| 1. |
- Dyrby, Tim B, et al.
(författare)
-
Segmentation of age-related white matter changes in a clinical multi-center study.
- 2008
-
Ingår i: NeuroImage. - : Elsevier BV. - 1053-8119. ; 41:2, s. 335-45
-
Tidskriftsartikel (refereegranskat)abstract
- Age-related white matter changes (WMC) are thought to be a marker of vascular pathology, and have been associated with motor and cognitive deficits. In the present study, an optimized artificial neural network was used as an automatic segmentation method to produce probabilistic maps of WMC in a clinical multi-center study. The neural network uses information from T1- and T2-weighted and fluid attenuation inversion recovery (FLAIR) magnetic resonance (MR) scans, neighboring voxels and spatial location. Generalizability of the neural network was optimized by including the Optimal Brain Damage (OBD) pruning method in the training stage. Six optimized neural networks were produced to investigate the impact of different input information on WMC segmentation. The automatic segmentation method was applied to MR scans of 362 non-demented elderly subjects from 11 centers in the European multi-center study Leukoaraiosis And Disability (LADIS). Semi-manually delineated WMC were used for validating the segmentation produced by the neural networks. The neural network segmentation demonstrated high consistency between subjects and centers, making it a promising technique for large studies. For WMC volumes less than 10 ml, an increasing discrepancy between semi-manual and neural network segmentation was observed using the similarity index (SI) measure. The use of all three image modalities significantly improved cross-center generalizability compared to neural networks using the FLAIR image only. Expert knowledge not available to the neural networks was a minor source of discrepancy, while variation in MR scan quality constituted the largest source of error.
|
|
| 2. |
- Gouw, Alida A, et al.
(författare)
-
Progression of white matter hyperintensities and incidence of new lacunes over a 3-year period: the Leukoaraiosis and Disability study.
- 2008
-
Ingår i: Stroke; a journal of cerebral circulation. - 1524-4628. ; 39:5, s. 1414-20
-
Tidskriftsartikel (refereegranskat)abstract
- BACKGROUND AND PURPOSE: We studied the natural course of white matter hyperintensities (WMH) and lacunes, the main MRI representatives of small vessel disease, over time and evaluated possible predictors for their development. METHODS: Baseline and repeat MRI (3-year follow-up) were collected within the multicenter, multinational Leukoaraiosis and Disability study (n=396). Baseline WMH were scored on MRI by the Fazekas scale and the Scheltens scale. WMH progression was assessed using the modified Rotterdam Progression scale (absence/presence of progression in 9 brain regions). Baseline and new lacunes were counted per region. WMH and lacunes at baseline and vascular risk factors were evaluated as predictors of WMH progression and new lacunes. RESULTS: WMH progressed (mean+/-SD=1.9+/-1.8) mostly in the subcortical white matter, where WMH was also most prevalent at baseline. The majority of new lacunes, which were found in 19% of the subjects (maximum=9), also appeared in the subcortical white matter, mainly of the frontal lobes, whereas most baseline lacunes were located in the basal ganglia. Baseline WMH and lacunes predicted both WMH progression and new lacunes. Furthermore, previous stroke, diabetes, and blood glucose were risk factors for WMH progression. Male sex, hypertension, systolic blood pressure, previous stroke, body mass index, high-density lipoprotein, and triglyceride levels were risk factors for new lacunes. CONCLUSIONS: WMH and lacunes progressed over time, predominantly in the subcortical white matter. Progression was observed especially in subjects with considerable WMH and lacunes at baseline. Moreover, the presence of vascular risk factors at baseline predicted WMH progression and new lacunes over a 3-year period.
|
|
