Fetal Brain MRI from Stanford Lucile Packard Children's Hospital

Magnetic resonance imaging offers unrivaled visualization of the fetal brain, which forms the basis for establishing age-specific morphologic milestones. However, gauging age-appropriate neural development remains a difficult task due to the constantly changing appearance of the fetal brain, variable image quality, and frequent motion artifacts. Here we present a large diverse single-center dataset of 741 developmentally normal fetal brain MRI with their corresponding gestational ages ranging from 19 to 39 weeks, as determined by estimated delivery date based on 1st trimester US. This dataset was used to build a deep learning model that accurately and reliably predicts gestational age using attention guidance and multi-plane learning approaches.

Index:
- folders 1 to 741, subdirectories for each fetal brain MRI in .jpg format, consisting of a sequence for each of the 3 planes (axial, sagittal, coronal)
- 'labels.xlsx', with columns for patient ID, gestational age in days and in weeks, and axial/sagittal/coronal series numbers and middle slice file names