TY - GEN
T1 - A Neuroimaging Feature Extraction Model for Imaging Genetics with Application to Alzheimer's Disease
AU - Li, Chunfei
AU - Fang, Chen
AU - Adjouadi, Malek
AU - Cabrerizo, Mercedes
AU - Barreto, Armando
AU - Andrian, Jean
AU - Duara, Ranjan
AU - Loewenstein, David
N1 - Publisher Copyright:
© 2017 IEEE.
PY - 2017/7/1
Y1 - 2017/7/1
N2 - Neuroimaging is an important research platform that can be very useful for eliciting new understanding on the complicated pathogenesis between genetics and disease phenotypes. Due to the extremely high dimensionality of image and genetic data, and considering the potential joint effect of genetic variants, multivariate techniques have been examined to detect Alzheimers disease (AD) related genetic variants expressed through single-nucleotide polymorphisms (SNPs). However, the image features used in support of those methods are not immediately related to the disease, and the detected genetic markers may not be related to AD. In this study, we propose an ensemble model based framework for firstly extracting 50 region-based image features whose values are predicted by base learners trained on raw neuroimaging morphological variables. This task is followed by performing sparse Partial Least Squares regression (sPLS) method on the extracted 50 AD related image features and pre-selected 1508 SNPs to detect the significant SNPs associated with the extracted image features. Instead of modeling a direct link between genetic variants and disease label, we captured disease information indirectly.
AB - Neuroimaging is an important research platform that can be very useful for eliciting new understanding on the complicated pathogenesis between genetics and disease phenotypes. Due to the extremely high dimensionality of image and genetic data, and considering the potential joint effect of genetic variants, multivariate techniques have been examined to detect Alzheimers disease (AD) related genetic variants expressed through single-nucleotide polymorphisms (SNPs). However, the image features used in support of those methods are not immediately related to the disease, and the detected genetic markers may not be related to AD. In this study, we propose an ensemble model based framework for firstly extracting 50 region-based image features whose values are predicted by base learners trained on raw neuroimaging morphological variables. This task is followed by performing sparse Partial Least Squares regression (sPLS) method on the extracted 50 AD related image features and pre-selected 1508 SNPs to detect the significant SNPs associated with the extracted image features. Instead of modeling a direct link between genetic variants and disease label, we captured disease information indirectly.
KW - Alzheimers disease
KW - Genome-wide association studies
KW - feature extraction
KW - genetics
KW - neuroimaging
KW - sparse partial least squares regression
UR - http://www.scopus.com/inward/record.url?scp=85045990720&partnerID=8YFLogxK
UR - http://www.scopus.com/inward/citedby.url?scp=85045990720&partnerID=8YFLogxK
U2 - 10.1109/BIBE.2017.00-85
DO - 10.1109/BIBE.2017.00-85
M3 - Conference contribution
AN - SCOPUS:85045990720
T3 - Proceedings - 2017 IEEE 17th International Conference on Bioinformatics and Bioengineering, BIBE 2017
SP - 15
EP - 20
BT - Proceedings - 2017 IEEE 17th International Conference on Bioinformatics and Bioengineering, BIBE 2017
PB - Institute of Electrical and Electronics Engineers Inc.
T2 - 17th IEEE International Conference on Bioinformatics and Bioengineering, BIBE 2017
Y2 - 23 October 2017 through 25 October 2017
ER -