Very preterm (VPT) infants (i.e., <32 weeks’ gestational age) are at much higher risk of developing various neurodevelopmental deficits. Earlier diagnosis soon after birth is urgently needed, as the first 2–3 years after birth represents a critical window of opportunity for early neuroplasticity in preterm infants. However, efforts to target interventions to prevent and/or treat neurodevelopmental deficits are hampered by our current inability to diagnose or predict risk of deficits accurately before the age of 3–5 years. Advances in magnetic resonance imaging (MRI) enable the noninvasive visualization of infants’ brains through acquired multimodal images. Accurately analyzing quantitative MRI features, including anatomical and connectivity features, affords unique opportunities to study early postnatal brain development and identify novel prognostic biomarkers. Building upon this premise, this chapter reviews several recent studies that attempt to predict future neurodevelopment of VPT infants through analyzing advanced neuroimaging MRI data with sophisticated deep learning models.