Development of a Machine Learning Model for Sonographic Assessment of Gestational Age

Abstract

ImportanceFetal ultrasonography is essential for confirmation of gestational age (GA), and accurate GA assessment is important for providing appropriate care throughout pregnancy and for identifying complications, including fetal growth disorders. Derivation of GA from manual fetal biometry measurements (ie, head, abdomen, and femur) is operator dependent and time-consuming.ObjectiveTo develop artificial intelligence (AI) models to estimate GA with higher accuracy and reliability, leveraging standard biometry images and fly-to ultrasonography videos.Design, Setting, and ParticipantsTo improve GA estimates, this diagnostic study used AI to interpret standard plane ultrasonography images and fly-to ultrasonography videos, which are 5- to 10-second videos that can be automatically recorded as part of the standard of care before the still image is captured. Three AI models were developed and validated: (1) an image model using standard plane images, (2) a video model using fly-to videos, and (3) an ensemble model (combining both image and video models). The models were trained and evaluated on data from the Fetal Age Machine Learning Initiative (FAMLI) cohort, which included participants from 2 study sites at Chapel Hill, North Carolina (US), and Lusaka, Zambia. Participants were eligible to be part of this study if they received routine antenatal care at 1 of these sites, were aged 18 years or older, had a viable intrauterine singleton pregnancy, and could provide written consent. They were not eligible if they had known uterine or fetal abnormality, or had any other conditions that would make participation unsafe or complicate interpretation. Data analysis was performed from January to July 2022.Main Outcomes and MeasuresThe primary analysis outcome for GA was the mean difference in absolute error between the GA model estimate and the clinical standard estimate, with the ground truth GA extrapolated from the initial GA estimated at an initial examination.ResultsOf the total cohort of 3842 participants, data were calculated for a test set of 404 participants with a mean (SD) age of 28.8 (5.6) years at enrollment. All models were statistically superior to standard fetal biometry–based GA estimates derived from images captured by expert sonographers. The ensemble model had the lowest mean absolute error compared with the clinical standard fetal biometry (mean [SD] difference, −1.51 [3.96] days; 95% CI, −1.90 to −1.10 days). All 3 models outperformed standard biometry by a more substantial margin on fetuses that were predicted to be small for their GA.Conclusions and RelevanceThese findings suggest that AI models have the potential to empower trained operators to estimate GA with higher accuracy.

Evolving the Era of 5D Ultrasound? A Systematic Literature Review on the Applications for Artificial Intelligence Ultrasound Imaging in Obstetrics and Gynecology

“…The estimation of GA is one of the important indications for obstetric US in early pregnancy that helps to adjust maternity care and identify complications such as prematurity or fetal growth disorders [144]. It is usually calculated using the last menstrual period and is confirmed with fetal CRL and biometry.…”

“…Lastly, four studies used data from the Fetal Age Machine Learning Initiative (FAMLI), which is an obstetrical US development project in low-income settings. The purpose of these studies, which were based on US data from the US and Zambia, was the successful establishment of an AI algorithm for GA estimation from simplified blind US sweeps of US novices in low-resource countries [144,145,152,153]. The benefits of the GA AI models were the possibility for application in low-resource countries [144,145,148,149,152], even without internet connectivity [145], and in portable devices [148], promising high accuracy with an error of 3.9 to 5 days in GA estimation [149,152].…”

“…The purpose of these studies, which were based on US data from the US and Zambia, was the successful establishment of an AI algorithm for GA estimation from simplified blind US sweeps of US novices in low-resource countries [144,145,152,153]. The benefits of the GA AI models were the possibility for application in low-resource countries [144,145,148,149,152], even without internet connectivity [145], and in portable devices [148], promising high accuracy with an error of 3.9 to 5 days in GA estimation [149,152]. An important limitation of the AI models was described to be application in very early [144,147] or very late stages of pregnancy [146,147,152], the latter of which was due to the thickened texture of the fetal skull.…”

The relationship between placental thickness and gestational age in pregnant women: A cross‐sectional study

“…Ultrasound measurement of placental thickness is a simple and effective criterion for determining GA. The diameter around the head, biparietal diameter, abdominal circumference, and femoral length are all sonographically derived fetal characteristics that are used to date the pregnancy 8,9 . These are commonly used to estimate GA, either alone or in combination.…”

“…The diameter around the head, biparietal diameter, abdominal circumference, and femoral length are all sonographically derived fetal characteristics that are used to date the pregnancy. 8,9 These are commonly used to estimate GA, either alone or in combination. Researchers have demonstrated that placental markers effectively assess children for GA (GA) and that intrauterine growth restriction (IUGR) requires early intervention.…”