Enhancing prenatal care through deep learning

One promising application of deep learning within the medical field is in prenatal care, a critical aspect of healthcare provided to pregnant women aimed at preventing complications and ensuring the well-being of both the mother and infant before, during, and after birth. Prenatal care involves regular check-ups with a healthcare provider to monitor the mother's health and the growth and development of the fetus. Typically, this includes a series of tests and screenings, such as ultrasounds, blood tests, genetic testing, and, when necessary, surgical interventions, all aimed at identifying and addressing potential complications early on. This thesis is dedicated to utilizing deep learning techniques to improve the health and well-being of mothers and fetuses during pregnancy and delivery. Specifically, it focuses on developing an automated method for recognizing standard planes and measuring biometrics during routine fetal ultrasound exams. Additionally, we have designed a method for directly estimating fetal birth weight from ultrasound video scans, which has been enhanced by incorporating multimodal data. Building on these findings, we introduce a novel method for predicting fetal weight during pregnancy based exclusively on the fetal abdominal view. Furthermore, we present a fast and effective neural network tailored for segmenting and highlighting placental vessels during fetoscopic laser photocoagulation in cases of Twin-to-Twin Transfusion Syndrome (TTTS), aiming to assist surgeons during fetal surgery in clinical environments.