RT doctoral thesis
T1 Predicting Neurodevelopment in Very Preterm Infants Using Thalamic MRI Features and Machine Learning
A1 Trimarco, Emiliano
A2 Materno-Infantil y Radiología
K1 MRI
K1 Thalamus
K1 Preterm Infants
K1 Neurodevelopment
K1 BrainAGE
AB Preterm birth is the primary cause of infant death and is associated with laterneurodevelopmental impairments. Neuroimaging is a powerful tool to analyse neuroanatomy abnormalities in preterm infants, allowing the examination of differentbrain structures, such as the thalamus and its alterations. Notably, the thalamusis a crucial hub for regulating cortical connectivity. Moreover, severe brain injuryin preterm infants can impact thalamic growth and maturation over the long term.Therefore, studying thalamus morphology during the neonatal period using magneticresonance imaging (MRI) can help identify markers that can predict neurodevelopmental outcomes in this vulnerable population. In this work, we semi-automaticallysegmented the thalamus structure from MRI scans and extracted thalamic morphological features from these segmentations. Consecutively, we employed K-meansclustering, an unsupervised machine learning algorithm, to explore hidden patternsrelated to thalamic features in early and term-equivalent scans. Preliminary analyses revealed a significant association between these features and MRI scores usedin clinical settings to assess brain development in very preterm infants at termequivalent age. The results showed 77% of preterm-born infants with abnormalMRI scores were clustered together, suggesting a strong link between these featuresand brain development complications. While several studies demonstrate the relationship between preterm birth and reduced thalamus volume at term-equivalentage, our study aims to investigate the link between thalamic volume trajectoryduring the early postnatal period and neurodevelopment at two years of age. Considering perinatal variables such as brain injury, we analysed the association ofthalamic volume trajectory, calculated from early and term-equivalent MRIs of 116very preterm infants, with cognitive, motor, and language outcomes at two years ofage, assessed using the Bayley Scales of Infant and Toddler Development Third Edition. Our analysis employs bivariate methods to describe the study population interms of clinical variables. In addition, we examined the impact of clinical variableson thalamic volume and then explored the relationship between thalamic volumeand neurodevelopmental outcomes using multilevel linear regression models. Ourresults suggest an association between severe brain injury (p < 0.001) and reducedthalamic volume. Moreover, thalamic volume trajectory during early postnatal lifewas significantly associated with the three subscale scores of the neurodevelopmentalassessment (cognitive: p = 0.004; motor: p = 0.001; language: p = 0.019). Finally,we employed Brain Age Gap Estimation (BrainAGE) based on thalamic volume toquantify delays in thalamic growth in very preterm infants compared to those bornat term. Successively, we developed a machine learning classification model usingBrainAGE analysis results, achieving 82% accuracy in predicting adverse neurodevelopmental outcomes. This model highlights the potential of the thalamus as abiomarker for the early identification of preterm infants at risk of adverse neurodevelopmental outcomes.
YR 2026
FD 2026
LK http://hdl.handle.net/10498/39691
UL http://hdl.handle.net/10498/39691
LA eng
DS Repositorio Institucional de la Universidad de Cádiz
RD 06-nov-2026