Automatic segmentation of white matter hyperintensities in the elderly using FLAIR images at 3T

Abstract

PurposeTo determine the precision and accuracy of an automated method for segmenting white matter hyperintensities (WMH) on fast fluid-attenuated inversion-recovery (FLAIR) images in elderly brains at 3T.Materials and MethodsFLAIR images from 18 individuals (60–82 years, 9 females) with WMH burdens ranging from 1–80 cm3 were used. The protocol included the removal of clearly hyperintense voxels; two-class fuzzy C-means clustering (FCM); and thresholding to segment probable WMH. Two false-positive minimization (FPM) methods using white matter templates were tested. Precision was assessed by adding synthetic hyperintense voxels to brain slices. Accuracy was validated by comparing automatic and manual segmentations. Whole-brain, voxel-wise metrics of similarity, under- and overestimation were used to evaluate both precision and accuracy.ResultsPrecision was high, as the lowest accuracy in the synthetic datasets was 93%. Both FPM strategies successfully improved overall accuracy. Whole-brain accuracy for the FCM segmentation alone ranged from 45%–81%, which improved to 75%–85% using the FPM strategies.ConclusionThe method was accurate across the range of WMH burden typically seen in the elderly. Accuracy levels achieved or exceeded those of other approaches using multispectral and/or more sophisticated pattern recognition methods. J. Magn. Reson. Imaging 2010;31:1311–1322. © 2010 Wiley-Liss, Inc.

Are acute infarcts the cause of leukoaraiosis? Brain mapping for 16 consecutive weeks

“…Segmentation of leukoaraiosis was performed using a previously validated algorithm. 18 The resulting regions of leukoaraiosis are consistent with the STRIVE (STandards for ReportIng Vascular changes on nEuroimaging) definition of "whitematter hyperintensities of presumed vascular origin." 19 That is, lacunes, perivascular spaces, and hyperintensities within the brainstem and deep gray matter were not included in the analysis.…”

Temporal and Spatial Variances in Arterial Spin-Labeling Are Inversely Related to Large-Artery Blood Velocity

“…Brain mass was estimated on the basis of tissue densities of 1.03 g/mL for GM and 1.04 g/mL for WM. 20 In-house software, 21 combined with manual editing, segmented WMH from the FLAIR image. Stroke lesions were identified by CSF segmentation from the T1WI, manual editing, and confirmation against the FLAIR image.…”

A Hyperspectral Imaging Approach to White Matter Hyperintensities Detection in Brain Magnetic Resonance Images

“…Accordingly, segmentation of WMH has been recently directed to semi-unsupervised and automatic methods which rely on computer assisted tools to help diagnosis to avoid human subjective interpretation. Most importantly, such computer assisted diagnosis can be further used to quantify WMH and calculate its volume [3][4][5][6][7]. However, it also comes with two major issues.…”