Feed-forward neural networks using cerebral MR spectroscopy and DTI might predict neurodevelopmental outcome in preterm neonates

Abstract

Objectives We aimed to evaluate the ability of feed-forward neural networks (fNNs) to predict the neurodevelopmental outcome (NDO) of very preterm neonates (VPIs) at 12 months corrected age by using biomarkers of cerebral MR proton spectroscopy (1H-MRS) and diffusion tensor imaging (DTI) at term-equivalent age (TEA). Methods In this prospective study, 300 VPIs born before 32 gestational weeks received an MRI scan at TEA between September 2013 and December 2017. Due to missing or poor-quality spectroscopy data and missing neurodevelopmental tests, 173 VPIs were excluded. Data sets consisting of 103 and 115 VPIs were considered for prediction of motor and cognitive developmental delay, respectively. Five metabolite ratios and two DTI characteristics in six different areas of the brain were evaluated. A feature selection algorithm was developed for receiving a subset of characteristics prevalent for the VPIs with a developmental delay. Finally, the predictors were constructed employing multiple fNNs and fourfold cross-validation. Results By employing the constructed fNN predictors, we were able to predict cognitive delays of VPIs with 85.7% sensitivity, 100% specificity, 100% positive predictive value (PPV) and 99.1% negative predictive value (NPV). For the prediction of motor delay, we achieved a sensitivity of 76.9%, a specificity of 98.9%, a PPV of 90.9% and an NPV of 96.7%. Conclusion FNNs might be able to predict motor and cognitive development of VPIs at 12 months corrected age when employing biomarkers of cerebral 1H-MRS and DTI quantified at TEA. Key Points • A feed-forward neuronal network is a promising tool for outcome prediction in premature infants. • Cerebral proton magnetic resonance spectroscopy and diffusion tensor imaging can be used for the construction of early prognostic biomarkers. • Premature infants that would most benefit from early intervention services can be spotted at the time of optimal neuroplasticity.

Radiomics analysis of MR neonatal brain: will it be the Rosetta stone for predicting the poor psychomotor outcome in preterm newborns?

“…Recently, an artificial neural network, a segment of artificial intelligence, with one hidden layer, called feedforward neural network (fNN), w as used to predict t he neurodevelopmental outcome of very preterm neonates at 12 months corrected age by using biomarkers of cerebral MR proton spectroscopy (1H-MRS) and DTI at TEA. According to the authors, fNNs might be able to predict motor and cognitive development of preterm infants up to 12 months corrected age [6].…”

A Diffusion Tensor Imaging Analysis of Frontal Lobe White Matter Microstructure in Trigonocephaly Patients

“…2 Translating these numbers to our cohort would mean a subset, of 9 to 14 patients of this cohort, would be affected. Although a previous study in preterm neonates used DTI as a predictive tool to assess neurocognitive functioning later in life, 32 our study may have missed the subtle effect of only a subgroup of neurocognitively affected patients with trigonocephaly. However, if we assess the raw data, we cannot distinguish an outlying subgroup of patients with trigonocephaly.…”

Lactylation may be a Novel Posttranslational Modification in Inflammation in Neonatal Hypoxic-Ischemic Encephalopathy

“…Deep gray matter injury, including damage to the thalamus, hippocampus, putamen, and basal ganglia, as well as cortical loss can be revealed by magnetic resonance imaging (MRI) and proton magnetic resonance spectroscopy (1H-MRS) ( Fatemi et al, 2009 ; Higgins et al, 2011 ). After neonatal and pediatric brain injury, acute changes in energy metabolism and long-term metabolic dysregulation leave the brain susceptible to damage and unable to maintain the numerous processes required for normal development ( Goergen et al, 2014 ; Kendall et al, 2014 ; Janjic et al, 2020 ). Any injury compounded by the rapidly developing brain’s high metabolic demands can jeopardize normal developmental processes and result in neurodevelopmental consequences ranging from mild to severe learning impairments ( Shanmugalingam et al, 2006 ; Goergen et al, 2014 ).…”