Abstract
BackgroundWe tested the hypothesis whether texture analysis (TA) from MR images could identify patterns associated with an abnormal neurobehavior in small for gestational age (SGA) neonates.MethodsUltrasound and MRI were performed on 91 SGA fetuses at 37 weeks of GA. Frontal lobe, basal ganglia, mesencephalon and cerebellum were delineated from fetal MRIs. SGA neonates underwent NBAS test and were classified as abnormal if ≥1 area was <5th centile and as normal if all areas were >5th centile. Textural features associated with neurodevelopment were selected and machine learning was used to model a predictive algorithm.ResultsOf the 91 SGA neonates, 49 were classified as normal and 42 as abnormal. The accuracies to predict an abnormal neurobehavior based on TA were 95.12% for frontal lobe, 95.56% for basal ganglia, 93.18% for mesencephalon and 83.33% for cerebellum.ConclusionsFetal brain MRI textural patterns were associated with neonatal neurodevelopment. Brain MRI TA could be a useful tool to predict abnormal neurodevelopment in SGA.
Highlights
Smallness for gestational age affects 10% of all pregnancies [1]
Some fetuses with this diagnosis are constitutionally small, in a substantial proportion of cases, the diagnosis of small for gestational age (SGA) identifies mild forms of fetal growth restriction due to placental insufficiency that are not expressed by umbilical artery Doppler
Concerning the scores of the Neonatal Behavioral Assessment Scale (NBAS) test, overall worse results were found in the abnormal NBAS test results group and were more pronounced in the habituation and regulation of state clusters (Table 4)
Summary
In clinical practice when an estimated fetal weight is below the tenth centile and Doppler assessment of the umbilical artery is normal, the diagnosis of a small-for-gestational-age (SGA) is reached [2,3,4]. At present the detection of SGAs at risk of abnormal neurodevelopment is limited since standard clinical examinations fail to identify significant differences. For this purpose, it is crucial to develop new biomarkers based on the characterization of distinctive brain patterns associated with abnormal neurodevelopment. We tested the hypothesis whether texture analysis (TA) from MR images could identify patterns associated with an abnormal neurobehavior in small for gestational age (SGA) neonates
Sign-in/Register to view highlights & summary Sign-in/Register to access full text options 
Talk to us
Join us for a 30 min session where you can share your feedback and ask us any queries you have
Schedule a call
