Cargando…
Deep Multimodal Learning From MRI and Clinical Data for Early Prediction of Neurodevelopmental Deficits in Very Preterm Infants
The prevalence of disabled survivors of prematurity has increased dramatically in the past 3 decades. These survivors, especially, very preterm infants (VPIs), born ≤ 32 weeks gestational age, are at high risk for neurodevelopmental impairments. Early and clinically effective personalized prediction...
Autores principales: | , , , , , , |
---|---|
Formato: | Online Artículo Texto |
Lenguaje: | English |
Publicado: |
Frontiers Media S.A.
2021
|
Materias: | |
Acceso en línea: | https://www.ncbi.nlm.nih.gov/pmc/articles/PMC8525883/ https://www.ncbi.nlm.nih.gov/pubmed/34675773 http://dx.doi.org/10.3389/fnins.2021.753033 |
_version_ | 1784585773376339968 |
---|---|
author | He, Lili Li, Hailong Chen, Ming Wang, Jinghua Altaye, Mekibib Dillman, Jonathan R. Parikh, Nehal A. |
author_facet | He, Lili Li, Hailong Chen, Ming Wang, Jinghua Altaye, Mekibib Dillman, Jonathan R. Parikh, Nehal A. |
author_sort | He, Lili |
collection | PubMed |
description | The prevalence of disabled survivors of prematurity has increased dramatically in the past 3 decades. These survivors, especially, very preterm infants (VPIs), born ≤ 32 weeks gestational age, are at high risk for neurodevelopmental impairments. Early and clinically effective personalized prediction of outcomes, which forms the basis for early treatment decisions, is urgently needed during the peak neuroplasticity window—the first couple of years after birth—for at-risk infants, when intervention is likely to be most effective. Advances in MRI enable the noninvasive visualization of infants' brains through acquired multimodal images, which are more informative than unimodal MRI data by providing complementary/supplementary depicting of brain tissue characteristics and pathology. Thus, analyzing quantitative multimodal MRI features affords unique opportunities to study early postnatal brain development and neurodevelopmental outcome prediction in VPIs. In this study, we investigated the predictive power of multimodal MRI data, including T2-weighted anatomical MRI, diffusion tensor imaging, resting-state functional MRI, and clinical data for the prediction of neurodevelopmental deficits. We hypothesize that integrating multimodal MRI and clinical data improves the prediction over using each individual data modality. Employing the aforementioned multimodal data, we proposed novel end-to-end deep multimodal models to predict neurodevelopmental (i.e., cognitive, language, and motor) deficits independently at 2 years corrected age. We found that the proposed models can predict cognitive, language, and motor deficits at 2 years corrected age with an accuracy of 88.4, 87.2, and 86.7%, respectively, significantly better than using individual data modalities. This current study can be considered as proof-of-concept. A larger study with external validation is important to validate our approach to further assess its clinical utility and overall generalizability. |
format | Online Article Text |
id | pubmed-8525883 |
institution | National Center for Biotechnology Information |
language | English |
publishDate | 2021 |
publisher | Frontiers Media S.A. |
record_format | MEDLINE/PubMed |
spelling | pubmed-85258832021-10-20 Deep Multimodal Learning From MRI and Clinical Data for Early Prediction of Neurodevelopmental Deficits in Very Preterm Infants He, Lili Li, Hailong Chen, Ming Wang, Jinghua Altaye, Mekibib Dillman, Jonathan R. Parikh, Nehal A. Front Neurosci Neuroscience The prevalence of disabled survivors of prematurity has increased dramatically in the past 3 decades. These survivors, especially, very preterm infants (VPIs), born ≤ 32 weeks gestational age, are at high risk for neurodevelopmental impairments. Early and clinically effective personalized prediction of outcomes, which forms the basis for early treatment decisions, is urgently needed during the peak neuroplasticity window—the first couple of years after birth—for at-risk infants, when intervention is likely to be most effective. Advances in MRI enable the noninvasive visualization of infants' brains through acquired multimodal images, which are more informative than unimodal MRI data by providing complementary/supplementary depicting of brain tissue characteristics and pathology. Thus, analyzing quantitative multimodal MRI features affords unique opportunities to study early postnatal brain development and neurodevelopmental outcome prediction in VPIs. In this study, we investigated the predictive power of multimodal MRI data, including T2-weighted anatomical MRI, diffusion tensor imaging, resting-state functional MRI, and clinical data for the prediction of neurodevelopmental deficits. We hypothesize that integrating multimodal MRI and clinical data improves the prediction over using each individual data modality. Employing the aforementioned multimodal data, we proposed novel end-to-end deep multimodal models to predict neurodevelopmental (i.e., cognitive, language, and motor) deficits independently at 2 years corrected age. We found that the proposed models can predict cognitive, language, and motor deficits at 2 years corrected age with an accuracy of 88.4, 87.2, and 86.7%, respectively, significantly better than using individual data modalities. This current study can be considered as proof-of-concept. A larger study with external validation is important to validate our approach to further assess its clinical utility and overall generalizability. Frontiers Media S.A. 2021-10-05 /pmc/articles/PMC8525883/ /pubmed/34675773 http://dx.doi.org/10.3389/fnins.2021.753033 Text en Copyright © 2021 He, Li, Chen, Wang, Altaye, Dillman and Parikh. https://creativecommons.org/licenses/by/4.0/This is an open-access article distributed under the terms of the Creative Commons Attribution License (CC BY). The use, distribution or reproduction in other forums is permitted, provided the original author(s) and the copyright owner(s) are credited and that the original publication in this journal is cited, in accordance with accepted academic practice. No use, distribution or reproduction is permitted which does not comply with these terms. |
spellingShingle | Neuroscience He, Lili Li, Hailong Chen, Ming Wang, Jinghua Altaye, Mekibib Dillman, Jonathan R. Parikh, Nehal A. Deep Multimodal Learning From MRI and Clinical Data for Early Prediction of Neurodevelopmental Deficits in Very Preterm Infants |
title | Deep Multimodal Learning From MRI and Clinical Data for Early Prediction of Neurodevelopmental Deficits in Very Preterm Infants |
title_full | Deep Multimodal Learning From MRI and Clinical Data for Early Prediction of Neurodevelopmental Deficits in Very Preterm Infants |
title_fullStr | Deep Multimodal Learning From MRI and Clinical Data for Early Prediction of Neurodevelopmental Deficits in Very Preterm Infants |
title_full_unstemmed | Deep Multimodal Learning From MRI and Clinical Data for Early Prediction of Neurodevelopmental Deficits in Very Preterm Infants |
title_short | Deep Multimodal Learning From MRI and Clinical Data for Early Prediction of Neurodevelopmental Deficits in Very Preterm Infants |
title_sort | deep multimodal learning from mri and clinical data for early prediction of neurodevelopmental deficits in very preterm infants |
topic | Neuroscience |
url | https://www.ncbi.nlm.nih.gov/pmc/articles/PMC8525883/ https://www.ncbi.nlm.nih.gov/pubmed/34675773 http://dx.doi.org/10.3389/fnins.2021.753033 |
work_keys_str_mv | AT helili deepmultimodallearningfrommriandclinicaldataforearlypredictionofneurodevelopmentaldeficitsinverypreterminfants AT lihailong deepmultimodallearningfrommriandclinicaldataforearlypredictionofneurodevelopmentaldeficitsinverypreterminfants AT chenming deepmultimodallearningfrommriandclinicaldataforearlypredictionofneurodevelopmentaldeficitsinverypreterminfants AT wangjinghua deepmultimodallearningfrommriandclinicaldataforearlypredictionofneurodevelopmentaldeficitsinverypreterminfants AT altayemekibib deepmultimodallearningfrommriandclinicaldataforearlypredictionofneurodevelopmentaldeficitsinverypreterminfants AT dillmanjonathanr deepmultimodallearningfrommriandclinicaldataforearlypredictionofneurodevelopmentaldeficitsinverypreterminfants AT parikhnehala deepmultimodallearningfrommriandclinicaldataforearlypredictionofneurodevelopmentaldeficitsinverypreterminfants |