PVS (EPVS) segmentation remains challenging due to their small size, variable morphology, similarity with other pathological features, and limited annotated datasets. This paper presents the EPVS Challenge organized at MICCAI 2024, which aims to advance the development of automated algorithms for EPVS segmentation across multi-site data. We provided a diverse dataset comprising 100 training, 50 validation, and 50 testing scans collected from multiple international sites (UK, Singapore, and China) with varying MRI protocols and demographics. All annotations followed the STRIVE protocol to ensure standardized ground truth and covered the full brain parenchyma. Seven teams completed the full challenge, implementing various deep learning approaches primarily based on U-Net architectures with innovations in multi-modal processing, ensemble strategies, and transformer-based components. Performance was evaluated using dice similarity coefficient, absolute volume difference, recall, and precision metrics. The winning method employed MedNeXt architecture with a dual 2D/3D strategy for handling varying slice thicknesses. The top solutions showed relatively good performance on test data from seen datasets, but significant degradation of performance was observed on the previously unseen Shanghai cohort, highlighting cross-site generalization challenges due to domain shift. This challenge establishes an important benchmark for EPVS segmentation methods and underscores the need for the continued development of robust algorithms that can generalize in diverse clinical settings.

Alzheimer's disease (AD) is a major cause of dementia and cognitive decline. Here, we assessed how episodic memory (EM) network dysfunction, a hallmark of AD, is related to the longitudinal progression of AD biomarkers, neurodegeneration and cognition using data from the DZNE DELCODE study. This data set includes over 1000 longitudinal functional magnetic resonance imaging measurements of EM network function. We related activation and deactivation of EM to individual disease progression scores from a disease progression model. Voxel-wise analyses revealed widespread loss of deactivation and activation with disease progression. Trajectories for the loss of deactivation were nonlinear, associated with amyloid- and tau-positivity and visually preceded trajectories of cognitive decline. The relationship between deactivation and cognitive decline was partly independent of neurodegeneration. Our results provide evidence that synaptic dysfunction and neurodegeneration are independent drivers of cognitive decline, providing a rationale for targeting synaptic dysfunction along the AD cascade.

Brain maintenance - the preservation of brain structure or function relevant to cognitive performance - remains challenging to quantify. Here, we propose a domain-general brain maintenance index derived by jointly modelling the longitudinal co-evolution of ageing-related atrophy (via medial temporal lobe to ventricle ratio, MTLV-ratio), white matter hyperintensities (WMH), and global cognition assessed by the preclinical Alzheimer's cognitive composite (PACC5) using latent growth curve modelling. We demonstrate its utility in 543 cognitively unimpaired older adults from the DELCODE cohort, followed annually over four years. We show that changes in MTLV-ratio and WMH additively predict cognitive change. We further show that higher neuroticism, depressive symptoms, lower openness, and faster biological ageing are related to unfavourable domain-specific trajectories and poorer brain maintenance. Our findings highlight the combined relevance of WMH and ageing-related atrophy dynamics for brain maintenance. Maintaining cerebrovascular and mental health alongside cognitive engagement could promote brain maintenance, delay cognitive decline and dementia.

Inferior frontal sulcal hyperintensities (IFSH) observed on fluid-attenuated inversion recovery (FLAIR) MRI have been proposed as indicators of elevated cerebrospinal fluid waste accumulation in cerebral small vessel disease (CSVD). However, to validate IFSH as a reliable imaging biomarker, further replication studies are required. The objective of this study was to investigate associations between IFSH and CSVD, and their potential repercussions, i.e., cognitive impairment and depression. We prospectively recruited 47 patients with CSVD and 29 cognitively normal controls (NC). IFSH were rated visually based on FLAIR MRI. Using different regression models, we explored the relationship between IFSH, group status (CSVD vs. NC), CSVD severity assessed with MRI, cognitive function, and symptoms of depression. Patients with CSVD were more likely to have higher IFSH scores compared to NC (OR 5.64, 95% CI 1.91-16.60), and greater CSVD severity on MRI predicted more severe IFSH (OR 1.47, 95% CI 1.14-1.88). Higher IFSH scores were associated with lower cognitive function (-0.96, 95% CI -1.81 to -0.10), and higher levels of depression (0.33, 95% CI 0.01-0.65). CSVD and IFSH may be tightly linked to each other, and the accumulation of waste products, indicated by IFSH, could have detrimental effects on cognitive function and symptoms of depression.

Cerebral small vessel disease (CSVD) is a common neurological condition that contributes to strokes, dementia, disability, and mortality worldwide. We conducted a systematic review and meta-analysis to investigate the use of neuroimaging CSVD markers in machine learning (ML) based diagnosis and prognosis of cognitive impairment and dementia, and identify both methodological changes over time and barriers to clinical translation. Following the PRISMA guidelines, we systematically searched for original studies that used both neuroimaging CSVD markers and ML methods for diagnosing and prognosing neurodegenerative diseases (preregistration in PROSPERO: CRD42022366767). Each paper was independently reviewed by a pair of reviewers at all stages, with a third consulted to resolve conflicts. We meta-analysed the effectiveness of ML models to distinguish healthy controls from Alzheimer’s dementia and cognitive impairment, using area under the curve (AUC) as the performance metric. We identified 75 studies: 43 on diagnosis, 27 on prognosis, and 5 on both. Nearly 60

Background Recurrent hemorrhage represents a significant risk for patients with lobar hemorrhage and underlying cerebral amyloid angiopathy. However, it remains unknown, whether cerebrospinal fluid biomarkers of β‐amyloid (Aβ) retention, predict recurrent hemorrhagic events in these patients. Methods In this retrospective study, we evaluated patients with first‐ever lobar intracerebral hemorrhage or convexity subarachnoid hemorrhage who underwent cerebrospinal fluid analysis of Aβ40, Aβ42, and Aβ42/40 ratio. Biomarker levels were compared between patients with and without recurrent hemorrhage, and optimal cutoff values were derived from receiver operating characteristic analysis to define high and low biomarker groups. Negative binomial regression models, adjusted for age, sex, and hypertension, were used to assess associations with recurrent hemorrhage rates, and Kaplan–Meier survival analysis evaluated time to first event as a sensitivity measure. Results Among 289 patients with lobar hemorrhage, 48 were eligible for analysis (mean age, 72.4 years; 44% women; median follow‐up, 2.7 years). Patients with recurrent hemorrhage had significantly lower Aβ40 and Aβ42 levels (P<0.05). Those with low Aβ42 levels exhibited a recurrence rate of 18.2 versus 1.7 events per 100 patient‐years (incidence rate ratio, 12.7 [95% CI, 1.5–306.6]; P=0.035; sensitivity, 89%; specificity, 54%), while low Aβ40 levels were associated with 63.6 versus 4.5 events per 100 patient‐years (incidence rate ratio, 41.0 [95% CI, 5.8–434.4]; P<0.001; sensitivity, 44%; specificity, 95%). Combining probable cerebral amyloid angiopathy (Boston criteria version 1.5) with low Aβ40 levels improved risk stratification, yielding a rule‐in specificity of 75% and a rule‐out sensitivity of 100%. Additionally, the Aβ42/40 ratio demonstrated robust accuracy for identifying probable cerebral amyloid angiopathy (sensitivity, 63%; specificity, 83%). Conclusions Cerebrospinal fluid Aβ biomarkers are effective in predicting recurrent hemorrhage and identifying probable cerebral amyloid angiopathy in patients with lobar hemorrhage. These findings underscore the potential of disease‐specific biofluid markers to improve clinical risk stratification and guide management strategies.

Computational competitions are the standard for benchmarking medical image analysis algorithms, but they typically use small curated test datasets acquired at a few centers, leaving a gap to the reality of diverse multicentric patient data. To this end, the Federated Tumor Segmentation (FeTS) Challenge represents the paradigm for real-world algorithmic performance evaluation. The FeTS challenge is a competition to benchmark (i) federated learning aggregation algorithms and (ii) state-of-the-art segmentation algorithms, across multiple international sites. Weight aggregation and client selection techniques were compared using a multicentric brain tumor dataset in realistic federated learning simulations, yielding benefits for adaptive weight aggregation, and efficiency gains through client sampling. Quantitative performance evaluation of state-of-the-art segmentation algorithms on data distributed internationally across 32 institutions yielded good generalization on average, albeit the worst-case performance revealed data-specific modes of failure. Similar multi-site setups can help validate the real-world utility of healthcare AI algorithms in the future.

Introduction Cerebral small vessel disease (CSVD) is a common neurological condition that contributes to strokes, dementia, disability, and mortality worldwide. We conducted a systematic review and meta-analysis to investigate the use of neuroimaging CSVD markers in machine learning (ML)-based diagnosis and prognosis of cognitive impairment and dementia and identify both methodological changes over time and barriers to clinical translation. Methods Following the PRISMA guidelines, we systematically searched for original studies using both neuroimaging CSVD markers and ML methods for diagnosing and prognosing neurodegenerative diseases (preregistration in PROSPERO: CRD42022366767). Each paper was independently reviewed by a pair of reviewers at all stages, with a third consulted to resolve conflicts. We meta-analysed the ability of ML models to distinguish healthy controls from Alzheimer’s dementia and cognitive impairment, using area under the curve (AUC) as the performance metric. Results We identified 75 studies: 43 on diagnosis, 27 on prognosis, and 5 on both. Nearly 60% of studies were published in the past two years, reflecting a growing interest in using CSVD markers in ML-based diagnosis and prognosis of neurodegenerative diseases, especially Alzheimer’s dementia. This rising interest may be linked to the strong performance of such models: according to our meta-analysis, ML approaches using CSVD markers perform well in differentiating healthy controls from Alzheimer’s dementia (AUC 0.88 [95%-CI 0.85–0.92]) and cognitive impairment (AUC 0.84 [95%-CI 0.74–0.95]). The growing interest has unfortunately not been matched by methodological rigour: only 16 studies met the criteria for inclusion in the meta-analysis due to inconsistent reporting, just five assessed the generalisability of their models on external datasets, and six lacked clear diagnostic criteria. Conclusions Interest in incorporating CSVD markers into ML models for neurodegenerative disease classification is on the rise, and their performance suggests that this is worth further exploration. Serious methodological issues, including inconsistent reporting, limited generalisability testing, and potential biases, are unfortunately common and hinder further adoption. Our targeted recommendations provide a roadmap to accelerate the integration of ML into clinical practice.

Cerebral small vessel disease (CSVD) often coexists with neurodegenerative pathologies, yet their role remains underexplored. This study aims to determine their prevalence, risk factors, and cognitive effects in patients with deep perforator arteriopathy (DPA) or cerebral amyloid angiopathy (CAA) using the biomarker-based ATN classification. In this cross-sectional study 186 patients (median age 75 years, 41

Perivascular spaces (PVS), when enlarged, become visible and quantifiable on brain magnetic resonance images (MRI). PVS visibility in MRI has been found to be associated with ageing, hypertension, sleep disorders, and cerebral small vessel disease, but their relationship with cognition in adults remains unclear. Here, we aimed to determine whether PVS volumes were associated with cognitive performance, using MRI and cognitive data from 14 different cohorts on ageing, dementia, and cerebrovascular disease. We computationally segmented PVS and estimated PVS volumes within the basal ganglia (BG-PVS) and cerebral white matter, primarily including the centrum semiovale (CSO-PVS) regions-of-interest. We then performed cross-sectional and longitudinal meta-analyses, both accounting for random effects. The cross-sectional meta-analysis employed a linear mixed model to relate PVS volumes to cognitive performance scores (Montreal Cognitive Assessment, MoCA or, Toronto Cognitive Assessment, TorCA) divided by the maximum in each cohort. The longitudinal meta-analysis used logistic regression to predict cognitive status, either remaining cognitively normal or developing impairment over time, from PVS volumes as a percentage in the respective regions-of-interest. Cross-sectional meta-analysis ( n  = 17771). Individuals with higher fractional PVS volumes had lower cognitive performance scores. This observation was consistent across multiple studies and remained significant after adjusting for age, sex, white matter hyperintensities, and years of education. A 10% change in CSO-PVS volume would estimate a 2% reduction in cognitive score. Longitudinal meta-analysis ( n  = 2447). Higher fractional PVS volumes tended to predict a greater likelihood of any cognitive impairment, although this relationship varied according to the participant populations (healthy aging, stroke, memory clinic) and/or other long-term brain changes (e.g., atrophy, worsening WMH), and variation in duration of follow-up. The volume of MRI-visible PVS impacts ageing, vascular or neurogenerative processes leading to cognitive decline. More longitudinal data are needed to confirm the association. Other PVS measures should be assessed as these may be more sensitive to cognitive decline.

Neuropsychiatric symptoms, such as executive dysfunction, fatigue, and depression, are common and disabling in post-COVID syndrome, often hindering daily activities and work. While the exact mechanisms remain unclear, recent studies suggest SARS-CoV-2 may damage the blood-brain barrier (BBB), contributing to these symptoms. If BBB dysfunction is central, structural changes may occur in neighbouring areas, such as in perivascular spaces (PVS). In this study, we measured PVS volumes in 80 participants, both with and without neuropsychiatric post-COVID syndrome, to assess whether PVS enlargement was associated with the syndrome and its duration. We used data from the post-COVID Brain project, a study designed to investigate differences in brain morphology, cognitive function, and overall neurological health between post-COVID patients and healthy controls. The study included 50 neuropsychiatric post-COVID patients and 30 age- and gender-matched healthy controls. We semi-automatically quantified PVS in the basal ganglia (BG ROI) and centrum semiovale (CSO ROI) and leveraged linear regression to test whether neuropsychiatric post-COVID syndrome and its duration were associated with fractional PVS volumes. We adjusted all models for age, sex, years of education, body-mass-index, and cardiovascular disease history. In the full sample, the difference in fractional PVS volumes between individuals with and without neuropsychiatric post-COVID syndrome increased with age (BG: βAge × Post-COVID? = 0.49 (SE 0.21), Z = 2.34, P = 0.022; CSO: βAge × Post-COVID? = 0.45 (SE 0.22), Z = 2.05, P = 0.044). In individuals with a neuropsychiatric post-COVID syndrome, longer duration of the neuropsychiatric symptoms was associated with larger fractional PVS volumes (BG: βPost-COVID duration = 0.27 (SE 0.12), Z = 2.20, P = 0.034; CSO: βPost-COVID duration = 0.30 (SE 0.13), Z = 2.28, P = 0.028). The presence and duration of neuropsychiatric post-COVID syndrome in humans relate to the extent of enlargement of PVS in the brain.