Empowering imaging biomarkers of Alzheimer's disease

NEUROBIOLOGY OF AGING

卷:36

Article

Gutman, Boris A.¹  Wang, Yalin²  Yanovsky, Igor³  Hua, Xue¹  Toga, Arthur W.⁸  Jack, Clifford R., Jr.⁴  Weiner, Michael W.^5,6,7  Thompson, Paul M.^1,8 

[1] Univ So Calif, Keck Sch Med, USC Imaging Genet Ctr, Los Angeles, CA 90033 USA

[2] Arizona State Univ, Sch Comp Informat & Decis Syst Engn, Tempe, AZ USA

[3] UCLA Joint Inst Reg Earth Syst Sci & Engn, Los Angeles, CA USA

[4] Mayo Clin, Rochester, MN USA

[5] UC San Francisco, Dept Radiol & Biomed Imaging, San Francisco, CA USA

[6] UC San Francisco, Dept Med, San Francisco, CA USA

[7] UC San Francisco, Dept Psychiat, San Francisco, CA USA

[8] Univ So Calif, Keck Sch Med, Inst Neuroimaging & Informat, Los Angeles, CA 90033 USA

关键词: Linear discriminant analysis;    Shape analysis;    Tensor-based morphometry;    ADNI;    Lateral ventricles;    Alzheimer's disease;    Mild cognitive impairment;    Biomarker;    Drug trial;    Machine learning;   

DOI  :  10.1016/j.neurobiolaging.2014.05.038

来源: Elsevier

【 摘 要 】

In a previous report, we proposed a method for combining multiple markers of atrophy caused by Alzheimer's disease into a single atrophy score that is more powerful than any one feature. We applied the method to expansion rates of the lateral ventricles, achieving the most powerful ventricular atrophy measure to date. Here, we expand our method's application to tensor-based morphometry measures. We also combine the volumetric tensor-based morphometry measures with previously computed ventricular surface measures into a combined atrophy score. We show that our atrophy scores are longitudinally unbiased with the intercept bias estimated at 2 orders of magnitude below the mean atrophy of control subjects at 1 year. Both approaches yield the most powerful biomarker of atrophy not only for ventricular measures but also for all published unbiased imaging measures to date. A 2-year trial using our measures requires only 31 (22, 43) Alzheimer's disease subjects or 56 (44, 64) subjects with mild cognitive impairment to detect 25% slowing in atrophy with 80% power and 95% confidence. (C) 2015 Elsevier Inc. All rights reserved.

【 授权许可】

Free