Abstract
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.
| Original language | English (US) |
|---|---|
| Title of host publication | Proceedings - 2017 IEEE 17th International Conference on Bioinformatics and Bioengineering, BIBE 2017 |
| Publisher | Institute of Electrical and Electronics Engineers Inc. |
| Pages | 15-20 |
| Number of pages | 6 |
| Volume | 2018-January |
| ISBN (Electronic) | 9781538613245 |
| DOIs | |
| State | Published - Jan 8 2018 |
| Event | 17th IEEE International Conference on Bioinformatics and Bioengineering, BIBE 2017 - Herndon, United States Duration: Oct 23 2017 → Oct 25 2017 |
Other
| Other | 17th IEEE International Conference on Bioinformatics and Bioengineering, BIBE 2017 |
|---|---|
| Country | United States |
| City | Herndon |
| Period | 10/23/17 → 10/25/17 |
Fingerprint
Keywords
- Alzheimers disease
- feature extraction
- genetics
- Genome-wide association studies
- neuroimaging
- sparse partial least squares regression
ASJC Scopus subject areas
- Information Systems
- Biomedical Engineering
- Modeling and Simulation
- Signal Processing
- Health Informatics
Cite this
A Neuroimaging Feature Extraction Model for Imaging Genetics with Application to Alzheimer's Disease. / Li, Chunfei; Fang, Chen; Adjouadi, Malek; Cabrerizo, Mercedes; Barreto, Armando; Andrian, Jean; Duara, Ranjan; Loewenstein, David.
Proceedings - 2017 IEEE 17th International Conference on Bioinformatics and Bioengineering, BIBE 2017. Vol. 2018-January Institute of Electrical and Electronics Engineers Inc., 2018. p. 15-20.Research output: Chapter in Book/Report/Conference proceeding › Conference contribution
}
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
PY - 2018/1/8
Y1 - 2018/1/8
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 - feature extraction
KW - genetics
KW - Genome-wide association studies
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
VL - 2018-January
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.
ER -