Premium
Texture analyses of quantitative susceptibility maps to differentiate Alzheimer's disease from cognitive normal and mild cognitive impairment
Author(s) -
Hwang EoJin,
Kim HyugGi,
Kim Danbi,
Rhee Hak Young,
Ryu ChangWoo,
Liu Tian,
Wang Yi,
Jahng GeonHo
Publication year - 2016
Publication title -
medical physics
Language(s) - English
Resource type - Journals
SCImago Journal Rank - 1.473
H-Index - 180
eISSN - 2473-4209
pISSN - 0094-2405
DOI - 10.1118/1.4958959
Subject(s) - cognition , cognitive impairment , alzheimer's disease , disease , texture (cosmology) , medicine , artificial intelligence , psychology , neuroscience , computer science , pathology , image (mathematics)
Purpose: Although a number of studies have focused on finding anatomical regions in which iron concentrations are high, no study has been conducted to examine the overall variations in susceptibility maps of Alzheimer's disease (AD). The objective of this study, therefore, was to differentiate AD from cognitive normal (CN) and mild cognitive impairment (MCI) using a texture analysis of quantitative susceptibility maps (QSMs). Methods: The study was approved by the local institutional review board, and informed consent was obtained from all subjects. In each participant group—CN, MCI, and AD—18 elderly subjects were enrolled. A fully first‐order flow‐compensated 3D gradient‐echo sequence was run to obtain axial magnitudes and phase images and to produce QSM data. Sagittal structural 3D T1‐weighted (3DT1W) images were also obtained with the magnetization‐prepared rapid acquisition of gradient‐echo sequence to obtain brain tissue images. The first‐ and second‐order texture parameters of the QSMs and 3DT1W images were obtained to evaluate group differences using a one‐way analysis of covariance. Results: For the first‐order QSM analysis, mean, standard deviation, and covariance of signal intensity separated the subject groups (F = 5.191, p = 0.009). For the second‐order analysis, angular second moment, contrast, and correlation separated the subject groups (F = 6.896, p = 0.002). Finally, a receiver operating characteristic curve analysis differentiated MCI from CN in white matter on the QSMs ( z = 3.092, p = 0.0020). Conclusions: This was the first study to evaluate the textures of QSM in AD, which overcame the limitations of voxel‐based analyses. The QSM texture analysis successfully distinguished both AD and MCI from CN and outperformed the voxel‐based analysis using 3DT1‐weighed images in separating MCI from CN. The first‐order textures were more efficient in differentiating MCI from CN than did the second‐order.