.png){kind=icon}
.png){kind=icon}
Return
Automated detection of cerebral microbleeds on ex-vivo MRI scans of community-based older adults
.png){kind=icon}
OA
AI
G
A
G
D
J
K
DOI：10.1016/j.neuroimage.2026.121986.png)
.png){kind=icon}
.png){kind=icon}
Share.png){kind=icon}
Save
Abstract
En 中文
• A comprehensive automated detection method for cerebral microbleeds on ex-vivo MRI • Combines synthesis with self-supervised pretraining and confidence-aware learning • Addresses data scarcity and class imbalance • Detects 90% of CMBs at 15 false positives in data from community-based older adults • Partially automates CMB annotation enabling large-scale MRI and pathology studies
Keywords:
magnetic resonance imaging
neuropathology
microbleed
ex-vivo
biomarkers
CMB=cerebral microbleed
CAA=cerebral amyloid angiopathy
AD=Alzheimer’s disease
ICH=intracerebral hemorrhage
SWI=susceptibility weighted imaging
GRE=gradient echo
MAP=Rush Memory and Aging Project
MARS=Minority Aging Research Study
ROS=Religious Orders Study
PMI=post-mortem interval
AI Summary
Key information extracted from the uploaded paper, including a brief overview, abstract, background, key highlights, visual analysis, and future outlook.
Journal
IF:
4.5
Papers:
1.3K
Citations:
10.6W
Organization
Cited Papers