Can we predict subject-specific dynamic cortical thickness maps during infancy from birth?

Yu Meng, Gang Li, Islem Rekik, Han Zhang, Yaozong Gao, Weili Lin, Dinggang Shen

Research output: Contribution to journalArticle

  • 2 Citations

Abstract

Understanding the early dynamic development of the human cerebral cortex remains a challenging problem. Cortical thickness, as one of the most important morphological attributes of the cerebral cortex, is a sensitive indicator for both normal neurodevelopment and neuropsychiatric disorders, but its early postnatal development remains largely unexplored. In this study, we investigate a key question in neurodevelopmental science: can we predict the future dynamic development of cortical thickness map in an individual infant based on its available MRI data at birth? If this is possible, we might be able to better model and understand the early brain development and also early detect abnormal brain development during infancy. To this end, we develop a novel learning-based method, called Dynamically-Assembled Regression Forest (DARF), to predict the development of the cortical thickness map during the first postnatal year, based on neonatal MRI features. We applied our method to 15 healthy infants and predicted their cortical thickness maps at 3, 6, 9, and 12 months of age, with respectively mean absolute errors of 0.209 mm, 0.332 mm, 0.340 mm, and 0.321 mm. Moreover, we found that the prediction precision is region-specific, with high precision in the unimodal cortex and relatively low precision in the high-order association cortex, which may be associated with their differential developmental patterns. Additional experiments also suggest that using more early time points for prediction can further significantly improve the prediction accuracy. Hum Brain Mapp 38:2865–2874, 2017.

LanguageEnglish (US)
Pages2865-2874
Number of pages10
JournalHuman Brain Mapping
Volume38
Issue number6
DOIs
StatePublished - Jun 1 2017

Fingerprint

Parturition
Cerebral Cortex
Brain
Human Development
Learning
Forests

Keywords

  • cortical surface
  • cortical thickness prediction
  • infant brain
  • longitudinal development

ASJC Scopus subject areas

  • Anatomy
  • Radiological and Ultrasound Technology
  • Radiology Nuclear Medicine and imaging
  • Neurology
  • Clinical Neurology

Cite this

Can we predict subject-specific dynamic cortical thickness maps during infancy from birth? / Meng, Yu; Li, Gang; Rekik, Islem; Zhang, Han; Gao, Yaozong; Lin, Weili; Shen, Dinggang.

In: Human Brain Mapping, Vol. 38, No. 6, 01.06.2017, p. 2865-2874.

Research output: Contribution to journalArticle

Meng, Yu ; Li, Gang ; Rekik, Islem ; Zhang, Han ; Gao, Yaozong ; Lin, Weili ; Shen, Dinggang. / Can we predict subject-specific dynamic cortical thickness maps during infancy from birth?. In: Human Brain Mapping. 2017 ; Vol. 38, No. 6. pp. 2865-2874.
@article{fcb37102b64b4b03b56b78d32e069e4a,
title = "Can we predict subject-specific dynamic cortical thickness maps during infancy from birth?",
abstract = "Understanding the early dynamic development of the human cerebral cortex remains a challenging problem. Cortical thickness, as one of the most important morphological attributes of the cerebral cortex, is a sensitive indicator for both normal neurodevelopment and neuropsychiatric disorders, but its early postnatal development remains largely unexplored. In this study, we investigate a key question in neurodevelopmental science: can we predict the future dynamic development of cortical thickness map in an individual infant based on its available MRI data at birth? If this is possible, we might be able to better model and understand the early brain development and also early detect abnormal brain development during infancy. To this end, we develop a novel learning-based method, called Dynamically-Assembled Regression Forest (DARF), to predict the development of the cortical thickness map during the first postnatal year, based on neonatal MRI features. We applied our method to 15 healthy infants and predicted their cortical thickness maps at 3, 6, 9, and 12 months of age, with respectively mean absolute errors of 0.209 mm, 0.332 mm, 0.340 mm, and 0.321 mm. Moreover, we found that the prediction precision is region-specific, with high precision in the unimodal cortex and relatively low precision in the high-order association cortex, which may be associated with their differential developmental patterns. Additional experiments also suggest that using more early time points for prediction can further significantly improve the prediction accuracy. Hum Brain Mapp 38:2865–2874, 2017.",
keywords = "cortical surface, cortical thickness prediction, infant brain, longitudinal development",
author = "Yu Meng and Gang Li and Islem Rekik and Han Zhang and Yaozong Gao and Weili Lin and Dinggang Shen",
year = "2017",
month = "6",
day = "1",
doi = "10.1002/hbm.23555",
language = "English (US)",
volume = "38",
pages = "2865--2874",
journal = "Human Brain Mapping",
issn = "1065-9471",
publisher = "Wiley-Liss Inc.",
number = "6",

}

TY - JOUR

T1 - Can we predict subject-specific dynamic cortical thickness maps during infancy from birth?

AU - Meng, Yu

AU - Li, Gang

AU - Rekik, Islem

AU - Zhang, Han

AU - Gao, Yaozong

AU - Lin, Weili

AU - Shen, Dinggang

PY - 2017/6/1

Y1 - 2017/6/1

N2 - Understanding the early dynamic development of the human cerebral cortex remains a challenging problem. Cortical thickness, as one of the most important morphological attributes of the cerebral cortex, is a sensitive indicator for both normal neurodevelopment and neuropsychiatric disorders, but its early postnatal development remains largely unexplored. In this study, we investigate a key question in neurodevelopmental science: can we predict the future dynamic development of cortical thickness map in an individual infant based on its available MRI data at birth? If this is possible, we might be able to better model and understand the early brain development and also early detect abnormal brain development during infancy. To this end, we develop a novel learning-based method, called Dynamically-Assembled Regression Forest (DARF), to predict the development of the cortical thickness map during the first postnatal year, based on neonatal MRI features. We applied our method to 15 healthy infants and predicted their cortical thickness maps at 3, 6, 9, and 12 months of age, with respectively mean absolute errors of 0.209 mm, 0.332 mm, 0.340 mm, and 0.321 mm. Moreover, we found that the prediction precision is region-specific, with high precision in the unimodal cortex and relatively low precision in the high-order association cortex, which may be associated with their differential developmental patterns. Additional experiments also suggest that using more early time points for prediction can further significantly improve the prediction accuracy. Hum Brain Mapp 38:2865–2874, 2017.

AB - Understanding the early dynamic development of the human cerebral cortex remains a challenging problem. Cortical thickness, as one of the most important morphological attributes of the cerebral cortex, is a sensitive indicator for both normal neurodevelopment and neuropsychiatric disorders, but its early postnatal development remains largely unexplored. In this study, we investigate a key question in neurodevelopmental science: can we predict the future dynamic development of cortical thickness map in an individual infant based on its available MRI data at birth? If this is possible, we might be able to better model and understand the early brain development and also early detect abnormal brain development during infancy. To this end, we develop a novel learning-based method, called Dynamically-Assembled Regression Forest (DARF), to predict the development of the cortical thickness map during the first postnatal year, based on neonatal MRI features. We applied our method to 15 healthy infants and predicted their cortical thickness maps at 3, 6, 9, and 12 months of age, with respectively mean absolute errors of 0.209 mm, 0.332 mm, 0.340 mm, and 0.321 mm. Moreover, we found that the prediction precision is region-specific, with high precision in the unimodal cortex and relatively low precision in the high-order association cortex, which may be associated with their differential developmental patterns. Additional experiments also suggest that using more early time points for prediction can further significantly improve the prediction accuracy. Hum Brain Mapp 38:2865–2874, 2017.

KW - cortical surface

KW - cortical thickness prediction

KW - infant brain

KW - longitudinal development

UR - http://www.scopus.com/inward/record.url?scp=85015314583&partnerID=8YFLogxK

UR - http://www.scopus.com/inward/citedby.url?scp=85015314583&partnerID=8YFLogxK

U2 - 10.1002/hbm.23555

DO - 10.1002/hbm.23555

M3 - Article

VL - 38

SP - 2865

EP - 2874

JO - Human Brain Mapping

T2 - Human Brain Mapping

JF - Human Brain Mapping

SN - 1065-9471

IS - 6

ER -