Infant Brain Development Prediction with Latent Partial Multi-View Representation Learning

Changqing Zhang, Ehsan Adeli, Zhengwang Wu, Gang Li, Weili Lin, Dinggang Shen

Research output: Contribution to journalArticle

1 Citation (Scopus)

Abstract

The early postnatal period witnesses rapid and dynamic brain development. However, the relationship between brain anatomical structure and cognitive ability is still unknown. Currently, there is no explicit model to characterize this relationship in the literature. In this paper, we explore this relationship by investigating the mapping between morphological features of the cerebral cortex and cognitive scores. To this end, we introduce a multi-view multi-task learning approach to intuitively explore complementary information from different time-points and handle the missing data issue in longitudinal studies simultaneously. Accordingly, we establish a novel model, Latent Partial Multi-View Representation Learning. Our approach regards data from different time-points as different views and constructs a latent representation to capture the complementary information from incomplete time-points. The latent representation explores the complementarity across different time-points and improves the accuracy of prediction. The minimization problem is solved by the Alternating Direction Method of Multipliers (ADMM). Experimental results on both synthetic and real data validate the effectiveness of our proposed algorithm.

Original languageEnglish
JournalIEEE Transactions on Medical Imaging
DOIs
Publication statusAccepted/In press - 2018 Jan 1

Fingerprint

Child Development
Brain
Learning
Aptitude
Cerebral Cortex
Longitudinal Studies

Keywords

  • Brain modeling
  • Cognitive ability
  • Computational modeling
  • Data models
  • Infant brain development
  • Longitudinal analysis
  • Magnetic resonance imaging
  • Multi-view learning
  • Pediatrics
  • Predictive models
  • Task analysis

ASJC Scopus subject areas

  • Software
  • Radiological and Ultrasound Technology
  • Computer Science Applications
  • Electrical and Electronic Engineering

Cite this

Infant Brain Development Prediction with Latent Partial Multi-View Representation Learning. / Zhang, Changqing; Adeli, Ehsan; Wu, Zhengwang; Li, Gang; Lin, Weili; Shen, Dinggang.

In: IEEE Transactions on Medical Imaging, 01.01.2018.

Research output: Contribution to journalArticle

@article{a64a934a57d048d3bcfe50acae97474c,
title = "Infant Brain Development Prediction with Latent Partial Multi-View Representation Learning",
abstract = "The early postnatal period witnesses rapid and dynamic brain development. However, the relationship between brain anatomical structure and cognitive ability is still unknown. Currently, there is no explicit model to characterize this relationship in the literature. In this paper, we explore this relationship by investigating the mapping between morphological features of the cerebral cortex and cognitive scores. To this end, we introduce a multi-view multi-task learning approach to intuitively explore complementary information from different time-points and handle the missing data issue in longitudinal studies simultaneously. Accordingly, we establish a novel model, Latent Partial Multi-View Representation Learning. Our approach regards data from different time-points as different views and constructs a latent representation to capture the complementary information from incomplete time-points. The latent representation explores the complementarity across different time-points and improves the accuracy of prediction. The minimization problem is solved by the Alternating Direction Method of Multipliers (ADMM). Experimental results on both synthetic and real data validate the effectiveness of our proposed algorithm.",
keywords = "Brain modeling, Cognitive ability, Computational modeling, Data models, Infant brain development, Longitudinal analysis, Magnetic resonance imaging, Multi-view learning, Pediatrics, Predictive models, Task analysis",
author = "Changqing Zhang and Ehsan Adeli and Zhengwang Wu and Gang Li and Weili Lin and Dinggang Shen",
year = "2018",
month = "1",
day = "1",
doi = "10.1109/TMI.2018.2874964",
language = "English",
journal = "IEEE Transactions on Medical Imaging",
issn = "0278-0062",
publisher = "Institute of Electrical and Electronics Engineers Inc.",

}

TY - JOUR

T1 - Infant Brain Development Prediction with Latent Partial Multi-View Representation Learning

AU - Zhang, Changqing

AU - Adeli, Ehsan

AU - Wu, Zhengwang

AU - Li, Gang

AU - Lin, Weili

AU - Shen, Dinggang

PY - 2018/1/1

Y1 - 2018/1/1

N2 - The early postnatal period witnesses rapid and dynamic brain development. However, the relationship between brain anatomical structure and cognitive ability is still unknown. Currently, there is no explicit model to characterize this relationship in the literature. In this paper, we explore this relationship by investigating the mapping between morphological features of the cerebral cortex and cognitive scores. To this end, we introduce a multi-view multi-task learning approach to intuitively explore complementary information from different time-points and handle the missing data issue in longitudinal studies simultaneously. Accordingly, we establish a novel model, Latent Partial Multi-View Representation Learning. Our approach regards data from different time-points as different views and constructs a latent representation to capture the complementary information from incomplete time-points. The latent representation explores the complementarity across different time-points and improves the accuracy of prediction. The minimization problem is solved by the Alternating Direction Method of Multipliers (ADMM). Experimental results on both synthetic and real data validate the effectiveness of our proposed algorithm.

AB - The early postnatal period witnesses rapid and dynamic brain development. However, the relationship between brain anatomical structure and cognitive ability is still unknown. Currently, there is no explicit model to characterize this relationship in the literature. In this paper, we explore this relationship by investigating the mapping between morphological features of the cerebral cortex and cognitive scores. To this end, we introduce a multi-view multi-task learning approach to intuitively explore complementary information from different time-points and handle the missing data issue in longitudinal studies simultaneously. Accordingly, we establish a novel model, Latent Partial Multi-View Representation Learning. Our approach regards data from different time-points as different views and constructs a latent representation to capture the complementary information from incomplete time-points. The latent representation explores the complementarity across different time-points and improves the accuracy of prediction. The minimization problem is solved by the Alternating Direction Method of Multipliers (ADMM). Experimental results on both synthetic and real data validate the effectiveness of our proposed algorithm.

KW - Brain modeling

KW - Cognitive ability

KW - Computational modeling

KW - Data models

KW - Infant brain development

KW - Longitudinal analysis

KW - Magnetic resonance imaging

KW - Multi-view learning

KW - Pediatrics

KW - Predictive models

KW - Task analysis

UR - http://www.scopus.com/inward/record.url?scp=85054615632&partnerID=8YFLogxK

UR - http://www.scopus.com/inward/citedby.url?scp=85054615632&partnerID=8YFLogxK

U2 - 10.1109/TMI.2018.2874964

DO - 10.1109/TMI.2018.2874964

M3 - Article

C2 - 30307859

AN - SCOPUS:85054615632

JO - IEEE Transactions on Medical Imaging

JF - IEEE Transactions on Medical Imaging

SN - 0278-0062

ER -