In-utero 3D MRI analysis of embryos in mice is difficult due to the periodic and non-periodic motion, small tissues and multiple embryos involved. This paper presents an automated algorithm for serial alignment of fetal tissue in MRI of pregnant mice. The algorithm extends our former algorithm to allow follow up across time between 3D MR sequences in a difficult novel small animal application. The algorithm is based on features combining intensity and geometric information and the registration energy function is minimized by alternating optimization with regard to the feature correspondence and transformation model. Experimental validation on a set of MRI acquisition with fetal livers and placentas demonstrate the high accuracy and promise of the approach. The results confirm that measures of development can be automatically derived from multifetal pregnancy in mice.