Search

Background: Cerebral microbleeds (CMB) are indicators of severe cerebral small vessel disease (CSVD) that can be identified through hemosiderin-sensitive sequences in MRI. Specifically, quantitative susceptibility mapping (QSM) and deep learning were applied to detect CMBs in MRI., Purpose: To automatically detect CMB on QSM, we proposed a two-stage deep learning pipeline., Study Type: Retrospective., Subjects: A total number of 1843 CMBs from 393 patients (69 ± 12) with cerebral small vessel disease were included in this study. Seventy-eight subjects (70 ± 13) were used as external testing., Field Strength/sequence: 3 T/QSM., Assessment: The proposed pipeline consisted of two stages. In stage I, 2.5D fast radial symmetry transform (FRST) algorithm along with a one-layer convolutional network was used to identify CMB candidate regions in QSM images. In stage II, the V-Net was utilized to reduce false positives. The V-Net was trained using CMB and non CMB labels, which allowed for high-level feature extraction and differentiation between CMBs and CMB mimics like vessels. The location of CMB was assessed according to the microbleeds anatomical rating scale (MARS) system., Statistical Tests: The sensitivity and positive predicative value (PPV) were reported to evaluate the performance of the model. The number of false positive per subject was presented., Results: Our pipeline demonstrated high sensitivities of up to 94.9% at stage I and 93.5% at stage II. The overall sensitivity was 88.9%, and the false positive rate per subject was 2.87. With respect to MARS, sensitivities of above 85% were observed for nine different brain regions., Data Conclusion: We have presented a deep learning pipeline for detecting CMB in the CSVD cohort, along with a semi-automated MARS scoring system using the proposed method. Our results demonstrated the successful application of deep learning for CMB detection on QSM and outperformed previous handcrafted methods., Level of Evidence: 2 TECHNICAL EFFICACY: Stage 2., (© 2023 The Authors. Journal of Magnetic Resonance Imaging published by Wiley Periodicals LLC on behalf of International Society for Magnetic Resonance in Medicine.)

Background: Recent studies in Caucasians with transient ischaemic attack or ischaemic stroke have demonstrated significant age-specific associations between cerebral small vessel disease (SVD) burden on magnetic resonance imaging and renal impairment. We aimed to validate these findings in a large cohort of Chinese with ischaemic stroke., Methods: In 959 Chinese with ischaemic stroke who received a brain magnetic resonance imaging at the University of Hong Kong, we determined the age-specific associations of renal impairment (glomerular filtration rate < 60 mL/min/1.73 m 2 ) with neuroimaging markers of SVD as well as with the SVD score., Results: Although renal impairment was associated with the SVD score in univariate analysis in all patients (odds ratio 1.61, 95% confidence interval 1.24-2.09, P < .0001), these associations were attenuated after adjusting for age and sex (P = .38). Similar findings were noted in patients with ischaemic stroke due to SVD and non-SVD subtypes. However, in 222 of 959 patients aged <60, renal impairment was independently associated with an increasing microbleed (adjusted odds ratio 6.82, 2.26-20.59), subcortical (4.97, 1.62-15.24) periventricular white matter hyperintensity (3.96, 1.08-14.51) and global SVD burden (3.41, 1.16-10.04; all P < .05) even after adjusting for age, sex, and vascular risk factors. Nevertheless, there were no associations between renal impairment and individual neuroimaging markers of SVD nor with the SVD score in patients aged ≥60 after adjusting for age and sex (all P > .05)., Conclusions: In Chinese with ischaemic stroke, renal impairment was independently associated with microbleed, white matter hyperintensity and global SVD burden in individuals aged <60, but not in those aged ≥60, suggesting that there may be shared susceptibilities to premature systemic disease., (Copyright © 2019 The Authors. Published by Elsevier Inc. All rights reserved.)

Different cerebral small vessel disease (SVD) lesion types have been shown to disrupt structural brain network individually. Considering that they often coexist, we investigated the relation between their collective effect using the recently proposed total SVD score and structural brain network on MRI in 95 patients with first transient ischemic attack (TIA) or ischemic stroke. Fifty-nine patients with and 36 without any SVD lesions were included. The total SVD score was recorded. Diffusion tensor imaging was performed to estimate structural brain connections for subsequent brain connectivity analysis. The global efficiency and characteristic path length of the structural brain network are respectively lower and higher due to SVD. Lower nodal efficiency is also found in the insular, precuneus, supplementary motor area, paracentral lobule, putamen and hippocampus. The total SVD score is correlated with global network measures, the local clustering coefficient and nodal efficiency of hippocampus, and the nodal efficiency of paracentral lobule. We have successfully demonstrated that the disruption of global and local structural brain networks are associated with the increase in the overall SVD severity or burden of patients with TIA or first-time stroke.

Objective: In patients with TIA and ischemic stroke, we validated the total small vessel disease (SVD) score by determining its prognostic value for recurrent stroke., Methods: Two independent prospective studies were conducted, one comprising predominantly Caucasian patients with TIA/ischemic stroke (Oxford Vascular Study [OXVASC]) and one predominantly Chinese patients with ischemic stroke (University of Hong Kong [HKU]). Cerebral MRI was performed and assessed for lacunes, microbleeds, white matter hyperintensities (WMH), and perivascular spaces (PVS). Predictive value of total SVD score for risk of recurrent stroke was determined and potential refinements considered., Results: In 2,002 patients with TIA/ischemic stroke (OXVASC n = 1,028, HKU n = 974, 6,924 patient-years follow-up), a higher score was associated with an increased risk of recurrent ischemic stroke (adjusted hazard ratio [HR] per unit increase: 1.32, 1.16-1.51, p < 0.0001; c statistic 0.61, 0.56-0.65, p < 0.0001) and intracerebral hemorrhage (ICH) (HR 1.54, 1.11-2.13, p = 0.009; c statistic 0.65, 0.54-0.76, p = 0.006). A higher score predicted recurrent stroke in SVD and non-SVD TIA/ischemic stroke subtypes ( c statistic 0.67, 0.59-0.74, p < 0.0001 and 0.60, 0.55-0.65, p < 0.0001). Including burden of microbleeds and WMH and adjusting the cutoff of basal ganglia PVS potentially improved predictive power for ICH ( c statistic 0.71, 0.60-0.81, p het = 0.45), but not for recurrent ischemic stroke ( c statistic 0.60, 0.56-0.65, p het = 0.76) on internal validation., Conclusions: The total SVD score has predictive value for recurrent stroke after TIA/ischemic stroke. Prediction of recurrence in patients with nonlacunar events highlights the potential role of SVD in wider stroke etiology., (Copyright © 2017 The Author(s). Published by Wolters Kluwer Health, Inc. on behalf of the American Academy of Neurology.)