TY - GEN
T1 - Applying sparse coding to surface multivariate tensor-based morphometry to predict future cognitive decline
AU - Zhang, Jie
AU - Stonnington, Cynthia
AU - Li, Qingyang
AU - Shi, Jie
AU - Bauer, Robert J.
AU - Gutman, Boris A.
AU - Chen, Kewei
AU - Reiman, Eric M.
AU - Thompson, Paul M.
AU - Ye, Jieping
AU - Wang, Yalin
N1 - Funding Information:
The research was supported in part by NIH (R21AG043760, R21AG049216, R01AG031581, P30AG19610), NSF (DMS-1413417, IIS-1421165) and Arizona Alzheimer's Disease Consortium (ADHS14-052688). Funded in part by NIH ENIGMA Center grant U54EB020403, supported by the Big Data to Knowledge (BD2K) Centers of Excellence program
Publisher Copyright:
© 2016 IEEE.
PY - 2016/6/15
Y1 - 2016/6/15
N2 - Alzheimer's disease (AD) is a progressive brain disease. Accurate diagnosis of AD and its prodromal stage, mild cognitive impairment, is crucial for clinical trial design. There is also growing interests in identifying brain imaging biomarkers that help evaluate AD risk presymptomatically. Here, we applied a recently developed multivariate tensor-based morphometry (mTBM) method to extract features from hip-pocampal surfaces, derived from anatomical brain MRI. For such surface-based features, the feature dimension is usually much larger than the number of subjects. We used dictionary learning and sparse coding to effectively reduce the feature dimensions. With the new features, an Adaboost classifier was employed for binary group classification. In tests on publicly available data from the Alzheimers Disease Neuroimaging Initiative, the new framework outperformed several standard imaging measures in classifying different stages of AD. The new approach combines the efficiency of sparse coding with the sensitivity of surface mTBM, and boosts classification performance.
AB - Alzheimer's disease (AD) is a progressive brain disease. Accurate diagnosis of AD and its prodromal stage, mild cognitive impairment, is crucial for clinical trial design. There is also growing interests in identifying brain imaging biomarkers that help evaluate AD risk presymptomatically. Here, we applied a recently developed multivariate tensor-based morphometry (mTBM) method to extract features from hip-pocampal surfaces, derived from anatomical brain MRI. For such surface-based features, the feature dimension is usually much larger than the number of subjects. We used dictionary learning and sparse coding to effectively reduce the feature dimensions. With the new features, an Adaboost classifier was employed for binary group classification. In tests on publicly available data from the Alzheimers Disease Neuroimaging Initiative, the new framework outperformed several standard imaging measures in classifying different stages of AD. The new approach combines the efficiency of sparse coding with the sensitivity of surface mTBM, and boosts classification performance.
KW - Alzheimer's disease
KW - dictionary learning and sparse coding
KW - multivariate tensor-based morphometry
UR - http://www.scopus.com/inward/record.url?scp=84978422123&partnerID=8YFLogxK
UR - http://www.scopus.com/inward/citedby.url?scp=84978422123&partnerID=8YFLogxK
U2 - 10.1109/ISBI.2016.7493350
DO - 10.1109/ISBI.2016.7493350
M3 - Conference contribution
AN - SCOPUS:84978422123
T3 - Proceedings - International Symposium on Biomedical Imaging
SP - 646
EP - 650
BT - 2016 IEEE International Symposium on Biomedical Imaging
PB - IEEE Computer Society
T2 - 2016 IEEE 13th International Symposium on Biomedical Imaging: From Nano to Macro, ISBI 2016
Y2 - 13 April 2016 through 16 April 2016
ER -