Deep-Learning-Based MRI Microbleeds Detection for Cerebral Small Vessel Disease on Quantitative Susceptibility Mapping.

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.

Low-Density Lipoprotein Cholesterol and Risk of Recurrent Vascular Events in Chinese Patients With Ischemic Stroke With and Without Significant Atherosclerosis.

Background Recent trials have shown that low-density lipoprotein cholesterol (LDL-C) <1.80 mmol/L (<70 mg/dL) is associated with a reduced risk of major adverse cardiovascular events in White patients with ischemic stroke with atherosclerosis. However, it remains uncertain whether the findings can be generalized to Asian patients, or that similar LDL-C targets should be adopted in patients with stroke without significant atherosclerosis. Methods and Results We performed a prospective cohort study and recruited consecutive Chinese patients with ischemic stroke with magnetic resonance angiography of the intra- and cervicocranial arteries performed at the University of Hong Kong between 2008 and 2014. Serial postevent LDL-C measurements were obtained. Risk of major adverse cardiovascular events in patients with mean postevent LDL-C <1.80 versus ≥1.80 mmol/L, stratified by presence or absence of significant (≥50%) large-artery disease (LAD) and by ischemic stroke subtypes, were compared. Nine hundred four patients (mean age, 69±12 years; 60% men) were followed up for a mean 6.5±2.4 years (mean, 9±5 LDL-C readings per patient). Regardless of LAD status, patients with a mean postevent LDL-C <1.80 mmol/L were associated with a lower risk of major adverse cardiovascular events (with significant LAD: multivariable-adjusted subdistribution hazard ratio, 0.65; 95% CI, 0.42-0.99; without significant LAD: subdistribution hazard ratio, 0.53; 95% CI, 0.32-0.88) (both P<0.05). Similar findings were noted in patients with ischemic stroke attributable to large-artery atherosclerosis (subdistribution hazard ratio, 0.48; 95% CI, 0.28-0.84) and in patients with other ischemic stroke subtypes (subdistribution hazard ratio, 0.64; 95% CI, 0.43-0.95) (both P<0.05). Conclusions A mean LDL-C <1.80 mmol/L was associated with a lower risk of major adverse cardiovascular events in Chinese patients with ischemic stroke with and without significant LAD. Further randomized trials to determine the optimal LDL-C cutoff in stroke patients without significant atherosclerosis are warranted.