Sonographic determination of gestational age

Combining deep learning and intelligent biometry to extract ultrasound standard planes and assess early gestational weeks

OBJECTIVES

To develop and validate a fully automated AI system to extract standard planes, assess early gestational weeks, and compare the performance of the developed system to sonographers.

METHODS

In this three-center retrospective study, 214 consecutive pregnant women that underwent transvaginal ultrasounds between January and December 2018 were selected. Their ultrasound videos were automatically split into 38,941 frames using a particular program. First, an optimal deep-learning classifier was selected to extract the standard planes with key anatomical structures from the ultrasound frames. Second, an optimal segmentation model was selected to outline gestational sacs. Third, novel biometry was used to measure, select the largest gestational sac in the same video, and assess gestational weeks automatically. Finally, an independent test set was used to compare the performance of the system with that of sonographers. The outcomes were analyzed using the area under the receiver operating characteristic curve (AUC), sensitivity, specificity, and mean similarity between two samples (mDice).

RESULTS

The standard planes were extracted with an AUC of 0.975, a sensitivity of 0.961, and a specificity of 0.979. The gestational sacs' contours were segmented with a mDice of 0.974 (error less than 2 pixels). The comparison showed that the relative error of the tool in assessing gestational weeks was 12.44% and 6.92% lower and faster (min, 0.17 vs. 16.6 and 12.63) than that of the intermediate and senior sonographers, respectively.

CONCLUSIONS

This proposed end-to-end tool allows automatic assessment of gestational weeks in early pregnancy and may reduce manual analysis time and measurement errors.

CLINICAL RELEVANCE STATEMENT

The fully automated tool achieved high accuracy showing its potential to optimize the increasingly scarce resources of sonographers. Explainable predictions can assist in their confidence in assessing gestational weeks and provide a reliable basis for managing early pregnancy cases.

KEY POINTS

• The end-to-end pipeline enabled automatic identification of the standard plane containing the gestational sac in an ultrasound video, as well as segmentation of the sac contour, automatic multi-angle measurements, and the selection of the sac with the largest mean internal diameter to calculate the early gestational week. • This fully automated tool combining deep learning and intelligent biometry may assist the sonographer in assessing the early gestational week, increasing accuracy and reducing the analyzing time, thereby reducing observer dependence.

Can Early First Trimester Ultrasounds Correctly Determine Gestational Age Compared to Ultrasounds Performed Between 7 to 14 Weeks Gestational Age?

OBJECTIVES

The Society of Obstetricians and Gynaecologists of Canada (SOGC) recommends the use of an ultrasound performed between 7 and 14 weeks gestation to accurately predict gestational age (GA). This study aimed to assess the accuracy of earlier ultrasounds (5 to 6⁶ weeks gestation) by comparing the estimated delivery dates (EDD) in participants that had undergone both an earlier ultrasound and ultrasound completed during the standard of care timeframe.

METHODS

EDD based on crown-rump length were retrospectively reviewed for patients that had undergone an ultrasound between 5-6⁶ weeks GA versus the recommended 7-14 weeks GA at the Montfort Hospital during 2018 and 2019. The charts of 981 patients that had an ultrasound prior to 7 weeks GA and at 7-14 weeks GA were reviewed; 54 were included.

RESULTS

There was no significant difference (P = 0.307) between the EDD of the early (5-6⁶ weeks GA) and the second ultrasound (7-14 weeks GA). The first ultrasounds were then separated into very early (5-5⁶ weeks GA) and early (6-6⁶ weeks GA) and compared. No significant differences (P = 0.579) were found. Similarly, no difference was found between the EDD of the early (6-6⁶ weeks GA) and standard of care timing (P = 0.324).

CONCLUSION

These results show no significant difference in accurately determining the EDD between ultrasounds completed at the early and standard of care time points. This could result in cost-saving benefits by foregoing a repeat ultrasound; however, further research is required prior to applying these findings in clinical settings.

Analysis of maturation features in fetal brain ultrasound via artificial intelligence for the estimation of gestational age

BACKGROUND

Optimal prenatal care relies on accurate gestational age dating. After the first trimester, the accuracy of current gestational age estimation methods diminishes with increasing gestational age. Considering that, in many countries, access to first trimester crown rump length is still difficult owing to late booking, infrequent access to prenatal care, and unavailability of early ultrasound examination, the development of accurate methods for gestational age estimation in the second and third trimester of pregnancy remains an unsolved challenge in fetal medicine.

OBJECTIVE

This study aimed to evaluate the performance of an artificial intelligence method based on automated analysis of fetal brain morphology on standard cranial ultrasound sections to estimate the gestational age in second and third trimester fetuses compared with the current formulas using standard fetal biometry.

STUDY DESIGN

Standard transthalamic axial plane images from a total of 1394 patients undergoing routine fetal ultrasound were used to develop an artificial intelligence method to automatically estimate gestational age from the analysis of fetal brain information. We compared its performance-as stand alone or in combination with fetal biometric parameters-against 4 currently used fetal biometry formulas on a series of 3065 scans from 1992 patients undergoing second (n=1761) or third trimester (n=1298) routine ultrasound, with known gestational age estimated from crown rump length in the first trimester.

RESULTS

Overall, 95% confidence interval of the error in gestational age estimation was 14.2 days for the artificial intelligence method alone and 11.0 when used in combination with fetal biometric parameters, compared with 12.9 days of the best method using standard biometrics alone. In the third trimester, the lower 95% confidence interval errors were 14.3 days for artificial intelligence in combination with biometric parameters and 17 days for fetal biometrics, whereas in the second trimester, the 95% confidence interval error was 6.7 and 7, respectively. The performance differences were even larger in the small-for-gestational-age fetuses group (14.8 and 18.5, respectively).

CONCLUSION

An automated artificial intelligence method using standard sonographic fetal planes yielded similar or lower error in gestational age estimation compared with fetal biometric parameters, especially in the third trimester. These results support further research to improve the performance of these methods in larger studies.

GestAltNet: aggregation and attention to improve deep learning of gestational age from placental whole-slide images

The placenta is the first organ to form and performs the functions of the lung, gut, kidney, and endocrine systems. Abnormalities in the placenta cause or reflect most abnormalities in gestation and can have life-long consequences for the mother and infant. Placental villi undergo a complex but reproducible sequence of maturation across the third-trimester. Abnormalities of villous maturation are a feature of gestational diabetes and preeclampsia, among others, but there is significant interobserver variability in their diagnosis. Machine learning has emerged as a powerful tool for research in pathology. To capture the volume of data and manage heterogeneity within the placenta, we developed GestaltNet, which emulates human attention to high-yield areas and aggregation across regions. We used this network to estimate the gestational age (GA) of scanned placental slides and compared it to a baseline model lacking the attention and aggregation functions. In the test set, GestaltNet showed a higher r2 (0.9444 vs. 0.9220) than the baseline model. The mean absolute error (MAE) between the estimated and actual GA was also better in the GestaltNet (1.0847 weeks vs. 1.4505 weeks). On whole-slide images, we found the attention sub-network discriminates areas of terminal villi from other placental structures. Using this behavior, we estimated GA for 36 whole slides not previously seen by the model. In this task, similar to that faced by human pathologists, the model showed an r2 of 0.8859 with an MAE of 1.3671 weeks. We show that villous maturation is machine-recognizable. Machine-estimated GA could be useful when GA is unknown or to study abnormalities of villous maturation, including those in gestational diabetes or preeclampsia. GestaltNet points toward a future of genuinely whole-slide digital pathology by incorporating human-like behaviors of attention and aggregation.

Détermination de l'âge gestationnel par échographie

OBJECTIF

Aider les cliniciens à attribuer un âge gestationnel en fonction des résultats de la biométrie échographique.

ISSUES

Déterminer si la datation par échographie offre une évaluation plus précise de l'âge gestationnel que la datation en fonction des dernières règles avec ou sans recours à l'échographie. Offrir, aux praticiens et aux chercheurs du domaine des soins de maternité, des lignes directrices factuelles en matière d'attribution de l'âge gestationnel. Identifier les paramètres biométriques échographiques qui sont de fiabilité supérieure lorsque l'âge gestationnel est incertain. Déterminer la rentabilité de l'évaluation de l'âge gestationnel par échographie. RéSULTATS: La littérature publiée a été récupérée par l'intermédiaire de recherches menées dans PubMed ou MEDLINE et The Cochrane Library en 2013 au moyen d'un vocabulaire contrôlé et de mots clés appropriés (p. ex. « gestational age », « ultrasound biometry » et « ultrasound dating »). Les résultats ont été restreints aux analyses systématiques, aux essais comparatifs randomisés / essais cliniques comparatifs et aux études observationnelles rédigés en anglais. Aucune restriction n'a été appliquée en matière de dates. Les recherches ont été mises à jour de façon régulière et intégrées à la directive clinique jusqu'au 31 juillet 2013. La littérature grise (non publiée) a été identifiée par l'intermédiaire de recherches menées dans les sites Web d'organismes s'intéressant à l'évaluation des technologies dans le domaine de la santé et d'organismes connexes, dans des collections de directives cliniques, dans des registres d'essais cliniques et auprès de sociétés de spécialité médicale nationales et internationales.

VALEURS

La qualité des résultats est évaluée au moyen des critères décrits dans le rapport du Groupe d'étude canadien sur les soins de santé préventifs (Tableau 1). AVANTAGES, DéSAVANTAGES ET COûTS: L'attribution précise d'un âge gestationnel pourrait réduire l'incidence du déclenchement mené en raison d'une grossesse prolongée et améliorer les soins obstétricaux en nous permettant de planifier la chronologie des interventions nécessaires de façon optimale et d'éviter les interventions inutiles. Une datation plus précise permet l'optimisation de la tenue de tests prénataux de dépistage de l'aneuploïdie. Un algorithme national d'attribution de l'âge gestationnel pourrait atténuer les variations pancanadiennes en matière de pratique pour les cliniciens et les chercheurs. Parmi les désavantages potentiels, on trouve la réattribution possible des dates lorsqu'une pathologie fœtale importante (comme le retard de croissance intra-utérin ou la macrosomie) donne lieu à une divergence entre les résultats de la biométrie échographique et l'âge gestationnel clinique. Une telle réattribution pourrait mener à l'omission d'interventions fœtales justifiées ou à la tenue d'interventions fœtales injustifiées. DéCLARATIONS SOMMAIRES: RECOMMANDATIONS.