Cerebellar Microbleed Distribution Patterns and Cerebral Amyloid Angiopathy

Pasi, Marco; Pongpitakmetha, Thanakit; Charidimou, Andreas; Singh, Smita; Tsai, Hsin‐Hsi; Xiong, Li; Boulouis, Grégoire; Warren, Andrew; Rosand, Jonathan; Frosch, Matthew P.; Viswanathan, Anand; Gurol, M. Edip; Greenberg, Steven M.

doi:10.1161/strokeaha.119.024843

Cited by 43 publications

(37 citation statements)

References 27 publications

(39 reference statements)

Supporting

Mentioning

Contrasting

Unclassified

Order By: Relevance

“…This is along the same line with cerebellar dentate nucleus involvement. As equivalents of deep CMBs, CMBs in cerebellar dentate nucleus are likely due to hypertensive angiopathy as reported in recent studies 18 , 19 . Our prediction models suggested optimal cut-off values of lobar CMBs predicting Aβ positivity as 16.4 (GBM) or 14.3 (RF).…”

Section: Discussionsupporting

confidence: 56%

Prediction of amyloid β PET positivity using machine learning in patients with suspected cerebral amyloid angiopathy markers

Jung

Lee

Kim

et al. 2020

Sci Rep

View full text Add to dashboard Cite

Amyloid-β(Aβ) PET positivity in patients with suspected cerebral amyloid angiopathy (CAA) MRI markers is predictive of a worse cognitive trajectory, and it provides insights into the underlying vascular pathology (CAA vs. hypertensive angiopathy) to facilitate prognostic prediction and appropriate treatment decisions. In this study, we applied two interpretable machine learning algorithms, gradient boosting machine (GBM) and random forest (RF), to predict Aβ PET positivity in patients with CAA MRI markers. In the GBM algorithm, the number of lobar cerebral microbleeds (CMBs), deep CMBs, lacunes, CMBs in dentate nuclei, and age were ranked as the most influential to predict Aβ positivity. In the RF algorithm, the absence of diabetes was additionally chosen. Cut-off values of the above variables predictive of Aβ positivity were as follows: (1) the number of lobar CMBs > 16.4(GBM)/14.3(RF), (2) no deep CMBs(GBM/RF), (3) the number of lacunes > 7.4(GBM/RF), (4) age > 74.3(GBM)/64(RF), (5) no CMBs in dentate nucleus(GBM/RF). The classification performances based on the area under the receiver operating characteristic curve were 0.83 in GBM and 0.80 in RF. Our study demonstrates the utility of interpretable machine learning in the clinical setting by quantifying the relative importance and cutoff values of predictive variables for Aβ positivity in patients with suspected CAA markers.

show abstract

Section: Discussionsupporting

confidence: 56%

Prediction of amyloid β PET positivity using machine learning in patients with suspected cerebral amyloid angiopathy markers

Jung

Lee

Kim

et al. 2020

Sci Rep

View full text Add to dashboard Cite

show abstract

“…2 ) [ 54 – 57 ]. Arteriolosclerosis has been found to more commonly present with deep cerebral and cerebellar microbleeds (CMB) [ 56 ], deep lacunes [ 57 ], perivascular spaces (PVS) visible in the basal ganglia [ 55 ], deep ICH and peri-basal ganglia WMH [ 54 ] (Fig. 1 c, Fig.…”

Section: Neuroimaging Evaluationmentioning

confidence: 99%

“…2 ). In contrast, evidence suggests that CAA more typically presents with cortical CMB [ 53 , 56 ], cortical cerebral microinfarcts (CMI) [ 58 ], lobar lacunes [ 57 ], PVS visible in the centrum semiovale [ 55 ], cortical superficial siderosis (cSS) [ 51 ], convexity subarachnoid hemorrhage (cSAH) [ 59 , 60 ], lobar ICH and WMH foci distributed as multiple subcortical spots [ 54 ] (Fig. 1 c, Fig.…”

Section: Neuroimaging Evaluationmentioning

confidence: 99%

Cerebral small vessel disease and vascular cognitive impairment: from diagnosis to management

Zotin

Sveikata

Viswanathan

et al. 2021

Current Opinion in Neurology

Self Cite

101

View full text Add to dashboard Cite

Purpose of review We present recent developments in the field of small vessel disease (SVD)-related vascular cognitive impairment, including pathological mechanisms, updated diagnostic criteria, cognitive profile, neuroimaging markers and risk factors. We further address available management and therapeutic strategies. Recent findings Vascular and neurodegenerative pathologies often co-occur and share similar risk factors. The updated consensus criteria aim to standardize vascular cognitive impairment (VCI) diagnosis, relying strongly on cognitive profile and MRI findings. Aggressive blood pressure control and multidomain lifestyle interventions are associated with decreased risk of cognitive impairment, but disease-modifying treatments are still lacking. Recent research has led to a better understanding of mechanisms leading to SVD-related cognitive decline, such as blood-brain barrier dysfunction, reduced cerebrovascular reactivity and impaired perivascular clearance. Summary SVD is the leading cause of VCI and is associated with substantial morbidity. Tackling cardiovascular risk factors is currently the most effective approach to prevent cognitive decline in the elderly. Advanced imaging techniques provide tools for early diagnosis and may play an important role as surrogate markers for cognitive endpoints in clinical trials. Designing and testing disease-modifying interventions for VCI remains a key priority in healthcare.

show abstract

“…8 In older populations, the presence of CMBs is associated with increased rates of dementia and vascular events. 9,10 CMBs are also characteristically identified and associated with cognitive impairment in specific disease conditions; for example, cerebral amyloid angiopathy 11 and traumatic diffuse axonal brain injury 12 and as a long-term effect of cranial radiotherapy. 13,14 Only 1 previous published study has explored CMBs in ITP, where a CMB was identified on gradient echo T2* MRI in 1 of 27 children with short duration of ITP.…”

Section: Introductionmentioning

confidence: 99%

Identification of occult cerebral microbleeds in adults with immune thrombocytopenia

Cooper

Morrison

Vladescu

et al. 2020

Blood

View full text Add to dashboard Cite

Management of symptoms and prevention of life-threatening haemorrhage in Immune thrombocytopenia (ITP) must be balanced against adverse effects of available therapies. Since current treatment guidelines based on platelet count are confounded by variable bleeding phenotypes, there is a need to identify new objective markers of disease severity for improved treatment stratification. In this cross-sectional, prospective study of 49 patients with ITP and lowest recorded (nadir) platelet counts below 30 x 109/L, we used Susceptibility-Weighted Magnetic Resonance Imaging (SWI) to detect cerebral microbleeds (CMBs) as a marker of occult haemorrhage. CMBs were detected using a semi-automated method and correlated with clinical metadata using multivariate Poisson regression analysis. Lobar CMBs were identified in 43% (21/49); prevalence increased with decreasing nadir platelet count (15/25 <5x109/L; 4/11 5-9x109/L; 2/9 10-14x109/L; 0/4 >15x109/L), and was associated with longer disease duration (p=7x10-6), lower nadir platelet count (p=0.005), lower platelet count at time of MRI (p=0.029), and higher organ bleeding scores (p=0.028). Mucosal and skin bleeding scores, number of previous treatments, age and sex were not associated with CMBs. Occult cerebral microhaemorrhage is common in patients with moderate to severe ITP. Strong associations with ITP duration may reflect CMB accrual over time or more refractory disease. Although associated, neither low platelet count or bleeding scores predict CMBs. SWI could therefore provide an additional non-invasive biomarker of haemorrhagic phenotype, and potential adjunct for treatment stratification. Further longitudinal studies in children and adults will allow greater understanding of the natural history, and clinical and prognostic significance of CMBs.

show abstract

Cerebellar Microbleed Distribution Patterns and Cerebral Amyloid Angiopathy

Cited by 43 publications

References 27 publications

Prediction of amyloid β PET positivity using machine learning in patients with suspected cerebral amyloid angiopathy markers

Prediction of amyloid β PET positivity using machine learning in patients with suspected cerebral amyloid angiopathy markers

Cerebral small vessel disease and vascular cognitive impairment: from diagnosis to management

Identification of occult cerebral microbleeds in adults with immune thrombocytopenia

Contact Info

Product

Resources

About