We develop algorithms for fetal MRI interpretation, to enable noninvasive fetal monitoring from MRI.

We develop algorithms to enable tracking and segmentation of the fetus and placenta in dynamic MRI series. Signal inhomogeneity correction and subsequent analysis of the MRI signal provides measures of placental function and fetal development, which promise to yield novel biomarkers of fetal health for monitoring during pregnancy.


One twin example case. Manual segmentation is performed on the template frame for placenta, fetal livers and fetal brains. Through our temporal registration, the manual segmentation is propagated to the other frames. The video shows one cross-sectional view of the series with the propagated segmentation outlines.