Predicting progressions of cognitive outcomes via high-order multi-modal multi-task feature learning

Lyujian Lu, Hua Wang, Xiaohui Yao, Shannon Risacher, Andrew Saykin, Li Shen

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

2 Citations (Scopus)

Abstract

Many existing studies on complex brain disorders, such as Alzheimer's Disease, usually employed regression analysis to associate the neuroimaging measures to cognitive status. However, whether these measures in multiple modalities have the predictive power to infer the trajectory of cognitive performance over time still remain under-explored. In this paper, we propose a high-order multi-modal multi-mask feature learning model to uncover temporal relationship between the longitudinal neuroimaging measures and progressive cognitive output scores. The regularizations through sparsity-induced norms implemented in the proposed learning model enable the selection of only a small number of imaging features over time and capture modality structures for multi-modal imaging markers. The promising experimental results in extensive empirical studies performed on the ADNI cohort have validated the effectiveness of the proposed method.

Original languageEnglish (US)
Title of host publication2018 IEEE 15th International Symposium on Biomedical Imaging, ISBI 2018
PublisherIEEE Computer Society
Pages545-548
Number of pages4
Volume2018-April
ISBN (Electronic)9781538636367
DOIs
StatePublished - May 23 2018
Event15th IEEE International Symposium on Biomedical Imaging, ISBI 2018 - Washington, United States
Duration: Apr 4 2018Apr 7 2018

Other

Other15th IEEE International Symposium on Biomedical Imaging, ISBI 2018
CountryUnited States
CityWashington
Period4/4/184/7/18

Fingerprint

Neuroimaging
Learning
Imaging techniques
Regression analysis
Masks
Brain
Trajectories
Brain Diseases
Alzheimer Disease
Regression Analysis

Keywords

  • Alzheimer's Disease
  • Feature Learning
  • Longitudinal Regression
  • Multi-Modal

ASJC Scopus subject areas

  • Biomedical Engineering
  • Radiology Nuclear Medicine and imaging

Cite this

Lu, L., Wang, H., Yao, X., Risacher, S., Saykin, A., & Shen, L. (2018). Predicting progressions of cognitive outcomes via high-order multi-modal multi-task feature learning. In 2018 IEEE 15th International Symposium on Biomedical Imaging, ISBI 2018 (Vol. 2018-April, pp. 545-548). IEEE Computer Society. https://doi.org/10.1109/ISBI.2018.8363635

Predicting progressions of cognitive outcomes via high-order multi-modal multi-task feature learning. / Lu, Lyujian; Wang, Hua; Yao, Xiaohui; Risacher, Shannon; Saykin, Andrew; Shen, Li.

2018 IEEE 15th International Symposium on Biomedical Imaging, ISBI 2018. Vol. 2018-April IEEE Computer Society, 2018. p. 545-548.

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

Lu, L, Wang, H, Yao, X, Risacher, S, Saykin, A & Shen, L 2018, Predicting progressions of cognitive outcomes via high-order multi-modal multi-task feature learning. in 2018 IEEE 15th International Symposium on Biomedical Imaging, ISBI 2018. vol. 2018-April, IEEE Computer Society, pp. 545-548, 15th IEEE International Symposium on Biomedical Imaging, ISBI 2018, Washington, United States, 4/4/18. https://doi.org/10.1109/ISBI.2018.8363635
Lu L, Wang H, Yao X, Risacher S, Saykin A, Shen L. Predicting progressions of cognitive outcomes via high-order multi-modal multi-task feature learning. In 2018 IEEE 15th International Symposium on Biomedical Imaging, ISBI 2018. Vol. 2018-April. IEEE Computer Society. 2018. p. 545-548 https://doi.org/10.1109/ISBI.2018.8363635
Lu, Lyujian ; Wang, Hua ; Yao, Xiaohui ; Risacher, Shannon ; Saykin, Andrew ; Shen, Li. / Predicting progressions of cognitive outcomes via high-order multi-modal multi-task feature learning. 2018 IEEE 15th International Symposium on Biomedical Imaging, ISBI 2018. Vol. 2018-April IEEE Computer Society, 2018. pp. 545-548
@inproceedings{64524b1dd9654d9ea6142a8babd948be,
title = "Predicting progressions of cognitive outcomes via high-order multi-modal multi-task feature learning",
abstract = "Many existing studies on complex brain disorders, such as Alzheimer's Disease, usually employed regression analysis to associate the neuroimaging measures to cognitive status. However, whether these measures in multiple modalities have the predictive power to infer the trajectory of cognitive performance over time still remain under-explored. In this paper, we propose a high-order multi-modal multi-mask feature learning model to uncover temporal relationship between the longitudinal neuroimaging measures and progressive cognitive output scores. The regularizations through sparsity-induced norms implemented in the proposed learning model enable the selection of only a small number of imaging features over time and capture modality structures for multi-modal imaging markers. The promising experimental results in extensive empirical studies performed on the ADNI cohort have validated the effectiveness of the proposed method.",
keywords = "Alzheimer's Disease, Feature Learning, Longitudinal Regression, Multi-Modal",
author = "Lyujian Lu and Hua Wang and Xiaohui Yao and Shannon Risacher and Andrew Saykin and Li Shen",
year = "2018",
month = "5",
day = "23",
doi = "10.1109/ISBI.2018.8363635",
language = "English (US)",
volume = "2018-April",
pages = "545--548",
booktitle = "2018 IEEE 15th International Symposium on Biomedical Imaging, ISBI 2018",
publisher = "IEEE Computer Society",
address = "United States",

}

TY - GEN

T1 - Predicting progressions of cognitive outcomes via high-order multi-modal multi-task feature learning

AU - Lu, Lyujian

AU - Wang, Hua

AU - Yao, Xiaohui

AU - Risacher, Shannon

AU - Saykin, Andrew

AU - Shen, Li

PY - 2018/5/23

Y1 - 2018/5/23

N2 - Many existing studies on complex brain disorders, such as Alzheimer's Disease, usually employed regression analysis to associate the neuroimaging measures to cognitive status. However, whether these measures in multiple modalities have the predictive power to infer the trajectory of cognitive performance over time still remain under-explored. In this paper, we propose a high-order multi-modal multi-mask feature learning model to uncover temporal relationship between the longitudinal neuroimaging measures and progressive cognitive output scores. The regularizations through sparsity-induced norms implemented in the proposed learning model enable the selection of only a small number of imaging features over time and capture modality structures for multi-modal imaging markers. The promising experimental results in extensive empirical studies performed on the ADNI cohort have validated the effectiveness of the proposed method.

AB - Many existing studies on complex brain disorders, such as Alzheimer's Disease, usually employed regression analysis to associate the neuroimaging measures to cognitive status. However, whether these measures in multiple modalities have the predictive power to infer the trajectory of cognitive performance over time still remain under-explored. In this paper, we propose a high-order multi-modal multi-mask feature learning model to uncover temporal relationship between the longitudinal neuroimaging measures and progressive cognitive output scores. The regularizations through sparsity-induced norms implemented in the proposed learning model enable the selection of only a small number of imaging features over time and capture modality structures for multi-modal imaging markers. The promising experimental results in extensive empirical studies performed on the ADNI cohort have validated the effectiveness of the proposed method.

KW - Alzheimer's Disease

KW - Feature Learning

KW - Longitudinal Regression

KW - Multi-Modal

UR - http://www.scopus.com/inward/record.url?scp=85048117531&partnerID=8YFLogxK

UR - http://www.scopus.com/inward/citedby.url?scp=85048117531&partnerID=8YFLogxK

U2 - 10.1109/ISBI.2018.8363635

DO - 10.1109/ISBI.2018.8363635

M3 - Conference contribution

AN - SCOPUS:85048117531

VL - 2018-April

SP - 545

EP - 548

BT - 2018 IEEE 15th International Symposium on Biomedical Imaging, ISBI 2018

PB - IEEE Computer Society

ER -