TY - JOUR
T1 - Thickness network features for prognostic applications in dementia
AU - Alzheimer's Disease Neuroimaging Initiative
AU - Raamana, Pradeep Reddy
AU - Weiner, Michael W.
AU - Wang, Lei
AU - Beg, Mirza Faisal
N1 - Funding Information:
We gratefully acknowledge funding support from Alzheimer Society of Canada Research Program (ASRP), Natural Sciences and Engineering Research Council of Canada (NSERC), Canadian Institutes of Health Research (CIHR) and Michael Smith Foundation for Health Research (MSFHR). They sincerely thank Dr Michael W. Weiner and the Freesurfer team at University of California, San Francisco for the computation and quality control of Freesurfer processing for ADNI data set.
Publisher Copyright:
© 2015 Elsevier Inc.
PY - 2015/1/1
Y1 - 2015/1/1
N2 - Regional analysis of cortical thickness has been studied extensively in building imaging biomarkers for early detection of Alzheimer's disease but not its interregional covariation of thickness. We present novel features based on the inter-regional covariation of cortical thickness. Initially, the cortical labels of each subject are partitioned into small patches (graph nodes) by spatial k-means clustering. A graph is then constructed by establishing a link between 2 nodes if the difference in thickness between the nodes is below a certain threshold. From this binary graph, a thickness network is computed using nodal degree, betweenness, and clustering coefficient measures. Fusing them with multiple kernel learning, it is observed that thickness network features discriminate mild cognitive impairment (MCI) converters from controls (CN) with an area under curve (AUC) of 0.83, 74% sensitivity and 76% specificity on a large subset obtained from the Alzheimer's Disease Neuroimaging Initiative data set. A comparison of predictive utility in Alzheimer's disease and/or CN classification (AUC of 0.92, 80% sensitivity [SENS] and 90% specificity [SPEC]), in discriminating CN from MCI (converters and nonconverters combined; AUC of 0.75, SENS and SPEC of 64% and 73%, respectively) and in discriminating between MCI nonconverters and MCI converters (AUC of 0.68, SENS and SPEC of 65% and 64%) is also presented. ThickNet features as defined here are novel, can be derived from a single magnetic resonance imaging scan, and demonstrate the potential for the computer-aided prognostic applications.
AB - Regional analysis of cortical thickness has been studied extensively in building imaging biomarkers for early detection of Alzheimer's disease but not its interregional covariation of thickness. We present novel features based on the inter-regional covariation of cortical thickness. Initially, the cortical labels of each subject are partitioned into small patches (graph nodes) by spatial k-means clustering. A graph is then constructed by establishing a link between 2 nodes if the difference in thickness between the nodes is below a certain threshold. From this binary graph, a thickness network is computed using nodal degree, betweenness, and clustering coefficient measures. Fusing them with multiple kernel learning, it is observed that thickness network features discriminate mild cognitive impairment (MCI) converters from controls (CN) with an area under curve (AUC) of 0.83, 74% sensitivity and 76% specificity on a large subset obtained from the Alzheimer's Disease Neuroimaging Initiative data set. A comparison of predictive utility in Alzheimer's disease and/or CN classification (AUC of 0.92, 80% sensitivity [SENS] and 90% specificity [SPEC]), in discriminating CN from MCI (converters and nonconverters combined; AUC of 0.75, SENS and SPEC of 64% and 73%, respectively) and in discriminating between MCI nonconverters and MCI converters (AUC of 0.68, SENS and SPEC of 65% and 64%) is also presented. ThickNet features as defined here are novel, can be derived from a single magnetic resonance imaging scan, and demonstrate the potential for the computer-aided prognostic applications.
KW - Alzheimer
KW - Cortical thickness
KW - Early detection
KW - Fusion
KW - Mild cognitive impairment
KW - Multiple kernel learning
KW - Network properties
UR - http://www.scopus.com/inward/record.url?scp=84916624596&partnerID=8YFLogxK
UR - http://www.scopus.com/inward/citedby.url?scp=84916624596&partnerID=8YFLogxK
U2 - 10.1016/j.neurobiolaging.2014.05.040
DO - 10.1016/j.neurobiolaging.2014.05.040
M3 - Article
C2 - 25444603
AN - SCOPUS:84916624596
SN - 0197-4580
VL - 36
SP - S91-S102
JO - Neurobiology of Aging
JF - Neurobiology of Aging
IS - S1
ER -