Sparse Bayesian multi-task learning for predicting cognitive outcomes from neuroimaging measures in Alzheimer's disease

Jing Wan, Zhilin Zhang, Jingwen Yan, Taiyong Li, Bhaskar D. Rao, Shiaofen Fang, Sungeun Kim, Shannon L. Risacher, Andrew Saykin, Li Shen

Research output: Chapter in Book/Report/Conference proceedingConference contribution

37 Citations (Scopus)

Abstract

Alzheimer's disease (AD) is the most common form of dementia that causes progressive impairment of memory and other cognitive functions. Multivariate regression models have been studied in AD for revealing relationships between neuroimaging measures and cognitive scores to understand how structural changes in brain can influence cognitive status. Existing regression methods, however, do not explicitly model dependence relation among multiple scores derived from a single cognitive test. It has been found that such dependence can deteriorate the performance of these methods. To overcome this limitation, we propose an efficient sparse Bayesian multi-task learning algorithm, which adaptively learns and exploits the dependence to achieve improved prediction performance. The proposed algorithm is applied to a real world neuroimaging study in AD to predict cognitive performance using MRI scans. The effectiveness of the proposed algorithm is demonstrated by its superior prediction performance over multiple state-of-the-art competing methods and accurate identification of compact sets of cognition-relevant imaging biomarkers that are consistent with prior knowledge.

Original languageEnglish
Title of host publicationProceedings of the IEEE Computer Society Conference on Computer Vision and Pattern Recognition
Pages940-947
Number of pages8
DOIs
StatePublished - 2012
Event2012 IEEE Conference on Computer Vision and Pattern Recognition, CVPR 2012 - Providence, RI, United States
Duration: Jun 16 2012Jun 21 2012

Other

Other2012 IEEE Conference on Computer Vision and Pattern Recognition, CVPR 2012
CountryUnited States
CityProvidence, RI
Period6/16/126/21/12

Fingerprint

Neuroimaging
Biomarkers
Learning algorithms
Brain
Imaging techniques
Data storage equipment

ASJC Scopus subject areas

  • Software
  • Computer Vision and Pattern Recognition

Cite this

Wan, J., Zhang, Z., Yan, J., Li, T., Rao, B. D., Fang, S., ... Shen, L. (2012). Sparse Bayesian multi-task learning for predicting cognitive outcomes from neuroimaging measures in Alzheimer's disease. In Proceedings of the IEEE Computer Society Conference on Computer Vision and Pattern Recognition (pp. 940-947). [6247769] https://doi.org/10.1109/CVPR.2012.6247769

Sparse Bayesian multi-task learning for predicting cognitive outcomes from neuroimaging measures in Alzheimer's disease. / Wan, Jing; Zhang, Zhilin; Yan, Jingwen; Li, Taiyong; Rao, Bhaskar D.; Fang, Shiaofen; Kim, Sungeun; Risacher, Shannon L.; Saykin, Andrew; Shen, Li.

Proceedings of the IEEE Computer Society Conference on Computer Vision and Pattern Recognition. 2012. p. 940-947 6247769.

Research output: Chapter in Book/Report/Conference proceedingConference contribution

Wan, J, Zhang, Z, Yan, J, Li, T, Rao, BD, Fang, S, Kim, S, Risacher, SL, Saykin, A & Shen, L 2012, Sparse Bayesian multi-task learning for predicting cognitive outcomes from neuroimaging measures in Alzheimer's disease. in Proceedings of the IEEE Computer Society Conference on Computer Vision and Pattern Recognition., 6247769, pp. 940-947, 2012 IEEE Conference on Computer Vision and Pattern Recognition, CVPR 2012, Providence, RI, United States, 6/16/12. https://doi.org/10.1109/CVPR.2012.6247769
Wan J, Zhang Z, Yan J, Li T, Rao BD, Fang S et al. Sparse Bayesian multi-task learning for predicting cognitive outcomes from neuroimaging measures in Alzheimer's disease. In Proceedings of the IEEE Computer Society Conference on Computer Vision and Pattern Recognition. 2012. p. 940-947. 6247769 https://doi.org/10.1109/CVPR.2012.6247769
Wan, Jing ; Zhang, Zhilin ; Yan, Jingwen ; Li, Taiyong ; Rao, Bhaskar D. ; Fang, Shiaofen ; Kim, Sungeun ; Risacher, Shannon L. ; Saykin, Andrew ; Shen, Li. / Sparse Bayesian multi-task learning for predicting cognitive outcomes from neuroimaging measures in Alzheimer's disease. Proceedings of the IEEE Computer Society Conference on Computer Vision and Pattern Recognition. 2012. pp. 940-947
@inproceedings{36b2f261a32f4a65822eae863adabefb,
title = "Sparse Bayesian multi-task learning for predicting cognitive outcomes from neuroimaging measures in Alzheimer's disease",
abstract = "Alzheimer's disease (AD) is the most common form of dementia that causes progressive impairment of memory and other cognitive functions. Multivariate regression models have been studied in AD for revealing relationships between neuroimaging measures and cognitive scores to understand how structural changes in brain can influence cognitive status. Existing regression methods, however, do not explicitly model dependence relation among multiple scores derived from a single cognitive test. It has been found that such dependence can deteriorate the performance of these methods. To overcome this limitation, we propose an efficient sparse Bayesian multi-task learning algorithm, which adaptively learns and exploits the dependence to achieve improved prediction performance. The proposed algorithm is applied to a real world neuroimaging study in AD to predict cognitive performance using MRI scans. The effectiveness of the proposed algorithm is demonstrated by its superior prediction performance over multiple state-of-the-art competing methods and accurate identification of compact sets of cognition-relevant imaging biomarkers that are consistent with prior knowledge.",
author = "Jing Wan and Zhilin Zhang and Jingwen Yan and Taiyong Li and Rao, {Bhaskar D.} and Shiaofen Fang and Sungeun Kim and Risacher, {Shannon L.} and Andrew Saykin and Li Shen",
year = "2012",
doi = "10.1109/CVPR.2012.6247769",
language = "English",
isbn = "9781467312264",
pages = "940--947",
booktitle = "Proceedings of the IEEE Computer Society Conference on Computer Vision and Pattern Recognition",

}

TY - GEN

T1 - Sparse Bayesian multi-task learning for predicting cognitive outcomes from neuroimaging measures in Alzheimer's disease

AU - Wan, Jing

AU - Zhang, Zhilin

AU - Yan, Jingwen

AU - Li, Taiyong

AU - Rao, Bhaskar D.

AU - Fang, Shiaofen

AU - Kim, Sungeun

AU - Risacher, Shannon L.

AU - Saykin, Andrew

AU - Shen, Li

PY - 2012

Y1 - 2012

N2 - Alzheimer's disease (AD) is the most common form of dementia that causes progressive impairment of memory and other cognitive functions. Multivariate regression models have been studied in AD for revealing relationships between neuroimaging measures and cognitive scores to understand how structural changes in brain can influence cognitive status. Existing regression methods, however, do not explicitly model dependence relation among multiple scores derived from a single cognitive test. It has been found that such dependence can deteriorate the performance of these methods. To overcome this limitation, we propose an efficient sparse Bayesian multi-task learning algorithm, which adaptively learns and exploits the dependence to achieve improved prediction performance. The proposed algorithm is applied to a real world neuroimaging study in AD to predict cognitive performance using MRI scans. The effectiveness of the proposed algorithm is demonstrated by its superior prediction performance over multiple state-of-the-art competing methods and accurate identification of compact sets of cognition-relevant imaging biomarkers that are consistent with prior knowledge.

AB - Alzheimer's disease (AD) is the most common form of dementia that causes progressive impairment of memory and other cognitive functions. Multivariate regression models have been studied in AD for revealing relationships between neuroimaging measures and cognitive scores to understand how structural changes in brain can influence cognitive status. Existing regression methods, however, do not explicitly model dependence relation among multiple scores derived from a single cognitive test. It has been found that such dependence can deteriorate the performance of these methods. To overcome this limitation, we propose an efficient sparse Bayesian multi-task learning algorithm, which adaptively learns and exploits the dependence to achieve improved prediction performance. The proposed algorithm is applied to a real world neuroimaging study in AD to predict cognitive performance using MRI scans. The effectiveness of the proposed algorithm is demonstrated by its superior prediction performance over multiple state-of-the-art competing methods and accurate identification of compact sets of cognition-relevant imaging biomarkers that are consistent with prior knowledge.

UR - http://www.scopus.com/inward/record.url?scp=84866683998&partnerID=8YFLogxK

UR - http://www.scopus.com/inward/citedby.url?scp=84866683998&partnerID=8YFLogxK

U2 - 10.1109/CVPR.2012.6247769

DO - 10.1109/CVPR.2012.6247769

M3 - Conference contribution

AN - SCOPUS:84866683998

SN - 9781467312264

SP - 940

EP - 947

BT - Proceedings of the IEEE Computer Society Conference on Computer Vision and Pattern Recognition

ER -