MIT and Boston Children's researchers build E(3)-Pose AI to track fetal head motion in MRI

MIT, Boston Children's Hospital, and Inria researchers have developed E(3)-Pose, a deep learning model that tracks a fetus's head during MRI scans to produce a high-resolution 3D brain image.

The model embeds left-right symmetry of the fetal head in its architecture to identify the brain's orientation, and it was presented at the 2026 European Conference on Computer Vision.

The team says the model is trained mainly on third-trimester fetuses and plans to extend it to second-trimester scans.