Xiqi Zhu

Objective: White matter hyperintensities (WMH) are key neuroimaging markers of cerebral small vessel disease, associated with cognitive decline and stroke risk. Accurate quantification is essential yet manual segmentation is time-consuming and variable. We systematically evaluated AI performance for automated WMH segmentation across disease contexts and identified factors influencing model performance. Methods: Following PRISMA guidelines, we searched PubMed, Embase, Web of Science, Scopus, and IEEE Xplore from database inception to February 3, 2026 (PROSPERO: CRD420261355769). Studies employing AI-based WMH segmentation and reporting Dice similarity coefficient (DSC) were included. A random-effects meta-analysis was conducted, along with subgroup analyses, meta-regression, sensitivity analyses, and publication bias assessment. Results: 26 studies comprising 4,288 participants contributed to quantitative syntheses: 13 evaluated WMH segmentation in general cohorts, and 13 evaluated AD or CSVD-specific cohorts. In the general cohort meta-analysis, the pooled DSC was 0.78 (95% CI, 0.74–0.82). Disease-specific pooled DSC estimates were 0.75 for AD and 0.78 for CSVD. Exploratory meta-regression suggested an association between scanning parameters and DSC ( p = 0.042), whereas magnetic field strength showed a borderline association ( p = 0.052). Conclusion: AI demonstrates promising performance for automated WMH segmentation, with U-Net–based architectures showing superior accuracy. However, substantial heterogeneity highlights the need for standardized imaging protocols and robust external validation. Future multicenter studies are essential to improve model generalizability and facilitate clinical translation.

Background: Alzheimer’s disease (AD) and vascular dementia (VaD) have become significant global health challenges. Recent research evidence indicates a close comorbidity between AD and cerebral small vessel disease. The C677T (rs1801133, also known as c.665C > T) and A1298C (rs1801131) polymorphisms in the methylenetetrahydrofolate reductase ( MTHFR ) gene have been associated with both conditions, though conclusions vary across studies. Methods: We conducted a systematic search of PubMed, Embase, Web of Science and the Cochrane Library, covering the period from the inception of these databases to January 2026. Studies reporting the distribution of MTHFR C677T and/or A1298C genotypes were included. A fixed-effects model was used to calculate the pooled odds ratio (OR) and its 95% confidence interval (CI). Sensitivity analyses using random-effects models were also performed to test the robustness of the findings. Subgroup analyses were performed according to type of dementia and ethnicity. Results: A total of 26 C677T studies and 8 A1298C studies were included. In the allele contrast model (T vs. C), C677T was significantly associated with dementia (OR = 1.40, 95% CI 1.05–1.87, p = 0.021) and AD (OR = 1.40, 95% CI 1.01–1.93, p = 0.043), but no statistically significant association was observed for VaD (OR = 1.42, 95% CI 0.76–2.66, p = 0.266). C677T showed no significant association under homozygous, heterozygous, dominant, or recessive inheritance models. No significant heterogeneity in association was observed across racial subgroups. A1298C showed no significant association with dementia under any genetic model. Conclusion: This meta-analysis showed that the MTHFR C677T T allele is associated with the risk of AD in an allele-dependent model, with a similar but non-significant trend for VaD. The A1298C polymorphism shows no association with either type of dementia. These findings suggest that C677T genotyping may aid AD risk stratification in research, but it requires prospective validation and gene-environment studies before clinical use.

Hemorrhagic transformation (HT) remains a major complication after endovascular therapy (EVT) in patients with acute ischemic stroke (AIS). This study aime

Cerebral small vessel disease (CSVD) is a leading cause of vascular cognitive impairment and dementia, yet the neural structural and functional pattern of brain alterations across its clinical spectrum remains unclear. This study aimed to identify convergent and stage-specific structural and functional brain abnormalities in CSVD using a multimodal meta-analysis. Four electronic databases were searched including PubMed, Embase, Web of Science, and the Cochrane Library up to April 2025. Studies reporting whole-brain structural or functional differences comparing CSVD with normal cognition [CSVD-NC], CSVD-related mild cognitive impairment [CSVD-MCI], and CSVD-related vascular dementia [CSVD-VaD]) to healthy controls were included. Voxel-wise meta-analyses were performed using anisotropic effect-size seed-based d mapping (AES-SDM v5.15). A total of 33 datasets from 22 studies were included. CSVD-MCI patients showed increased activity in the left superior frontal gyrus, medial orbital and right lenticular nucleus, putamen, but decreased activity in the left superior medial frontal and right postcentral gyrus, alongside atrophy in the supplementary motor area and right insula. CSVD-VaD patients exhibited widespread functional and structural damage in the cingulate gyrus and corpus callosum. Multimodal analyses revealed early convergent alterations in fronto-thalamic circuits in CSVD-NC and a divergent alteration dynamic and often insidious toward callosal disruption in VaD. Our findings map the spatial distribution of brain alterations across the clinical spectrum of CSVD, with distinct yet converging functional and structural impairments at each stage. Fronto-striatal hyperactivation and insular atrophy mark MCI, while callosal degradation characterizes VaD.

Background: Parkinson's disease with mild cognitive impairment (PD‐MCI) is a critical dementia prodrome, but its structural neuropathology remains incompletely defined. While hippocampal atrophy is established, volumetric changes in other subcortical structures are poorly characterized. Objective: To perform the first comprehensive meta‐analysis quantifying gray matter volume alterations across six subcortical regions in PD‐MCI. Methods: A systematic search of PubMed, Web of Science, Embase, and Cochrane (inception‐June 2025) for studies reporting MRI volumetric data comparing PD‐MCI and cognitively normal PD (PD‐NC) was done. Random‐effects models calculated pooled weighted mean differences (WMDs) with 95% confidence intervals (CIs). Heterogeneity ( I ² ), publication bias, sensitivity analyses, and meta‐regression were assessed. Results: PD‐MCI showed significant bilateral atrophy versus PD‐NC in the hippocampus (total WMD = –0.65 cm ³ ), thalamus, putamen, and amygdala, alongside right‐lateralized globus pallidus atrophy (WMD = –0.08 cm ³ ). Bilateral caudate nuclei volumes were preserved. Sensitivity analyses confirmed robustness. Meta‐regression identified segmentation tools and country as sources of left hippocampal heterogeneity ( p < 0.05). No publication bias was detected. Conclusion: PD‐MCI exhibits a distinct subcortical atrophy signature involving limbic–striato‐thalamic networks, with right globus pallidus atrophy as a novel lateralized biomarker. Network‐based imaging paradigms are advocated, requiring standardized protocols and longitudinal validation. Systematic Review Registration: Identifier PROSPERO (CRD420251051275).

To evaluate the diagnostic performance of dual-layer detector spectral CT (DLCT)-derived extracellular volume fraction (ECV) for pre-operatively distinguis

Accurate preoperative prediction of lymph node metastasis (LNM) in intrahepatic cholangiocarcinoma (ICC) is crucial for clinical decision-making, but the p