Skip to main page content
U.S. flag

An official website of the United States government

Dot gov

The .gov means it’s official.
Federal government websites often end in .gov or .mil. Before sharing sensitive information, make sure you’re on a federal government site.

Https

The site is secure.
The https:// ensures that you are connecting to the official website and that any information you provide is encrypted and transmitted securely.

Access keys NCBI Homepage MyNCBI Homepage Main Content Main Navigation
. 2020 Sep 18:14:858.
doi: 10.3389/fnins.2020.00858. eCollection 2020.

Early Prediction of Cognitive Deficit in Very Preterm Infants Using Brain Structural Connectome With Transfer Learning Enhanced Deep Convolutional Neural Networks

Affiliations

Early Prediction of Cognitive Deficit in Very Preterm Infants Using Brain Structural Connectome With Transfer Learning Enhanced Deep Convolutional Neural Networks

Ming Chen et al. Front Neurosci. .

Abstract

Up to 40% of very preterm infants (≤32 weeks' gestational age) were identified with a cognitive deficit at 2 years of age. Yet, accurate clinical diagnosis of cognitive deficit cannot be made until early childhood around 3-5 years of age. Recently, brain structural connectome that was constructed by advanced diffusion tensor imaging (DTI) technique has been playing an important role in understanding human cognitive functions. However, available annotated neuroimaging datasets with clinical and outcome information are usually limited and expensive to enlarge in the very preterm infants' studies. These challenges hinder the development of neonatal prognostic tools for early prediction of cognitive deficit in very preterm infants. In this study, we considered the brain structural connectome as a 2D image and applied established deep convolutional neural networks to learn the spatial and topological information of the brain connectome. Furthermore, the transfer learning technique was utilized to mitigate the issue of insufficient training data. As such, we developed a transfer learning enhanced convolutional neural network (TL-CNN) model for early prediction of cognitive assessment at 2 years of age in very preterm infants using brain structural connectome. A total of 110 very preterm infants were enrolled in this work. Brain structural connectome was constructed using DTI images scanned at term-equivalent age. Bayley III cognitive assessments were conducted at 2 years of corrected age. We applied the proposed model to both cognitive deficit classification and continuous cognitive score prediction tasks. The results demonstrated that TL-CNN achieved improved performance compared to multiple peer models. Finally, we identified the brain regions most discriminative to the cognitive deficit. The results suggest that deep learning models may facilitate early prediction of later neurodevelopmental outcomes in very preterm infants at term-equivalent age.

Keywords: cognitive deficit; convolutional neural network; deep learning; structural connectome; transfer learning.

PubMed Disclaimer

Figures

FIGURE 1
FIGURE 1
Schematic diagram of the proposed transfer learning-enhanced deep CNN (TL-CNN) model to predict cognitive deficits at 2 years corrected age using brain structural connectome data obtained at term in very preterm infants. The top two blocks demonstrate a two-stage model training procedure, and the bottom block illustrates a potential clinical computer-aided diagnosis application after model training.
FIGURE 2
FIGURE 2
Receiver operating characteristic (ROC) curves of different prediction models using structural brain connectome at term-equivalent age in predicting cognitive deficits at 2 years corrected age in very preterm infants. The proposed TL-CNN model achieved the best area under the ROC curve among compared machine learning models. SVM, support vector machine; DNN, deep neural network; CNN, convolutional neural network; TL-DNN, transfer learning enhanced deep neural network; TL-CNN, transfer learning-enhanced convolutional neural network.
FIGURE 3
FIGURE 3
Top 15 discriminative brain structural connections identified by TL-CNN, a circos plot. The top three discriminative structural connections are located within frontal lobes, limbic lobes, and the subcortical structure.

Similar articles

Cited by

References

    1. Acharya S., Shukla S. (2012). Mirror neurons: Enigma of the metaphysical modular brain. J. Nat. Sci. Biol. Med. 3 118–124. 10.4103/0976-9668.101878 - DOI - PMC - PubMed
    1. Azizi S., Mousavi P., Yan P., Tahmasebi A., Kwak J. T., Xu S., et al. (2017). Transfer learning from RF to B-mode temporal enhanced ultrasound features for prostate cancer detection. Int. J. Comput. Assist. Radiol. Surg. 12 1111–1121. 10.1007/s11548-017-1573-x - DOI - PMC - PubMed
    1. Barkhof F., Haller S., Rombouts S. A. (2014). Resting-state functional MR imaging: a new window to the brain. Radiology 272 29–49. 10.1148/radiol.14132388 - DOI - PubMed
    1. Bassett D. S., Brown J. A., Deshpande V., Carlson J. M., Grafton S. T. (2011). Conserved and variable architecture of human white matter connectivity. Neuroimage 54 1262–1279. 10.1016/j.neuroimage.2010.09.006 - DOI - PubMed
    1. Bengio Y. (2012). “Deep Learning of Representations for Unsupervised and Transfer Learning,” in Paper presented at the Proceedings of ICML Workshop on Unsupervised and Transfer Learning, (Berlin: Springer; ).