Lili He1,2,3, Hailong Li1,3, Jinghua Wang4, Ming Chen1,5, Jonathan R. Dillman4,6, and Nehal Parikh1,2
1The Perinatal Institute and Section of Neonatology, Perinatal and Pulmonary Biology, Cincinnati Children's Hospital Medical Center, Cincinnati, OH, United States, 2Department of Pediatrics, University of Cincinnati College of Medicine, Cincinnati, OH, United States, 3Imaging Research Center, Cincinnati Children's Hospital Medical Center, Cincinnati, OH, United States, 4Department of Radiology, University of Cincinnati College of Medicine, Cincinnati, OH, United States, 5Department of Electronic Engineering and Computing Science, University of Cincinnati, Cincinnati, OH, United States, 6Department of Radiology, Cincinnati Children's Hospital Medical Center, Cincinnati, OH, United States
Synopsis
We proposed a deep transfer learning model using
the fusion of clinical and brain functional connectome data obtained at term for
early neurodevelopmental deficits prediction at two years corrected age in very
preterm infants. The proposed model was first trained in an unsupervised
fashion using
884 subjects from publicly available ABIDE repository, then fine-tuned and cross-validated
on 33 very preterm infants. Our model achieved an AUC of
0.77, 0.63 and 0.74 on the risk stratification of cognitive, language and motor
deficits, respectively. Our findings demonstrated the feasibility of using deep
transfer learning on connectome data for abnormal neurodevelopment prediction.
INTRODUCTION
Survivors following very premature
birth (i.e.,
≤32 weeks gestational age) 1 remain at high risk for neurodevelopmental impairments,
thereby increasing their risk for poor educational, health, and social
outcomes. 2 Unfortunately,
it may take 2-5 years from birth to accurately diagnose disabilities in these
high-risk infants. Early, accurate identification, soon after birth,
could pave the way for domain-specific, intensive early neuroprotective
therapies during a critical window for optimal neuroplasticity. There is a growing interest in developing
artificial intelligence neural network approaches to predict neurodevelopmental
and neurological deficits using connectome data. 3 Such models typically require training on large datasets, 4 but unfortunately large neuroimaging datasets are either
unavailable or expensive to obtain. Transfer learning represents an important
key to solve the fundamental problem of insufficient training data in deep
learning. 5 We developed a multi-task transfer learning enhanced deep
neural network (TL-DNN) model to jointly predict multiple neurodevelopmental
deficits in preterm infants, including cognitive, language, and motor skills at
two years corrected age.METHODS
This study
includes 884 subjects (age range = 7-64 years,
median age = 14.7 years) from
the publicly available autism brain
imaging data exchange (ABIDE) repository 6 and 33 very preterm infants (gestational age at
birth 28.3 (2.4) weeks; postmenstrual
age at scan 40.2 (0.5) weeks). The
Nationwide Children's Hospital Institutional Review Board approved this study,
and written parental informed consent was obtained for every subject. All
preterm infants received standardized Bayley Scales of Infant and Toddler
Development III test at 2 years corrected age.
The Bayley-III cognitive, language, and motor scores are on a scale of 40 to
160, with a mean of 100 and standard deviation (SD) of 15. We grouped very
preterm infants using a cutoff of 85 into those at high vs. low risk for
moderate/severe neurodevelopmental deficits.
We employed our neonatal-optimized pipeline 7 for neonatal resting state
fMRI preprocessing using FMRIB Software Library (FSL, Oxford University,
UK), Statistical Parametric Mapping software (SPM, University College London,
UK), and Artifact Detection Tools (ART, MIT, Cambridge, US). Ninety ROIs were
defined based on a neonatal automated anatomical labeling (AAL) atlas. 8 The functional connectivity
was defined as the temporal correlation of BOLD signals between spatially apart
ROIs. 9 This was calculated using
functional connectivity toolbox (CONN). 10
An overview of the multi-task deep transfer learning framework is shown
in Figure 1. More specifically, the proposed framework includes
2 modules: 1) pre-training (Figure 1, top red panel). We first pre-train
a deep neural network (DNN) prototype in an unsupervised fashion using stacked
sparse autoencoder (SSAE) to learn the general representation of brain networks
from 884 older children and adults subjects. This DNN
prototype are comprised of fully-connected layers and batch
normalization layers. Batch normalization layer is able to mitigate the internal
covariate shift problem so as to accelerate the training process; 2) fine-tuning
(Figure 1, bottom green panel). We then adapt the pre-learned brain connectome
knowledge from module 1 to better represent neonatal connectome by fine-tuning
the whole TL-DNN model using 33 very preterm subjects. The
detailed architecture of TL-DNN is illustrated in Figure 2. It contains
two separate input channels for connectome and clinical data. Both channels are
later fused into a single channel as data integration. There are three parallel
output channels for cognitive, language and motor task, respectively. For neurodevelopmental
risk classification, we used softmax function in the output channels and
cross-entropy as loss function. For neurodevelopmental score regression, we
applied linear function in the output channels and mean-squared error as loss
function. After the fine-tuning, we will have an
optimized TL-DNN for the joint
neurodevelopmental outcome prediction. We validated the proposed TL-DNN model using
5-fold cross-validation with accuracy, sensitivity, specificity, and
area under the receiver operating characteristic curve (AUC) for risk
stratification, and Pearson’s correlation coefficient and mean absolute error for prediction of cognitive scores. RESULTS
We performed both risk
stratification (i.e., classification; neurodevelopmental score cutoff=85), and
score prediction (i.e., regression). Our transfer learning enhanced TL-DNN model achieved an AUC of 0.77,
0.63 and 0.74 on the risk stratification of cognitive, language and motor
deficits. As compared with a DNN model without transfer learning, our model significantly
improved risk stratification accuracy by 8.4% (p<0.001), 2.4% (p=0.034), and
7.5% (p<0.001) and improved the AUC by 0.05 (p<0.001), 0.04 (p<0.001)
and 0.14 (p<0.001), respectively (Table 1). In addition, Predicted cognitive
and motor neurodevelopmental scores were significantly correlated with actual
scores, measured with a Pearson’s correlation coefficient of 0.31 (p=0.04) and
0.36 (p=0.04), respectively (Table 2).DISCUSSIONS and CONCLUSIONS
Early and reliable identification of high-risk infants for later neurodevelopmental impairments
would facilitate targeted early interventions during periods of maximal
neuroplasticity to improve clinical outcomes. To mitigate concerns
regarding insufficient data for training a deep learning model, we employed
transfer learning in this work. We present a
transfer learning enhanced deep learning model using the fusion of brain
connectome and clinical data for early joint prediction of the neurodevelopmental
outcomes (cognitive, language and motor) at 2 years of age in very preterm
infants. A
larger study is needed to validate our approach.Acknowledgements
This
study was supported by the National Institutes of Health grants R21-HD094085,
R01-NS094200, and R01-NS096037 and a Trustee grant from Cincinnati Children’s
Hospital Medical Center. The content is solely
the responsibility of the authors and does not necessarily represent the
official views of the National Institutes of Health. We thank the ABIDE project investigators for making their data publicly available.References
1. Hamilton BE, Martin JA, Osterman MJ. Births: Preliminary
Data for 2015. Natl Vital Stat Rep. 2016;65(3):1-15.
2. Jarjour IT. Neurodevelopmental Outcome
After Extreme Prematurity: A Review of the Literature. Pediatric Neurology. 2015;52(2):143-152.
3. Barkhof F, Haller S, Rombouts SA.
Resting-state functional MR imaging: a new window to the brain. Radiology. 2014;272(1):29-49.
4. LeCun Y, Bengio Y, Hinton G. Deep
learning. Nature. 2015;521(7553):436-444.
5. Shin HC, Roth HR, Gao M, et al. Deep
Convolutional Neural Networks for Computer-Aided Detection: CNN Architectures,
Dataset Characteristics and Transfer Learning. IEEE Trans Med Imaging. 2016;35(5):1285-1298.
6. Di Martino A, Yan C-G, Li Q, et al. The
autism brain imaging data exchange: towards a large-scale evaluation of the
intrinsic brain architecture in autism. Molecular
psychiatry. 2014;19(6):659.
7. He L, Parikh NA. Aberrant Executive and
Frontoparietal Functional Connectivity in Very Preterm Infants With Diffuse
White Matter Abnormalities. Pediatr
Neurol. 2015;53(4):330-337.
8. Shi F, Yap PT, Wu G, et al. Infant
brain atlases from neonates to 1- and 2-year-olds. PLoS One. 2011;6(4):e18746.
9. Betzel RF, Bassett DS. Multi-scale
brain networks. Neuroimage. 2017;160:73-83.
10. Whitfield-Gabrieli S, Nieto-Castanon A.
Conn: a functional connectivity toolbox for correlated and anticorrelated brain
networks. Brain Connect. 2012;2(3):125-141.