Deep-learning computer vision can identify increased nuchal translucency in the first trimester of pregnancy.

OBJECTIVE: Many fetal anomalies can already be diagnosed by ultrasound in the first trimester of pregnancy. Unfortunately, in clinical practice, detection rates for anomalies in early pregnancy remain low. Our aim was to use an automated image segmentation algorithm to detect one of the most common fetal anomalies: a thickened nuchal translucency (NT), which is a marker for genetic and structural anomalies. METHODS: Standardized mid-sagittal ultrasound images of the fetal head and chest were collected for 560 fetuses between 11 and 13 weeks and 6 days of gestation, 88 (15.7%) of whom had an NT thicker than 3.5 mm. Image quality was graded as high or low by two fetal medicine experts. Images were divided into a training-set (n = 451, 55 thick NT) and a test-set (n = 109, 33 thick NT). We then trained a U-Net convolutional neural network to segment the fetus and the NT region and computed the NT:fetus ratio of these regions. The ability of this ratio to separate thick (anomalous) NT regions from healthy, typical NT regions was first evaluated in ground-truth segmentation to validate the metric and then with predicted segmentation to validate our algorithm, both using the area under the receiver operator curve (AUROC). RESULTS: The ground-truth NT:fetus ratio detected thick NTs with 0.97 AUROC in both the training and test sets. The fetus and NT regions were detected with a Dice score of 0.94 in the test set. The NT:fetus ratio based on model segmentation detected thick NTs with an AUROC of 0.96 relative to clinician labels. At a 91% specificity, 94% of thick NT cases were detected (sensitivity) in the test set. The detection rate was statistically higher (p = 0.003) in high versus low-quality images (AUROC 0.98 vs. 0.90, respectively). CONCLUSION: Our model provides an explainable deep-learning method for detecting increased NT. This technique can be used to screen for other fetal anomalies in the first trimester of pregnancy.

Performance of comprehensive first trimester fetal anatomy assessment.

OBJECTIVE: Ultrasound assessment of the fetal anatomy and fetal echocardiography are feasible in the first trimester of pregnancy. This study was designed to assess the performance of a comprehensive fetal anatomy assessment in a high-risk population at a tertiary fetal medicine unit. METHODS: A retrospective review of high-risk patients undergoing comprehensive fetal anatomy ultrasound assessment between 11 weeks and 13 + 6 weeks of gestation was conducted. Findings of the early anatomy ultrasound scan were compared with those of the second trimester anatomy scan, and birth outcomes or post-mortem results. RESULTS: Early anatomy ultrasounds were performed in 765 patients. The sensitivity of the scan for detecting fetal anomalies compared to the birth outcome was 80.5% (95% CI 73.5-86.3) and specificity was 93.1% (95%CI 90.6-95.2). Positive and negative predictive values were 78.5% (95% CI 71.4-84.6) and 93.9% (95% CI 91.4-95.8), respectively. The most missed and overdiagnosed abnormalities were ventricular septal defects. The second trimester ultrasound had sensitivity of 69.0% (95% CI 55.5-80.5) and specificity of 87.5% (95% CI 84.3-90.2). CONCLUSIONS: In a high-risk population, early assessments had similar performance metrics as the second trimester anatomy ultrasound. We advocate for a comprehensive fetal assessment in the care of high-risk pregnancies.

Impact of Planned Delivery on the Perinatal Outcome of Term Fetuses with Isolated Heart Defects.

OBJECTIVE: Pregnancies complicated by fetal heart defects often undergo a planned delivery prior to term by either induction of labour or cesarean delivery to ensure optimal availability of neonatal care. We aimed to assess whether such planned deliveries achieve their goal of better perinatal care. METHODS: We conducted a retrospective case-control study of pregnancies complicated by isolated fetal cardiac defects, without other fetal comorbidities, managed at a single fetal medicine unit over a 10-year period. Only pregnancies delivered past 37 weeks gestation were included. Patients undergoing elective delivery for care planning reasons only were compared with patients in whom planned delivery was clinically indicated and patients who laboured spontaneously. Obstetric and perinatal outcomes were recorded. RESULTS: Of the 180 pregnancies included in the study, 59 (32.8%) were in the elective group, 49 (27.2%), in the indicated group, and 72 (40%), in the spontaneous group. Mean gestational age at delivery was 39.0 ± 1.1 weeks overall and did not differ between the groups. For the elective group, only 35.6% of deliveries occurred during office hours, which was similar to the 2 other groups. The rate of adverse obstetric or postnatal outcomes was not statistically significantly different between groups. CONCLUSION: Timed delivery at term does not seem to be associated with an increased risk of poor perinatal outcomes. It may improve perinatal care by providing proximity to a neonatal intensive care unit and convenience for patients and providers.

Fetal Surgery for Open Spina Bifida in Canada: Initial Results.

OBJECTIVE: Fetal myelomeningocele closure results in better infant outcomes than postnatal closure at the cost of potential prematurity and maternal morbidity. Our aim is to describe the setup of a fetal myelomeningocele closure program in Canada and document its outcomes. METHODS: We conducted a retrospective review of all open fetal myelomeningocele closure surgeries performed at the Ontario Fetal Centre in its first 3 years of operation (2017-2020). Maternal and fetal baseline characteristics, surgical details, pregnancy outcomes, and infant follow-up until 1 year of age were recorded. RESULTS: Twenty-seven women underwent fetal myelomeningocele closure surgery, 10 of whom (37%) resided outside of Ontario. Mean gestational age at surgery was 25.0 ± 0.7 weeks. All surgeries were technically uncomplicated and no fetal deaths occurred. There was a significant negative correlation between increasing experience and skin-to-skin surgical time (R²â€¯= 0.36; P = 0.001). Of the 26 patients who have delivered, 4 (15.4%) experienced preterm prelabour rupture of membranes. Mean gestational age at delivery was 34.9±3.0 weeks. All but 1 patient delivered by cesarean. Maternal complications occurred in 9 women (34.6%). There were no maternal deaths, but 3 (11.5%) infant deaths. Of the 14 surviving infants who have reached at least 1 year of age, 5 (35.7%) underwent ventriculo-peritoneal shunting. Of the 9 infants who have not yet reached 1 year of age, 3 (33.3%) underwent endoscopic third ventriculostomy and none underwent shunting. CONCLUSION: Fetal open spina bifida closure can be performed in Canada, with results similar to those reported by other international expert centres. Long-term follow-up is ongoing.

Fetal spina bifida: What we tell the parents.

Worldwide, about 150 000 infants are born with spina bifida yearly, making this condition one of the most common fetal central nervous system anomalies compatible with life. Over the last decade, major changes have been introduced in the prenatal diagnosis and management of spina bifida. In this review, we provide a brief summary of the current management of fetal spina bifida and present essential information that should be provided to expecting parents when their fetus has been diagnosed with spina bifida. This information is focused around common parental questions, as encountered in our typical clinical practice, to facilitate knowledge translation.