Skip to main page content
U.S. flag

An official website of the United States government

Dot gov

The .gov means it’s official.
Federal government websites often end in .gov or .mil. Before sharing sensitive information, make sure you’re on a federal government site.

Https

The site is secure.
The https:// ensures that you are connecting to the official website and that any information you provide is encrypted and transmitted securely.

Access keys NCBI Homepage MyNCBI Homepage Main Content Main Navigation
. 2014 Sep;35(9):4827-40.
doi: 10.1002/hbm.22515. Epub 2014 Mar 31.

The power of neuroimaging biomarkers for screening frontotemporal dementia

Corey T McMillan  1 , Brian B Avants, Philip Cook, Lyle Ungar, John Q Trojanowski, Murray Grossman
Affiliations

The power of neuroimaging biomarkers for screening frontotemporal dementia

Corey T McMillan et al. Hum Brain Mapp. 2014 Sep.

Abstract

Frontotemporal dementia (FTD) is a clinically and pathologically heterogeneous neurodegenerative disease that can result from either frontotemporal lobar degeneration (FTLD) or Alzheimer's disease (AD) pathology. It is critical to establish statistically powerful biomarkers that can achieve substantial cost-savings and increase the feasibility of clinical trials. We assessed three broad categories of neuroimaging methods to screen underlying FTLD and AD pathology in a clinical FTD series: global measures (e.g., ventricular volume), anatomical volumes of interest (VOIs) (e.g., hippocampus) using a standard atlas, and data-driven VOIs using Eigenanatomy. We evaluated clinical FTD patients (N = 93) with cerebrospinal fluid, gray matter (GM) magnetic resonance imaging (MRI), and diffusion tensor imaging (DTI) to assess whether they had underlying FTLD or AD pathology. Linear regression was performed to identify the optimal VOIs for each method in a training dataset and then we evaluated classification sensitivity and specificity in an independent test cohort. Power was evaluated by calculating minimum sample sizes required in the test classification analyses for each model. The data-driven VOI analysis using a multimodal combination of GM MRI and DTI achieved the greatest classification accuracy (89% sensitive and 89% specific) and required a lower minimum sample size (N = 26) relative to anatomical VOI and global measures. We conclude that a data-driven VOI approach using Eigenanatomy provides more accurate classification, benefits from increased statistical power in unseen datasets, and therefore provides a robust method for screening underlying pathology in FTD patients for entry into clinical trials.

Keywords: Alzheimer's disease; DTI; MRI; biomarkers; classification; frontotemporal degeneration; statistical power.

PubMed Disclaimer

Figures

Figure 1
Figure 1
Schematic overview of training and test prediction procedures. (A) Cohort is randomly divided into training and test datasets. (B) Initial feature selection is performed by determining which VOIs minimize Bayesian information criterion (BIC). (C) Fivefold cross‐validation is performed within the training dataset by randomly dividing the cohort into five sets, calculating the features that achieve highest prediction accuracy, and permuting this process 1,000 times to identify the most stable VOIs for prediction. (D) Stable VOIs are entered into a power analysis in training cohort to confirm that there is a sufficient sample for test prediction. (E) ROC curve to calculate prediction accuracy in training cohort. (F) Power analysis in independent test cohort. (G) ROC curve to evaluate prediction accuracy in independent test cohort.
Figure 2
Figure 2
Selected volumes of interest (VOIs) for volumetric MRI and DTI methods. (A) Data‐driven MRI; (B) anatomical MRI; (C) data‐driven DTI; (D) anatomical DTI; (E) data‐driven multimodal (MRI + DTI); and (F) anatomical multimodal (MRI + DTI).
Figure 3
Figure 3
Receiver operator characteristic (ROC) curves for volumetric, DTI, and multimodal combination of neuroimaging approaches in independent test dataset.
Figure 4
Figure 4
Estimated minimum sample sizes for volumetric, DTI, and multimodal combination of neuroimaging approaches in independent test dataset.
See this image and copyright information in PMC

Similar articles

See all similar articles

Cited by

See all "Cited by" articles

References

    1. Adler DH, Pluta J, Kadivar S, Craige C, Gee JC, Avants BB, Yushkevich PA (2014): Histology‐derived volumetric annotation of the human hippocampal subfields in postmortem MRI. Neuroimage 84:505–523. - PMC - PubMed
    1. Alexander DC, Pierpaoli C, Basser PJ, Gee JC (2001): Spatial transformations of diffusion tensor magnetic resonance images. IEEE Trans Med Imaging 20:1131–1139. - PubMed
    1. Ard MC, Edland SD (2011): Power calculations for clinical trials in Alzheimer's disease. J Alzheimers Dis 26 (Suppl 3):369–377. - PMC - PubMed
    1. Armstrong MJ, Litvan I, Lang AE, Bak TH, Bhatia KP, Borroni B, Boxer AL, Dickson DW, Grossman M, Hallett M, Josephs KA, Kertesz A, Lee SE, Miller BL, Reich SG, Riley DE, Tolosa E, Tröster AI, Vidailhet M, Weiner WJ (2013): Criteria for the diagnosis of corticobasal degeneration. Neurology 80:496–503. - PMC - PubMed
    1. Augustinack JC, van der Kouwe AJW, Fischl B (2013): Medial temporal cortices in ex vivo magnetic resonance imaging. J Comp Neurol 521:4177–4188. - PMC - PubMed

Publication types

MeSH terms