Related Experiment Video
Updated: May 9, 2026
06:36
Micro-CT Imaging and Morphometric Analysis of Mouse Neonatal Brains
Published on: May 19, 2023
Automatic quantitative MRI texture analysis in small-for-gestational-age fetuses discriminates abnormal neonatal
Magdalena Sanz-Cortes1, Giuseppe A Ratta, Francesc Figueras
1Maternal-Fetal Medicine Department, ICGON, Hospital Clınic, Universitat de Barcelona, Barcelona, Spain. msanz1@clinic.ub.es
Plos One
|August 8, 2013
Summary
Texture analysis of fetal MRI can predict abnormal neurobehavior in small for gestational age (SGA) neonates. This advanced imaging technique offers a promising tool for early identification and intervention in high-risk infants.
Area of Science:
- Neuroimaging
- Developmental Pediatrics
- Machine Learning
Background:
- Small for gestational age (SGA) neonates are at increased risk for abnormal neurodevelopment.
- Current methods for assessing neurodevelopment in SGA neonates can be limited.
Purpose of the Study:
- To investigate if texture analysis (TA) of fetal magnetic resonance imaging (MRI) can identify patterns associated with abnormal neurobehavior in SGA neonates.
- To develop a predictive algorithm for abnormal neurodevelopment using fetal brain MRI texture.
Main Methods:
- Fetal MRI and ultrasound were performed on 91 SGA fetuses at 37 weeks of gestational age (GA).
- Specific brain regions (frontal lobe, basal ganglia, mesencephalon, cerebellum) were delineated from MRIs.
- Neonatal neurobehavioral assessment (NBAS) was used to classify infants as normal or abnormal, with machine learning applied to textural features.
Main Results:
- Texture analysis achieved high accuracy in predicting abnormal neurobehavior: 95.12% for the frontal lobe, 95.56% for the basal ganglia, 93.18% for the mesencephalon, and 83.33% for the cerebellum.
- The study successfully modeled a predictive algorithm using machine learning on textural features.
Conclusions:
- Fetal brain MRI textural patterns are significantly associated with neonatal neurodevelopmental outcomes in SGA infants.
- Brain MRI texture analysis shows potential as a valuable, non-invasive tool for predicting abnormal neurodevelopment in SGA neonates.
