Automated Quantification of Cerebral Microbleeds in SWI: Association with Vascular Risk Factors, White Matter
Ji Su Ko1, Yangsean Choi2, Eun Seon Jeong1
1From the Department of Radiology and Research Institute of Radiology (J.S.K., Y.C., E.S.J., J.E.P., H.S.K.), University of Ulsan College of Medicine, Asan Medical Centre, Seoul, Republic of Korea.
Background And Purpose:
The amount and distribution of cerebral microbleeds (CMB) are important risk factors for cognitive impairment. Our objective was to train and validate a deep learning (DL)-based segmentation model for cerebral microbleeds (CMBs) on SWI and to find associations among CMB, cognitive impairment, and vascular risk factors.
Materials And Methods:
Participants in this single-institution retrospective study underwent brain MRI to evaluate cognitive impairment between January and September 2023. For training the DL model, the nnU-Net framework was used without modifications. The performance of the DL model was evaluated on independent internal and external validation data sets. Linear regression analysis was used to find associations among log-transformed CMB numbers, cognitive function (Mini-Mental Status Examination [MMSE]), white matter hyperintensity (WMH) burden, and clinical vascular risk factors (age, sex, hypertension, diabetes, lipid profiles, and body mass index).
Results:
Training of the DL model (n = 287) resulted in a robust segmentation performance with an average Dice score of 0.73 (95% CI, 0.67-0.79) in an internal validation set (n = 67) and modest performance in an external validation set (Dice score = 0.46; 95% CI, 0.33-0.59; n = 68). In a temporally independent clinical data set (n = 448), older age, hypertension, and WMH burden were significantly associated with CMB numbers in all distributions (total, lobar, deep, and cerebellar; all P < . 01). The MMSE was significantly associated with hyperlipidemia (β = 1.88; 95% CI, 0.96-2.81; P < . 001), WMH burden (β = -0.17 per 1% WMH burden, 95% CI, -0.27-0.08; P < . 001), and total CMB number (β = -0.01 per 1 CMB, 95% CI, -0.02-0.001; P = .04) after adjusting for age and sex.
Conclusions:
The DL model showed a robust segmentation performance for CMB. In all distributions, CMB had significant positive associations with WMH burden. Increased WMH burden and CMB numbers were associated with decreased cognitive function.
Insights
Deep learning models accurately segmented cerebral microbleeds (CMB), revealing associations between CMB, white matter hyperintensities (WMH), and cognitive decline. Increased WMH and CMB numbers correlate with reduced cognitive function.
Area of Science:
- Neuroimaging
- Artificial Intelligence in Medicine
- Neurology
Background:
- Cerebral microbleeds (CMB) are linked to cognitive impairment.
- Accurate quantification of CMB is crucial for understanding neurological conditions.
Purpose of the Study:
- To develop and validate a deep learning (DL) model for segmenting CMB on SWI.
- To investigate associations between CMB, cognitive function, and vascular risk factors.
Main Methods:
- A DL model (nnU-Net) was trained and validated on internal and external datasets.
- Linear regression analyzed relationships between CMB, cognitive scores (MMSE), white matter hyperintensities (WMH), and vascular risk factors.
Main Results:
- The DL model achieved robust segmentation performance (Dice score 0.73) internally, with modest external validation (Dice score 0.46).
- Older age, hypertension, and WMH burden were associated with increased CMB.
- WMH burden and CMB numbers correlated with decreased cognitive function (MMSE).
Conclusions:
- Deep learning models demonstrate effective CMB segmentation.
- CMB and WMH burden are significantly associated with cognitive impairment.
Related Concept Videos
00:49The Blood-brain Barrier
01:15Ischemic Stroke ll: Pathophysiology
01:17Hemorrhagic Stroke l: Introduction
01:29Hemorrhagic Stroke ll: Pathophysiology
01:19Cerebral Edema l: Introduction
01:22Cerebral Edema ll: Pathophysiology