Free Water MR Imaging of White Matter Microstructural Changes is a Sensitive Marker of Amyloid Positivity in Alzheimer's Disease

Abstract

Background: Extracellular free water (FW) resulting from white matter degeneration limits the sensitivity of diffusion tensor imaging (DTI) in predicting Alzheimer's disease (AD).

Purpose: To evaluate the sensitivity of FW-DTI in detecting white matter microstructural changes in AD. To validate the effectiveness of FW-DTI indices to predict amyloid-beta (Aβ) positivity in mild cognitive impairment (MCI) subtypes.

Study type: Retrospective.

Population: Thirty-eight Aβ-negative cognitively healthy (CH) controls (68.74 ± 8.28 years old, 55% female), 15 Aβ-negative MCI patients (MCI-n) (68.87 ± 8.83 years old, 60% female), 29 Aβ-positive MCI patients (MCI-p) (73.03 ± 7.05 years old, 52% female), and 29 Aβ-positive AD patients (72.93 ± 9.11 years old, 55% female).

Field strength/sequence: 3.0T; DTI, T₁-weighted, T₂-weighted, T₂ star-weighted angiography, and Aβ PET (¹⁸F-florbetaben or ¹¹C-PIB).

Assessment: FW-corrected and standard diffusion indices were analyzed using trace-based spatial statistics. Area under the curve (AUC) in distinguishing MCI subtypes were compared using support vector machine (SVM).

Statistical tests: Chi-squared test, one-way analysis of covariance, general linear regression analyses, nonparametric permutation tests, partial Pearson's correlation, receiver operating characteristic curve analysis, and linear SVM. A P value <0.05 was considered statistically significant.

Results: Compared with CH/MCI-n/MCI-p, AD showed significant change in tissue compartment indices of FW-DTI. No difference was found in the FW index among pair-wise group comparisons (the minimum FWE-corrected P = 0.114). There was a significant association between FW-DTI indices and memory and visuospatial function. The SVM classifier with tissue radial diffusivity as an input feature had the best classification performance of MCI subtypes (AUC = 0.91), and the classifying accuracy of FW-DTI was all over 89.89%.

Data conclusion: FW-DTI indices prove to be potential biomarkers of AD. The classification of MCI subtypes based on SVM and FW-DTI indices has good accuracy and could help early diagnosis.

Evidence level: 4 TECHNICAL EFFICACY: Stage 2.

Keywords: Alzheimer's disease; diffusion tensor imaging; free water; support vector machine; white matter.