Predicting motor outcome in preterm infants from very early brain diffusion MRI using a deep learning convolutional
Susmita Saha1, Alex Pagnozzi1, Pierrick Bourgeat1
1Australian e-Health Research Centre, CSIRO, Brisbane, Australia.
Neuroimage
|April 13, 2020
Summary
Early brain diffusion MRI with deep learning can predict motor impairments in preterm infants. This convolutional neural network (CNN) model identifies at-risk infants, enabling earlier intervention for better outcomes.
Area of Science:
- Neuroscience
- Medical Imaging
- Artificial Intelligence
Background:
- Preterm birth (born <31 weeks gestational age) significantly increases the risk of neuromotor delay.
- Early prediction of adverse outcomes in preterm infants is critical for timely intervention.
Purpose of the Study:
- To predict abnormal motor outcomes at 2 years corrected age in preterm infants.
- To utilize early brain diffusion magnetic resonance imaging (MRI) and a deep learning convolutional neural network (CNN) model for prediction.
Main Methods:
- Diffusion MRI was acquired between 29-35 weeks postmenstrual age in 77 very preterm infants.
- Fractional anisotropy (FA) maps were generated and used to train a CNN model on image patches.
- Motor outcome was assessed at 2 years corrected age using the Neuro-Sensory Motor Developmental Assessment (NSMDA).
Main Results:
- The CNN model achieved a mean accuracy of 73% (SD 19%) in predicting abnormal motor outcomes.
- Sensitivity was 70% (SD 19%) and specificity was 74% (SD 39%).
- Heatmaps identified motor cortex and somatosensory regions as highly associated with abnormal outcomes.
Conclusions:
- An early brain MRI-based deep learning CNN model shows potential for identifying preterm infants at risk of motor impairment.
- The model can identify brain regions predictive of adverse neurodevelopmental outcomes.
- This approach allows for prediction before term equivalent age without manual feature extraction.
