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
. 2017 May 18:9:146.
doi: 10.3389/fnagi.2017.00146. eCollection 2017.

Conversion Discriminative Analysis on Mild Cognitive Impairment Using Multiple Cortical Features from MR Images

Shengwen Guo  1 , Chunren Lai  1 , Congling Wu  1 , Guiyin Cen  2 ; Alzheimer's Disease Neuroimaging Initiative
Collaborators, Affiliations

Conversion Discriminative Analysis on Mild Cognitive Impairment Using Multiple Cortical Features from MR Images

Shengwen Guo et al. Front Aging Neurosci. .

Erratum in

Abstract

Neuroimaging measurements derived from magnetic resonance imaging provide important information required for detecting changes related to the progression of mild cognitive impairment (MCI). Cortical features and changes play a crucial role in revealing unique anatomical patterns of brain regions, and further differentiate MCI patients from normal states. Four cortical features, namely, gray matter volume, cortical thickness, surface area, and mean curvature, were explored for discriminative analysis among three groups including the stable MCI (sMCI), the converted MCI (cMCI), and the normal control (NC) groups. In this study, 158 subjects (72 NC, 46 sMCI, and 40 cMCI) were selected from the Alzheimer's Disease Neuroimaging Initiative. A sparse-constrained regression model based on the l2-1-norm was introduced to reduce the feature dimensionality and retrieve essential features for the discrimination of the three groups by using a support vector machine (SVM). An optimized strategy of feature addition based on the weight of each feature was adopted for the SVM classifier in order to achieve the best classification performance. The baseline cortical features combined with the longitudinal measurements for 2 years of follow-up data yielded prominent classification results. In particular, the cortical thickness produced a classification with 98.84% accuracy, 97.5% sensitivity, and 100% specificity for the sMCI-cMCI comparison; 92.37% accuracy, 84.78% sensitivity, and 97.22% specificity for the cMCI-NC comparison; and 93.75% accuracy, 92.5% sensitivity, and 94.44% specificity for the sMCI-NC comparison. The best performances obtained by the SVM classifier using the essential features were 5-40% more than those using all of the retained features. The feasibility of the cortical features for the recognition of anatomical patterns was certified; thus, the proposed method has the potential to improve the clinical diagnosis of sub-types of MCI and predict the risk of its conversion to Alzheimer's disease.

Keywords: classification; conversion; cortical feature; feature reduction; mild cognitive impairment; sparse-constrained regression.

PubMed Disclaimer

Figures

Figure 1
Figure 1
Changes in classification performance with the increase in combined features (A) GMV, (B) Cortical thickness, (C) Surface area, and (D) Mean curvature. The vertical red dot lines denoted the best performances.
Figure 2
Figure 2
The normalized weights of combined cortical surface features with the highest (A) GM volume, (B) Cortical thickness, (C) Surface area, and (D) Mean curvature.
Figure 3
Figure 3
Selected count of GM volume and cortical thickness in 68 brain regions. Selected count means the count of combined features were selected for classification with the high performance, left, right denotes left and right hemisphere. (A) GM volume. (B) Cortical thickness.
Figure 4
Figure 4
Selected count of surface and mean curvature in 68 brain regions. (A) Surface area. (B) Mean curvature.
See this image and copyright information in PMC

References

    1. Adaszewski S., Dukart J., Kherif F., Frackowiak R., Draganski B., Neuroimaging A. D. (2013). How early can we predict Alzheimer's disease using computational anatomy? Neurobiol. Aging 34, 2815–2826. 10.1016/j.neurobiolaging.2013.06.015 - DOI - PubMed
    1. Banzo I., Jimenez-Bonilla J. F., Martinez-Rodriguez I., Quirce R., de Arcocha-Torres M., Bravo-Ferrer Z., et al. (2015). Patterns of C-PIB cerebral retention in mild cognitive impairment patients. Rev. Esp. Med. Nucl. Imagen. Mol. 35, 171–174. 10.1016/j.remn.2015.09.008 - DOI - PubMed
    1. Bao B. K., Zhu G., Shen J., Yan S. (2013). Robust image analysis with sparse representation on quantized visual features. IEEE Trans. Image Process. 22, 860–871. 10.1109/TIP.2012.2219543 - DOI - PubMed
    1. Boutet C., Chupin M., Lehericy S., Marrakchi-Kacem L., Epelbaum S., Poupon C., et al. . (2014). Detection of volume loss in hippocampal layers in Alzheimer's disease using 7 T MRI: a feasibility study. Neuroimage Clin. 5, 341–348. 10.1016/j.nicl.2014.07.011 - DOI - PMC - PubMed
    1. Bouwman F. H., Schoonenboom S. N., van der Flier W. M., van Elk E. J., Kok A., Barkhof F., et al. . (2007). CSF biomarkers and medial temporal lobe atrophy predict dementia in mild cognitive impairment. Neurobiol. Aging 28, 1070–1074. 10.1016/j.neurobiolaging.2006.05.006 - DOI - PubMed