A multi-task, multi-stage deep transfer learning model for early prediction of neurodevelopment in very preterm infants
Open Access
- 15 September 2020
- journal article
- research article
- Published by Springer Science and Business Media LLC in Scientific Reports
- Vol. 10 (1), 1-13
- https://doi.org/10.1038/s41598-020-71914-x
Abstract
Survivors following very premature birth (i.e., ≤ 32 weeks gestational age) remain at high risk for neurodevelopmental impairments. Recent advances in deep learning techniques have made it possible to aid the early diagnosis and prognosis of neurodevelopmental deficits. Deep learning models typically require training on large datasets, and unfortunately, large neuroimaging datasets with clinical outcome annotations are typically limited, especially in neonates. Transfer learning represents an important step to solve the fundamental problem of insufficient training data in deep learning. In this work, we developed a multi-task, multi-stage deep transfer learning framework using the fusion of brain connectome and clinical data for early joint prediction of multiple abnormal neurodevelopmental (cognitive, language and motor) outcomes at 2 years corrected age in very preterm infants. The proposed framework maximizes the value of both available annotated and non-annotated data in model training by performing both supervised and unsupervised learning. We first pre-trained a deep neural network prototype in a supervised fashion using 884 older children and adult subjects, and then re-trained this prototype using 291 neonatal subjects without supervision. Finally, we fine-tuned and validated the pre-trained model using 33 preterm infants. Our proposed model identified very preterm infants at high-risk for cognitive, language, and motor deficits at 2 years corrected age with an area under the receiver operating characteristic curve of 0.86, 0.66 and 0.84, respectively. Employing such a deep learning model, once externally validated, may facilitate risk stratification at term-equivalent age for early identification of long-term neurodevelopmental deficits and targeted early interventions to improve clinical outcomes in very preterm infants.Keywords
Funding Information
- National Institutes of Health (R21-HD094085, R01-NS094200)
- Cincinnati Children's Hospital Medical Center (Trustee grant)
This publication has 60 references indexed in Scilit:
- A Machine Learning Approach to Automated Structural Network Analysis: Application to Neonatal EncephalopathyPLOS ONE, 2013
- BrainNet Viewer: A Network Visualization Tool for Human Brain ConnectomicsPLOS ONE, 2013
- National, regional, and worldwide estimates of preterm birth rates in the year 2010 with time trends since 1990 for selected countries: a systematic analysis and implicationsThe Lancet, 2012
- Cognitive outcome at 24months is more predictive than at 18months for IQ at 8–9years in extremely low birth weight childrenEarly Human Development, 2012
- Spurious but systematic correlations in functional connectivity MRI networks arise from subject motionNeuroImage, 2012
- Identification of MCI individuals using structural and functional connectivity networksNeuroImage, 2012
- Infant Brain Atlases from Neonates to 1- and 2-Year-OldsPLOS ONE, 2011
- Intensive Care for Extreme Prematurity — Moving beyond Gestational AgeThe New England Journal of Medicine, 2008
- Clinical Data Predict Neurodevelopmental Outcome Better than Head Ultrasound in Extremely Low Birth Weight InfantsThe Journal of Pediatrics, 2007
- A component based noise correction method (CompCor) for BOLD and perfusion based fMRINeuroImage, 2007