Meeting Banner
Abstract #1695

Early prediction of cognitive deficits in very preterm infants using graph convolutional networks with brain structural connectome

Hailong Li1, Ming Chen1,2, Jinghua Wang3, Nehal A. Parikh4,5, and Lili He1,5
1Imaging Research Center, Department of Radiology, Cincinnati Children's Hospital Medical Center, Cincinnati, OH, United States, 2Department of Electrical Engineering and Computer Science, University of Cincinnati, Cincinnati, OH, United States, 3Deep MRI Imaging Inc., Lewes, DE, United States, 4The Perinatal Institute and Section of Neonatology, Perinatal and Pulmonary Biology, Cincinnati Children's Hospital Medical Center, Cincinnati, OH, United States, 5Department of Pediatrics, University of Cincinnati College of Medicine, Cincinnati, OH, United States

Up to 40% of very preterm infants (≤32 weeks’ gestational age) are identified with cognitive deficits at 2 years of age. Reproducible approaches that serve as neonatal prognostic tools are urgently needed for early treatment decision. We developed a graph convolutional network model to learn the latent topological features of brain structural connectome obtained at term-equivalent age for predicting cognitive deficits at 2 years corrected age in very preterm infants. The proposed model was able to identify infants at high-risk of cognitive deficits with a balanced accuracy of 78.5% and an area under the receiver operating characteristic curve of 0.78.

This abstract and the presentation materials are available to members only; a login is required.

Join Here

Abstract