Prediction of cognitive and motor outcome of preterm infants based on automatic quantitative descriptors from neonatal MR brain images

Sci Rep. 2017 May 19;7(1):2163. doi: 10.1038/s41598-017-02307-w.


This study investigates the predictive ability of automatic quantitative brain MRI descriptors for the identification of infants with low cognitive and/or motor outcome at 2-3 years chronological age. MR brain images of 173 patients were acquired at 30 weeks postmenstrual age (PMA) (n = 86) and 40 weeks PMA (n = 153) between 2008 and 2013. Eight tissue volumes and measures of cortical morphology were automatically computed. A support vector machine classifier was employed to identify infants who exhibit low cognitive and/or motor outcome (<85) at 2-3 years chronological age as assessed by the Bayley scales. Based on the images acquired at 30 weeks PMA, the automatic identification resulted in an area under the receiver operation characteristic curve (AUC) of 0.78 for low cognitive outcome, and an AUC of 0.80 for low motor outcome. Identification based on the change of the descriptors between 30 and 40 weeks PMA (n = 66) resulted in an AUC of 0.80 for low cognitive outcome and an AUC of 0.85 for low motor outcome. This study provides evidence of the feasibility of identification of preterm infants at risk of cognitive and motor impairments based on descriptors automatically computed from images acquired at 30 and 40 weeks PMA.

MeSH terms

  • Area Under Curve
  • Brain / diagnostic imaging
  • Brain / pathology
  • Cognition*
  • Humans
  • Image Processing, Computer-Assisted
  • Infant
  • Infant, Newborn
  • Infant, Premature*
  • Magnetic Resonance Imaging* / methods
  • Motor Activity*
  • Prognosis
  • ROC Curve