MIT AI keeps fetal brain MRI scans sharp even when the baby moves
Fetal brain MRI builds a 3D picture from a stack of 2D slices, but when the baby shifts during the scan, those slices end up at odd angles and leave gaps that can hide problems. MIT News reports that researchers at MIT, Boston Children’s Hospital and Inria built E(3)-Pose, a deep learning model that tracks the head’s position so the scanner can adjust on the fly. Its trick is building the left-right symmetry of the fetal head directly into the network, which makes orientation easier to read. The team presented the work at the 2026 European Conference on Computer Vision and hopes it brings faster, more comfortable scans and spares families repeat visits.