Early Prediction of Cognitive Deficit in Very Preterm Infants Using Brain Structural Connectome With Transfer Learning Enhanced Deep Convolutional Neural Networks
- PMID: 33041749
- PMCID: PMC7530168
- DOI: 10.3389/fnins.2020.00858
Early Prediction of Cognitive Deficit in Very Preterm Infants Using Brain Structural Connectome With Transfer Learning Enhanced Deep Convolutional Neural Networks
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.
Copyright © 2020 Chen, Li, Wang, Yuan, Altaye, Parikh and He.
Figures



Similar articles
-
Supervised contrastive learning enhances graph convolutional networks for predicting neurodevelopmental deficits in very preterm infants using brain structural connectome.Neuroimage. 2024 May 1;291:120579. doi: 10.1016/j.neuroimage.2024.120579. Epub 2024 Mar 26. Neuroimage. 2024. PMID: 38537766 Free PMC article.
-
A self-training deep neural network for early prediction of cognitive deficits in very preterm infants using brain functional connectome data.Pediatr Radiol. 2022 Oct;52(11):2227-2240. doi: 10.1007/s00247-022-05510-8. Epub 2022 Sep 22. Pediatr Radiol. 2022. PMID: 36131030 Free PMC article.
-
ConCeptCNN: A novel multi-filter convolutional neural network for the prediction of neurodevelopmental disorders using brain connectome.Med Phys. 2022 May;49(5):3171-3184. doi: 10.1002/mp.15545. Epub 2022 Mar 14. Med Phys. 2022. PMID: 35246986 Free PMC article.
-
Advanced Brain Imaging in Preterm Infants: A Narrative Review of Microstructural and Connectomic Disruption.Children (Basel). 2022 Mar 4;9(3):356. doi: 10.3390/children9030356. Children (Basel). 2022. PMID: 35327728 Free PMC article. Review.
-
Artificial intelligence role in advancement of human brain connectome studies.Front Neuroinform. 2024 Sep 20;18:1399931. doi: 10.3389/fninf.2024.1399931. eCollection 2024. Front Neuroinform. 2024. PMID: 39371468 Free PMC article.
Cited by
-
Deep learning distinguishes connectomes from focal epilepsy patients and controls: feasibility and clinical implications.Brain Commun. 2023 Oct 31;5(6):fcad294. doi: 10.1093/braincomms/fcad294. eCollection 2023. Brain Commun. 2023. PMID: 38025275 Free PMC article.
-
Supervised contrastive learning enhances graph convolutional networks for predicting neurodevelopmental deficits in very preterm infants using brain structural connectome.Neuroimage. 2024 May 1;291:120579. doi: 10.1016/j.neuroimage.2024.120579. Epub 2024 Mar 26. Neuroimage. 2024. PMID: 38537766 Free PMC article.
-
Global trends in neonatal MRI brain neuroimaging research over the last decade: a bibliometric analysis.Quant Imaging Med Surg. 2024 Feb 1;14(2):1526-1540. doi: 10.21037/qims-23-880. Epub 2024 Jan 2. Quant Imaging Med Surg. 2024. PMID: 38415119 Free PMC article.
-
Application of machine learning in early childhood development research: a scoping review.BMJ Open. 2025 Aug 19;15(8):e100358. doi: 10.1136/bmjopen-2025-100358. BMJ Open. 2025. PMID: 40829824 Free PMC article.
-
The Shape of the Brain's Connections Is Predictive of Cognitive Performance: An Explainable Machine Learning Study.Hum Brain Mapp. 2025 Apr 1;46(5):e70166. doi: 10.1002/hbm.70166. Hum Brain Mapp. 2025. PMID: 40143640 Free PMC article. Review.
References
-
- 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; ).
Grants and funding
LinkOut - more resources
Full Text Sources
Research Materials