Improved Automatic Segmentation of White Matter Hyperintensities in MRI Based on Multilevel Lesion Features.

Brain white matter hyperintensities (WMHs) are linked to increased risk of cerebrovascular and neurodegenerative diseases among the elderly. Consequently, detection and characterization of WMHs are of significant clinical importance. We propose a novel approach for WMH segmentation from multi-contrast MRI where both voxel-based and lesion-based information are used to improve overall performance in both volume-oriented and object-oriented metrics. Our segmentation method (AMOS-2D) consists of four stages following a "generate-and-test" approach: pre-processing, Gaussian white matter (WM) modelling, hierarchical multi-threshold WMH segmentation and object-based WMH filtering using support vector machines. Data from 28 subjects was used in this study covering a wide range of lesion loads. Volumetric T1-weighted images and 2D fluid attenuated inversion recovery (FLAIR) images were used as basis for the WM model and lesion masks defined manually in each subject by experts were used for training and evaluating the proposed method. The method obtained an average agreement (in terms of the Dice similarity coefficient, DSC) with experts equivalent to inter-expert agreement both in terms of WMH number (DSC = 0.637 vs. 0.651) and volume (DSC = 0.743 vs. 0.781). It allowed higher accuracy in detecting WMH compared to alternative methods tested and was further found to be insensitive to WMH lesion burden. Good agreement with expert annotations combined with stable performance largely independent of lesion burden suggests that AMOS-2D will be a valuable tool for fully automated WMH segmentation in patients with cerebrovascular and neurodegenerative pathologies.

Neurobiological correlates of depressive symptoms in people with subjective and mild cognitive impairment.

OBJECTIVE: To test the hypothesis that depressive symptoms correlate with Alzheimer's disease (AD) type changes in CSF and structural and functional imaging including hippocampus volume, cortical thickness, white matter lesions, Diffusion tensor imaging (DTI), and fluoro-deoxy-glucose positron emission tomography (FDG-PET) in patient with subjective (SCI) and mild (MCI) cognitive impairment. METHOD: In 60 patients, depressive symptoms were assessed using the Geriatric Depression Scale. The subjects underwent MRI, 18F-FDG PET imaging, and lumbar CSF extraction. RESULTS: Subjects with depressive symptoms (n=24) did not have more pathological AD biomarkers than non-depressed. Uncorrected there were trends towards larger hippocampal volumes (P=0.06), less orbital WM damage measured by DTI (P=0.10), and higher orbital glucose metabolism (P=0.02) in the depressed group. The findings were similar when SCI and MCI were analyzed separately. Similarly, in patients with pathological CSF biomarkers (i.e., predementia AD, n=24), we found that correlations between scores on GDS and CSF Aß42 and P-tau indicated less severe AD-specific CSF changes with increasing depression. CONCLUSION: Depressive symptoms are common in SCI/MCI, but are not associated with pathological imaging or CSF biomarkers of AD. Depression can explain cognitive impairment in SCI/MCI or add to cognitive impairment leading to an earlier clinical investigation in predementia AD.