Fetal MRI provides great anatomic details for diagnosis of perinatal disorders when ultrasound is inconclusive in assessing fetal anatomy during all phases of gestation. Immediate interventions can be attempted when abnormal anatomic changes of fetal brain structures are identified early during gestation. Size measurements of a fetal brain structure can be realized by identifying several landmarks of the structure accurately and calculating the distance between the landmarks. We developed a deep learning model that exploits U-net as a ‘transforming’ function to learn imaging features adjacent to a landmark point and predict the landmark location automatically.
This abstract and the presentation materials are available to members only; a login is required.