Application of variable threshold intensity to segmentation for white matter hyperintensities in fluid attenuated inversion recovery magnetic resonance images.

Published

Journal Article

White matter hyperintensities (WMHs) are regions of abnormally high intensity on T2-weighted or fluid-attenuated inversion recovery (FLAIR) magnetic resonance imaging (MRI). Accurate and reproducible automatic segmentation of WMHs is important since WMHs are often seen in the elderly and are associated with various geriatric and psychiatric disorders.We developed a fully automated monospectral segmentation method for WMHs using FLAIR MRIs. Through this method, we introduce an optimal threshold intensity (I O ) for segmenting WMHs, which varies with WMHs volume (V WMH), and we establish the I O -V WMH relationship.Our method showed accurate validations in volumetric and spatial agreements of automatically segmented WMHs compared with manually segmented WMHs for 32 confirmatory images. Bland-Altman values of volumetric agreement were 0.96 ± 8.311 ml (bias and 95 % confidence interval), and the similarity index of spatial agreement was 0.762 ± 0.127 (mean ± standard deviation). Furthermore, similar validation accuracies were obtained in the images acquired from different scanners.The proposed segmentation method uses only FLAIR MRIs, has the potential to be accurate with images obtained from different scanners, and can be implemented with a fully automated procedure. In our study, validation results were obtained with FLAIR MRIs from only two scanner types. The design of the method may allow its use in large multicenter studies with correct efficiency.

Full Text

Cited Authors

  • Yoo, BI; Lee, JJ; Han, JW; Oh, SYW; Lee, EY; MacFall, JR; Payne, ME; Kim, TH; Kim, JH; Kim, KW

Published Date

  • April 2014

Published In

Volume / Issue

  • 56 / 4

Start / End Page

  • 265 - 281

PubMed ID

  • 24493377

Pubmed Central ID

  • 24493377

Electronic International Standard Serial Number (EISSN)

  • 1432-1920

International Standard Serial Number (ISSN)

  • 0028-3940

Digital Object Identifier (DOI)

  • 10.1007/s00234-014-1322-6

Language

  • eng