Association of total cerebral small vessel disease burden with the cavitation of recent small subcortical infarcts

Quantitative Analysis of Multimodal MRI Markers and Clinical Risk Factors for Cerebral Small Vessel Disease Based on Deep Learning

Background

Cerebral small vessel disease lacks specific clinical manifestations, and extraction of valuable features from multimodal images is expected to improve its diagnostic accuracy. In this study, we used deep learning techniques to segment cerebral small vessel disease imaging markers in multimodal magnetic resonance images and analyze them with clinical risk factors.

Methods and results

We recruited 211 lacunar stroke patients and 83 control patients. The patients' cerebral small vessel disease markers were automatically segmented using a V-shaped bottleneck network, and the number and volume were calculated after manual correction. The segmentation results of the V-shaped bottleneck network for white matter hyperintensity and recent small subcortical infarction were in high agreement with the ground truth (DSC>0.90). In small lesion segmentation, cerebral microbleed (average recall=0.778; average precision=0.758) and perivascular spaces (average recall=0.953; average precision=0.923) were superior to lacunar infarct (average recall=0.339; average precision=0.432) in recall and precision. Binary logistic regression analysis showed that age, systolic blood pressure, and total cerebral small vessel disease load score were independent risk factors for lacunar stroke (P<0.05). Ordered logistic regression analysis showed age was positively correlated with cerebral small vessel disease load score and total cholesterol was negatively correlated with cerebral small vessel disease score (P<0.05).

Conclusion

Lacunar stroke patients exhibited higher cerebral small vessel disease imaging markers, and age, systolic blood pressure, and total cerebral small vessel disease score were independent risk factors for lacunar stroke patients. V-shaped bottleneck network segmentation network based on multimodal deep learning can segment and quantify various cerebral small vessel disease lesions to some extent.

Association between Twenty-Four-Hour Ambulatory Blood Pressure Variability and Cerebral Small Vessel Disease Burden in Acute Ischemic Stroke

Objective. This study is aimed at investigating the association between the twenty-four-hour ambulatory blood pressure variability monitoring (ABPM) and cerebral small vessel disease (cSVD) burden in acute ischemic stroke (AIS) patients. Methods. 115 AIS patients with demographics, vascular risk factors, 24 h ABPM, and brain magnetic resonance imaging (MRI) were retrospectively enrolled. 3.0 T MRI was used to assess cSVD burden by combining four MRI markers including white matter hyperintensities (WMHs), cerebral microbleeds (CMBs), perivascular spaces (PVS), and lacunes. Correlation analysis was conducted to detect whether ABPM was associated with cSVD burden in AIS patients. Results. 115 AIS patients with mean age $68.77\pm 10.26$ years and 75.7% male were enrolled in this study. 112 AIS patients (97.4%) had at least one cSVD marker. Spearman correlation analysis indicated that hypertension was positively correlated with cSVD burden ( $\rho =0.21$ , $P=0.07$ ). High-density lipoprotein (HDL) was negatively correlated with cSVD burden ( $\rho =-0.21$ , $P=0.02$ ). Blood pressure variability such as 24 h mean SBP ( $\rho =0.23$ , $P=0.01$ ), day mean SBP ( $\rho =0.23$ , $P=0.01$ ), and night mean SBP ( $\rho =0.20$ , $P=0.04$ ) was positively correlated with higher cSVD burden. Ordinal logistic regression analysis demonstrated that higher 24 h SBP SD and day mean SBP were independent risk factors for cSVD after controlling for other confounders. Conclusions. Higher BPV was significantly related to total cSVD burden in AIS patients. 24 h SBP SD and day mean SBP were independent risk factors for cSVD burden in AIS patients but not DBP or DBP variability.