Multi-task prediction of infant cognitive scores from longitudinal incomplete neuroimaging data

Ehsan Adeli, Yu Meng, Gang Li, Weili Lin, Dinggang Shen

Research output: Contribution to journalArticle

2 Citations (Scopus)

Abstract

Early postnatal brain undergoes a stunning period of development. Over the past few years, research on dynamic infant brain development has received increased attention, exhibiting how important the early stages of a child's life are in terms of brain development. To precisely chart the early brain developmental trajectories, longitudinal studies with data acquired over a long-enough period of infants' early life is essential. However, in practice, missing data from different time point(s) during the data gathering procedure is often inevitable. This leads to incomplete set of longitudinal data, which poses a major challenge for such studies. In this paper, prediction of multiple future cognitive scores with incomplete longitudinal imaging data is modeled into a multi-task machine learning framework. To efficiently learn this model, we account for selection of informative features (i.e., neuroimaging morphometric measurements for different time points), while preserving the structural information and the interrelation between these multiple cognitive scores. Several experiments are conducted on a carefully acquired in-house dataset, and the results affirm that we can predict the cognitive scores measured at the age of four years old, using the imaging data of earlier time points, as early as 24 months of age, with a reasonable performance (i.e., root mean square error of 0.18).

Original languageEnglish
JournalNeuroImage
DOIs
Publication statusAccepted/In press - 2018 Jan 1

Fingerprint

Neuroimaging
Brain
Child Development
Longitudinal Studies
Research
Datasets

Keywords

  • Bag-of-words
  • Brain fingerprinting
  • Longitudinal incomplete data
  • Low-rank tensor
  • Multi-task learning
  • Postnatal brain development
  • Sparsity

ASJC Scopus subject areas

  • Neurology
  • Cognitive Neuroscience

Cite this

Multi-task prediction of infant cognitive scores from longitudinal incomplete neuroimaging data. / Adeli, Ehsan; Meng, Yu; Li, Gang; Lin, Weili; Shen, Dinggang.

In: NeuroImage, 01.01.2018.

Research output: Contribution to journalArticle

@article{17f5dc33b7af4185884ffdbf1295d9d1,
title = "Multi-task prediction of infant cognitive scores from longitudinal incomplete neuroimaging data",
abstract = "Early postnatal brain undergoes a stunning period of development. Over the past few years, research on dynamic infant brain development has received increased attention, exhibiting how important the early stages of a child's life are in terms of brain development. To precisely chart the early brain developmental trajectories, longitudinal studies with data acquired over a long-enough period of infants' early life is essential. However, in practice, missing data from different time point(s) during the data gathering procedure is often inevitable. This leads to incomplete set of longitudinal data, which poses a major challenge for such studies. In this paper, prediction of multiple future cognitive scores with incomplete longitudinal imaging data is modeled into a multi-task machine learning framework. To efficiently learn this model, we account for selection of informative features (i.e., neuroimaging morphometric measurements for different time points), while preserving the structural information and the interrelation between these multiple cognitive scores. Several experiments are conducted on a carefully acquired in-house dataset, and the results affirm that we can predict the cognitive scores measured at the age of four years old, using the imaging data of earlier time points, as early as 24 months of age, with a reasonable performance (i.e., root mean square error of 0.18).",
keywords = "Bag-of-words, Brain fingerprinting, Longitudinal incomplete data, Low-rank tensor, Multi-task learning, Postnatal brain development, Sparsity",
author = "Ehsan Adeli and Yu Meng and Gang Li and Weili Lin and Dinggang Shen",
year = "2018",
month = "1",
day = "1",
doi = "10.1016/j.neuroimage.2018.04.052",
language = "English",
journal = "NeuroImage",
issn = "1053-8119",
publisher = "Academic Press Inc.",

}

TY - JOUR

T1 - Multi-task prediction of infant cognitive scores from longitudinal incomplete neuroimaging data

AU - Adeli, Ehsan

AU - Meng, Yu

AU - Li, Gang

AU - Lin, Weili

AU - Shen, Dinggang

PY - 2018/1/1

Y1 - 2018/1/1

N2 - Early postnatal brain undergoes a stunning period of development. Over the past few years, research on dynamic infant brain development has received increased attention, exhibiting how important the early stages of a child's life are in terms of brain development. To precisely chart the early brain developmental trajectories, longitudinal studies with data acquired over a long-enough period of infants' early life is essential. However, in practice, missing data from different time point(s) during the data gathering procedure is often inevitable. This leads to incomplete set of longitudinal data, which poses a major challenge for such studies. In this paper, prediction of multiple future cognitive scores with incomplete longitudinal imaging data is modeled into a multi-task machine learning framework. To efficiently learn this model, we account for selection of informative features (i.e., neuroimaging morphometric measurements for different time points), while preserving the structural information and the interrelation between these multiple cognitive scores. Several experiments are conducted on a carefully acquired in-house dataset, and the results affirm that we can predict the cognitive scores measured at the age of four years old, using the imaging data of earlier time points, as early as 24 months of age, with a reasonable performance (i.e., root mean square error of 0.18).

AB - Early postnatal brain undergoes a stunning period of development. Over the past few years, research on dynamic infant brain development has received increased attention, exhibiting how important the early stages of a child's life are in terms of brain development. To precisely chart the early brain developmental trajectories, longitudinal studies with data acquired over a long-enough period of infants' early life is essential. However, in practice, missing data from different time point(s) during the data gathering procedure is often inevitable. This leads to incomplete set of longitudinal data, which poses a major challenge for such studies. In this paper, prediction of multiple future cognitive scores with incomplete longitudinal imaging data is modeled into a multi-task machine learning framework. To efficiently learn this model, we account for selection of informative features (i.e., neuroimaging morphometric measurements for different time points), while preserving the structural information and the interrelation between these multiple cognitive scores. Several experiments are conducted on a carefully acquired in-house dataset, and the results affirm that we can predict the cognitive scores measured at the age of four years old, using the imaging data of earlier time points, as early as 24 months of age, with a reasonable performance (i.e., root mean square error of 0.18).

KW - Bag-of-words

KW - Brain fingerprinting

KW - Longitudinal incomplete data

KW - Low-rank tensor

KW - Multi-task learning

KW - Postnatal brain development

KW - Sparsity

UR - http://www.scopus.com/inward/record.url?scp=85047056734&partnerID=8YFLogxK

UR - http://www.scopus.com/inward/citedby.url?scp=85047056734&partnerID=8YFLogxK

U2 - 10.1016/j.neuroimage.2018.04.052

DO - 10.1016/j.neuroimage.2018.04.052

M3 - Article

C2 - 29709627

AN - SCOPUS:85047056734

JO - NeuroImage

JF - NeuroImage

SN - 1053-8119

ER -