Conversion and time-to-conversion predictions of mild cognitive impairment using low-rank affinity pursuit denoising and matrix completion

for the Alzheimer's Disease Neuroimaging Initiative

Research output: Contribution to journalArticle

6 Citations (Scopus)

Abstract

In this paper, we aim to predict conversion and time-to-conversion of mild cognitive impairment (MCI) patients using multi-modal neuroimaging data and clinical data, via cross-sectional and longitudinal studies. However, such data are often heterogeneous, high-dimensional, noisy, and incomplete. We thus propose a framework that includes sparse feature selection, low-rank affinity pursuit denoising (LRAD), and low-rank matrix completion (LRMC) in this study. Specifically, we first use sparse linear regressions to remove unrelated features. Then, considering the heterogeneity of the MCI data, which can be assumed as a union of multiple subspaces, we propose to use a low rank subspace method (i.e., LRAD) to denoise the data. Finally, we employ LRMC algorithm with three data fitting terms and one inequality constraint for joint conversion and time-to-conversion predictions. Our framework aims to answer a very important but yet rarely explored question in AD study, i.e., when will the MCI convert to AD? This is different from survival analysis, which provides the probabilities of conversion at different time points that are mainly used for global analysis, while our time-to-conversion prediction is for each individual subject. Evaluations using the ADNI dataset indicate that our method outperforms conventional LRMC and other state-of-the-art methods. Our method achieves a maximal pMCI classification accuracy of 84% and time prediction correlation of 0.665.

Original languageEnglish
Pages (from-to)68-82
Number of pages15
JournalMedical Image Analysis
Volume45
DOIs
Publication statusPublished - 2018 Apr 1

Fingerprint

Neuroimaging
Linear regression
Feature extraction
Survival Analysis
Longitudinal Studies
Linear Models
Cross-Sectional Studies
Joints
Cognitive Dysfunction
Datasets

Keywords

  • Classification
  • Data imputation
  • Low-rank representation
  • Matrix completion
  • Multi-task learning

ASJC Scopus subject areas

  • Radiological and Ultrasound Technology
  • Radiology Nuclear Medicine and imaging
  • Computer Vision and Pattern Recognition
  • Health Informatics
  • Computer Graphics and Computer-Aided Design

Cite this

Conversion and time-to-conversion predictions of mild cognitive impairment using low-rank affinity pursuit denoising and matrix completion. / for the Alzheimer's Disease Neuroimaging Initiative.

In: Medical Image Analysis, Vol. 45, 01.04.2018, p. 68-82.

Research output: Contribution to journalArticle

@article{41f22399adf9486d8804a51bd32f6c3a,
title = "Conversion and time-to-conversion predictions of mild cognitive impairment using low-rank affinity pursuit denoising and matrix completion",
abstract = "In this paper, we aim to predict conversion and time-to-conversion of mild cognitive impairment (MCI) patients using multi-modal neuroimaging data and clinical data, via cross-sectional and longitudinal studies. However, such data are often heterogeneous, high-dimensional, noisy, and incomplete. We thus propose a framework that includes sparse feature selection, low-rank affinity pursuit denoising (LRAD), and low-rank matrix completion (LRMC) in this study. Specifically, we first use sparse linear regressions to remove unrelated features. Then, considering the heterogeneity of the MCI data, which can be assumed as a union of multiple subspaces, we propose to use a low rank subspace method (i.e., LRAD) to denoise the data. Finally, we employ LRMC algorithm with three data fitting terms and one inequality constraint for joint conversion and time-to-conversion predictions. Our framework aims to answer a very important but yet rarely explored question in AD study, i.e., when will the MCI convert to AD? This is different from survival analysis, which provides the probabilities of conversion at different time points that are mainly used for global analysis, while our time-to-conversion prediction is for each individual subject. Evaluations using the ADNI dataset indicate that our method outperforms conventional LRMC and other state-of-the-art methods. Our method achieves a maximal pMCI classification accuracy of 84{\%} and time prediction correlation of 0.665.",
keywords = "Classification, Data imputation, Low-rank representation, Matrix completion, Multi-task learning",
author = "{for the Alzheimer's Disease Neuroimaging Initiative} and Thung, {Kim Han} and Yap, {Pew Thian} and Ehsan Adeli and Lee, {Seong Whan} and Dinggang Shen",
year = "2018",
month = "4",
day = "1",
doi = "10.1016/j.media.2018.01.002",
language = "English",
volume = "45",
pages = "68--82",
journal = "Medical Image Analysis",
issn = "1361-8415",
publisher = "Elsevier",

}

TY - JOUR

T1 - Conversion and time-to-conversion predictions of mild cognitive impairment using low-rank affinity pursuit denoising and matrix completion

AU - for the Alzheimer's Disease Neuroimaging Initiative

AU - Thung, Kim Han

AU - Yap, Pew Thian

AU - Adeli, Ehsan

AU - Lee, Seong Whan

AU - Shen, Dinggang

PY - 2018/4/1

Y1 - 2018/4/1

N2 - In this paper, we aim to predict conversion and time-to-conversion of mild cognitive impairment (MCI) patients using multi-modal neuroimaging data and clinical data, via cross-sectional and longitudinal studies. However, such data are often heterogeneous, high-dimensional, noisy, and incomplete. We thus propose a framework that includes sparse feature selection, low-rank affinity pursuit denoising (LRAD), and low-rank matrix completion (LRMC) in this study. Specifically, we first use sparse linear regressions to remove unrelated features. Then, considering the heterogeneity of the MCI data, which can be assumed as a union of multiple subspaces, we propose to use a low rank subspace method (i.e., LRAD) to denoise the data. Finally, we employ LRMC algorithm with three data fitting terms and one inequality constraint for joint conversion and time-to-conversion predictions. Our framework aims to answer a very important but yet rarely explored question in AD study, i.e., when will the MCI convert to AD? This is different from survival analysis, which provides the probabilities of conversion at different time points that are mainly used for global analysis, while our time-to-conversion prediction is for each individual subject. Evaluations using the ADNI dataset indicate that our method outperforms conventional LRMC and other state-of-the-art methods. Our method achieves a maximal pMCI classification accuracy of 84% and time prediction correlation of 0.665.

AB - In this paper, we aim to predict conversion and time-to-conversion of mild cognitive impairment (MCI) patients using multi-modal neuroimaging data and clinical data, via cross-sectional and longitudinal studies. However, such data are often heterogeneous, high-dimensional, noisy, and incomplete. We thus propose a framework that includes sparse feature selection, low-rank affinity pursuit denoising (LRAD), and low-rank matrix completion (LRMC) in this study. Specifically, we first use sparse linear regressions to remove unrelated features. Then, considering the heterogeneity of the MCI data, which can be assumed as a union of multiple subspaces, we propose to use a low rank subspace method (i.e., LRAD) to denoise the data. Finally, we employ LRMC algorithm with three data fitting terms and one inequality constraint for joint conversion and time-to-conversion predictions. Our framework aims to answer a very important but yet rarely explored question in AD study, i.e., when will the MCI convert to AD? This is different from survival analysis, which provides the probabilities of conversion at different time points that are mainly used for global analysis, while our time-to-conversion prediction is for each individual subject. Evaluations using the ADNI dataset indicate that our method outperforms conventional LRMC and other state-of-the-art methods. Our method achieves a maximal pMCI classification accuracy of 84% and time prediction correlation of 0.665.

KW - Classification

KW - Data imputation

KW - Low-rank representation

KW - Matrix completion

KW - Multi-task learning

UR - http://www.scopus.com/inward/record.url?scp=85041459324&partnerID=8YFLogxK

UR - http://www.scopus.com/inward/citedby.url?scp=85041459324&partnerID=8YFLogxK

U2 - 10.1016/j.media.2018.01.002

DO - 10.1016/j.media.2018.01.002

M3 - Article

VL - 45

SP - 68

EP - 82

JO - Medical Image Analysis

JF - Medical Image Analysis

SN - 1361-8415

ER -