Multi-task sparse screening for predicting future clinical scores using longitudinal cortical thickness measures

Jie Zhang, Yanshuai Tu, Qingyang Li, Richard John Caselli, Paul M. Thompson, Jieping Ye, Yalin Wang

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

1 Citation (Scopus)

Abstract

Cortical thickness estimation performed in-vivo via magnetic resonance imaging (MRI) is an effective measure of brain atrophy in preclinical individuals at high risk for Alzheimer's disease (AD). However, the high dimensionality of individual cortical thickness data coupled with small population samples make it challenging to perform cortical thickness feature selection for AD diagnosis and prognosis. Thus far, there are very few methods that can accurately predict future clinical scores using longitudinal cortical thickness measures. In this paper, we propose an unsupervised dictionary learning algorithm, termed Multi-task Sparse Screening (MSS) that produces improved results over previous methods within this problem domain. Specifically, we formulate and solve a multi-task problem using extracted top-p significant features from the Alzheimer's Disease Neuroimaging Initiative (ADNI) longitudinal data. Empirical studies on publicly available longitudinal data from ADNI dataset (N = 2797) demonstrate improved correlation coefficients and root mean square errors, when compared to other algorithms.

Original languageEnglish (US)
Title of host publication2018 IEEE 15th International Symposium on Biomedical Imaging, ISBI 2018
PublisherIEEE Computer Society
Pages1406-1410
Number of pages5
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

Alzheimer Disease
Screening
Neuroimaging
Magnetic resonance
Glossaries
Mean square error
Learning algorithms
Atrophy
Feature extraction
Brain
Magnetic Resonance Imaging
Learning
Imaging techniques
Population

Keywords

  • Alzheimer's Disease
  • Cortical Thickness
  • Dictionary Learning
  • Group Lasso
  • Multi-task

ASJC Scopus subject areas

  • Biomedical Engineering
  • Radiology Nuclear Medicine and imaging

Cite this

Zhang, J., Tu, Y., Li, Q., Caselli, R. J., Thompson, P. M., Ye, J., & Wang, Y. (2018). Multi-task sparse screening for predicting future clinical scores using longitudinal cortical thickness measures. In 2018 IEEE 15th International Symposium on Biomedical Imaging, ISBI 2018 (Vol. 2018-April, pp. 1406-1410). IEEE Computer Society. https://doi.org/10.1109/ISBI.2018.8363835

Multi-task sparse screening for predicting future clinical scores using longitudinal cortical thickness measures. / Zhang, Jie; Tu, Yanshuai; Li, Qingyang; Caselli, Richard John; Thompson, Paul M.; Ye, Jieping; Wang, Yalin.

2018 IEEE 15th International Symposium on Biomedical Imaging, ISBI 2018. Vol. 2018-April IEEE Computer Society, 2018. p. 1406-1410.

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

Zhang, J, Tu, Y, Li, Q, Caselli, RJ, Thompson, PM, Ye, J & Wang, Y 2018, Multi-task sparse screening for predicting future clinical scores using longitudinal cortical thickness measures. in 2018 IEEE 15th International Symposium on Biomedical Imaging, ISBI 2018. vol. 2018-April, IEEE Computer Society, pp. 1406-1410, 15th IEEE International Symposium on Biomedical Imaging, ISBI 2018, Washington, United States, 4/4/18. https://doi.org/10.1109/ISBI.2018.8363835
Zhang J, Tu Y, Li Q, Caselli RJ, Thompson PM, Ye J et al. Multi-task sparse screening for predicting future clinical scores using longitudinal cortical thickness measures. In 2018 IEEE 15th International Symposium on Biomedical Imaging, ISBI 2018. Vol. 2018-April. IEEE Computer Society. 2018. p. 1406-1410 https://doi.org/10.1109/ISBI.2018.8363835
Zhang, Jie ; Tu, Yanshuai ; Li, Qingyang ; Caselli, Richard John ; Thompson, Paul M. ; Ye, Jieping ; Wang, Yalin. / Multi-task sparse screening for predicting future clinical scores using longitudinal cortical thickness measures. 2018 IEEE 15th International Symposium on Biomedical Imaging, ISBI 2018. Vol. 2018-April IEEE Computer Society, 2018. pp. 1406-1410
@inproceedings{da56f05f3cb940efb225181a7be0d5d7,
title = "Multi-task sparse screening for predicting future clinical scores using longitudinal cortical thickness measures",
abstract = "Cortical thickness estimation performed in-vivo via magnetic resonance imaging (MRI) is an effective measure of brain atrophy in preclinical individuals at high risk for Alzheimer's disease (AD). However, the high dimensionality of individual cortical thickness data coupled with small population samples make it challenging to perform cortical thickness feature selection for AD diagnosis and prognosis. Thus far, there are very few methods that can accurately predict future clinical scores using longitudinal cortical thickness measures. In this paper, we propose an unsupervised dictionary learning algorithm, termed Multi-task Sparse Screening (MSS) that produces improved results over previous methods within this problem domain. Specifically, we formulate and solve a multi-task problem using extracted top-p significant features from the Alzheimer's Disease Neuroimaging Initiative (ADNI) longitudinal data. Empirical studies on publicly available longitudinal data from ADNI dataset (N = 2797) demonstrate improved correlation coefficients and root mean square errors, when compared to other algorithms.",
keywords = "Alzheimer's Disease, Cortical Thickness, Dictionary Learning, Group Lasso, Multi-task",
author = "Jie Zhang and Yanshuai Tu and Qingyang Li and Caselli, {Richard John} and Thompson, {Paul M.} and Jieping Ye and Yalin Wang",
year = "2018",
month = "5",
day = "23",
doi = "10.1109/ISBI.2018.8363835",
language = "English (US)",
volume = "2018-April",
pages = "1406--1410",
booktitle = "2018 IEEE 15th International Symposium on Biomedical Imaging, ISBI 2018",
publisher = "IEEE Computer Society",

}

TY - GEN

T1 - Multi-task sparse screening for predicting future clinical scores using longitudinal cortical thickness measures

AU - Zhang, Jie

AU - Tu, Yanshuai

AU - Li, Qingyang

AU - Caselli, Richard John

AU - Thompson, Paul M.

AU - Ye, Jieping

AU - Wang, Yalin

PY - 2018/5/23

Y1 - 2018/5/23

N2 - Cortical thickness estimation performed in-vivo via magnetic resonance imaging (MRI) is an effective measure of brain atrophy in preclinical individuals at high risk for Alzheimer's disease (AD). However, the high dimensionality of individual cortical thickness data coupled with small population samples make it challenging to perform cortical thickness feature selection for AD diagnosis and prognosis. Thus far, there are very few methods that can accurately predict future clinical scores using longitudinal cortical thickness measures. In this paper, we propose an unsupervised dictionary learning algorithm, termed Multi-task Sparse Screening (MSS) that produces improved results over previous methods within this problem domain. Specifically, we formulate and solve a multi-task problem using extracted top-p significant features from the Alzheimer's Disease Neuroimaging Initiative (ADNI) longitudinal data. Empirical studies on publicly available longitudinal data from ADNI dataset (N = 2797) demonstrate improved correlation coefficients and root mean square errors, when compared to other algorithms.

AB - Cortical thickness estimation performed in-vivo via magnetic resonance imaging (MRI) is an effective measure of brain atrophy in preclinical individuals at high risk for Alzheimer's disease (AD). However, the high dimensionality of individual cortical thickness data coupled with small population samples make it challenging to perform cortical thickness feature selection for AD diagnosis and prognosis. Thus far, there are very few methods that can accurately predict future clinical scores using longitudinal cortical thickness measures. In this paper, we propose an unsupervised dictionary learning algorithm, termed Multi-task Sparse Screening (MSS) that produces improved results over previous methods within this problem domain. Specifically, we formulate and solve a multi-task problem using extracted top-p significant features from the Alzheimer's Disease Neuroimaging Initiative (ADNI) longitudinal data. Empirical studies on publicly available longitudinal data from ADNI dataset (N = 2797) demonstrate improved correlation coefficients and root mean square errors, when compared to other algorithms.

KW - Alzheimer's Disease

KW - Cortical Thickness

KW - Dictionary Learning

KW - Group Lasso

KW - Multi-task

UR - http://www.scopus.com/inward/record.url?scp=85048101340&partnerID=8YFLogxK

UR - http://www.scopus.com/inward/citedby.url?scp=85048101340&partnerID=8YFLogxK

U2 - 10.1109/ISBI.2018.8363835

DO - 10.1109/ISBI.2018.8363835

M3 - Conference contribution

AN - SCOPUS:85048101340

VL - 2018-April

SP - 1406

EP - 1410

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

PB - IEEE Computer Society

ER -