Amyloid-PET in cerebral amyloid angiopathy: Detecting vascular amyloid deposits, not just blood

The Association Between Positive Amyloid-PET and Cognitive Decline Is Not Always Supportive of Alzheimer's Disease: Suggestions from a Case Report

Amyloid-β deposition is the pathological hallmark of both cerebral amyloid angiopathy and Alzheimer's disease dementia, clinical conditions that can share cognitive decline and positive Amyloid-PET scan. A case is reported involving an 82-year-old Italian female who presented initially a memory deficit, later transient focal neurologic episodes, and finally two symptomatic lobar intracerebral hemorrhages. In light of these events, MRI and PET imaging findings, acquired before cerebral hemorrhages, are reconsidered and discussed, highlighting the utility of Amyloid-PET in supporting an in vivo diagnosis of cerebral amyloid angiopathy.

Subcortical hemorrhage caused by cerebral amyloid angiopathy compared with hypertensive hemorrhage

OBJECTIVES

Most published reports on lobular hemorrhage in cerebral amyloid angiopathy (CAA) include patients diagnosed only by imaging studies. This study analyzed patients with subcortical hemorrhage histologically diagnosed as CAA or non-CAA (hypertensive).

METHODS

This is a retrospective study analyzing data from 100 craniotomy cases. Tissue of hematoma cavity wall was collected for histological investigation in hematoma removal by surgery in patients with subcortical hemorrhage. Statistical analyses of blood pressure, hematoma location and volume, outcome, and mortality was performed in CAA and non-CAA groups.

RESULTS

There were 47 CAA and 53 non-CAA cases, and average age was significantly older in the CAA group (p < 0.01). Blood pressure was significantly lower (p < 0.01) but hematoma volume was significantly greater (p < 0.05) in the CAA group. Rebleeding occurred in two CAA cases and one non-CAA case, but no re-operations were required. Average score of modified Rankin Scale, which is used to measure the degree of disability in patients who have had a stroke, at three months after surgery was not significantly different between the two groups (CAA: 3.94 ± 1.28, non-CAA: 3.58 ± 1.50). There were seven deaths in the CAA and six in the non-CAA group, and intraventricular hemorrhage highly complicated in the death cases in both groups. In the CAA group, average age of the fatal cases was significantly older than that of the surviving cases (p < 0.05) and six cases demonstrated dementia before onset of hemorrhage.

CONCLUSIONS

Surgical removal of a subcortical hemorrhage caused by CAA is not contraindicated. However, age > 80 years, complication with intraventricular hemorrhage, hematoma volume ≥ 50 ml, and dementia before onset of hemorrhage contribute to high mortality, and craniotomy should be carefully considered for such patients. A limitation of this study is that comparison between CAA and non-CAA groups was performed in the patients with only surgically indicated ICH, and does not evaluate entire ICH cases with CAA. However, this study appropriately compared pathologically diagnosed CAA and non-CAA in patients with moderate to severe lobular ICH with surgical indications.

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

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.