Machine learning for accurate estimation of fetal gestational age based on ultrasound images

External validation of models to estimate gestational age in the second and third trimester using ultrasound: A prospective multicentre observational study

OBJECTIVES

Accurate assessment of gestational age (GA) is important at both individual and population levels. The most accurate way to estimate GA in women who book late in pregnancy is unknown. The aim of this study was to externally validate the accuracy of equations for GA estimation in late pregnancy and to identify the best equation for estimating GA in women who do not receive an ultrasound scan until the second or third trimester.

DESIGN

This was a prospective, observational cross-sectional study.

SETTING

57 prenatal care centres, France.

PARTICIPANTS

Women with a singleton pregnancy and a previous 11-14-week dating scan that gave the observed GA were recruited over an 8-week period. They underwent a standardised ultrasound examination at one time point during the pregnancy (15-43 weeks), measuring 12 foetal biometric parameters that have previously been identified as useful for GA estimation.

MAIN OUTCOME MEASURES

A total of 189 equations that estimate GA based on foetal biometry were examined and compared with GA estimation based on foetal CRL. Comparisons between the observed GA and the estimated GA were made using R2, calibration slope and intercept. RMSE, mean difference and 95% range of error were also calculated.

RESULTS

A total of 2741 pregnant women were examined. After exclusions, 2339 participants were included. In the 20 best performing equations, the intercept ranged from -0.22 to 0.30, the calibration slope from 0.96 to 1.03 and the RSME from 0.67 to 0.87. Overall, multiparameter models outperformed single-parameter models. Both the 95% range of error and mean difference increased with gestation. Commonly used models based on measurement of the head circumference alone were not amongst the best performing models and were associated with higher 95% error and mean difference.

CONCLUSIONS

We provide strong evidence that GA-specific equations based on multiparameter models should be used to estimate GA in late pregnancy. However, as all methods of GA assessment in late pregnancy are associated with large prediction intervals, efforts to improve access to early antenatal ultrasound must remain a priority.

TRIAL REGISTRATION

The proposal for this study and the corresponding methodological review was registered on PROSPERO international register of systematic reviews (registration number: CRD4201913776).

Identifying First-Trimester Risk Factors for SGA-LGA Using Weighted Inheritance Voting Ensemble Learning

The classification of fetuses as Small for Gestational Age (SGA) and Large for Gestational Age (LGA) is a critical aspect of neonatal health assessment. SGA and LGA, terms used to describe fetal weights that fall below or above the expected weights for Appropriate for Gestational Age (AGA) fetuses, indicate intrauterine growth restriction and excessive fetal growth, respectively. Early prediction and assessment of latent risk factors associated with these classifications can facilitate timely medical interventions, thereby optimizing the health outcomes for both the infant and the mother. This study aims to leverage first-trimester data to achieve these objectives. This study analyzed data from 7943 pregnant women, including 424 SGA, 928 LGA, and 6591 AGA cases, collected from 2015 to 2021 at the Third Affiliated Hospital of Sun Yat-sen University in Guangzhou, China. We propose a novel algorithm, named the Weighted Inheritance Voting Ensemble Learning Algorithm (WIVELA), to predict the classification of fetuses into SGA, LGA, and AGA categories based on biochemical parameters, maternal factors, and morbidity during pregnancy. Additionally, we proposed algorithms for relevance determination based on the classifier to ascertain the importance of features associated with SGA and LGA. The proposed classification solution demonstrated a notable average accuracy rate of 92.12% on 10-fold cross-validation over 100 loops, outperforming five state-of-the-art machine learning algorithms. Furthermore, we identified significant latent maternal risk factors directly associated with SGA and LGA conditions, such as weight change during the first trimester, prepregnancy weight, height, age, and obstetric factors like fetal growth restriction and birthing LGA baby. This study also underscored the importance of biomarker features at the end of the first trimester, including HDL, TG, OGTT-1h, OGTT-0h, OGTT-2h, TC, FPG, and LDL, which reflect the status of SGA or LGA fetuses. This study presents innovative solutions for classifying and identifying relevant attributes, offering valuable tools for medical teams in the clinical monitoring of fetuses predisposed to SGA and LGA conditions during the initial stage of pregnancy. These proposed solutions facilitate early intervention in nutritional care and prenatal healthcare, thereby contributing to enhanced strategies for managing the health and well-being of both the fetus and the expectant mother.

Etiologically Based Functional Taxonomy of the Preterm Birth Syndrome

Preterm birth (PTB) is a complex syndrome traditionally defined by a single parameter, namely, gestational age at birth (ie, ˂37 weeks). This approach has limitations for clinical usefulness and may explain the lack of progress in identifying cause-specific effective interventions. The authors offer a framework for a functional taxonomy of PTB based on (1) conceptual principles established a priori; (2) known etiologic factors; (3) specific, prospectively identified obstetric and neonatal clinical phenotypes; and (4) postnatal follow-up of growth and development up to 2 years of age. This taxonomy includes maternal, placental, and fetal conditions routinely recorded in data collection systems.

Testing the generalizability and effectiveness of deep learning models among clinics: sperm detection as a pilot study

BACKGROUND

Deep learning has been increasingly investigated for assisting clinical in vitro fertilization (IVF). The first technical step in many tasks is to visually detect and locate sperm, oocytes, and embryos in images. For clinical deployment of such deep learning models, different clinics use different image acquisition hardware and different sample preprocessing protocols, raising the concern over whether the reported accuracy of a deep learning model by one clinic could be reproduced in another clinic. Here we aim to investigate the effect of each imaging factor on the generalizability of object detection models, using sperm analysis as a pilot example.

METHODS

Ablation studies were performed using state-of-the-art models for detecting human sperm to quantitatively assess how model precision (false-positive detection) and recall (missed detection) were affected by imaging magnification, imaging mode, and sample preprocessing protocols. The results led to the hypothesis that the richness of image acquisition conditions in a training dataset deterministically affects model generalizability. The hypothesis was tested by first enriching the training dataset with a wide range of imaging conditions, then validated through internal blind tests on new samples and external multi-center clinical validations.

RESULTS

Ablation experiments revealed that removing subsets of data from the training dataset significantly reduced model precision. Removing raw sample images from the training dataset caused the largest drop in model precision, whereas removing 20x images caused the largest drop in model recall. by incorporating different imaging and sample preprocessing conditions into a rich training dataset, the model achieved an intraclass correlation coefficient (ICC) of 0.97 (95% CI: 0.94-0.99) for precision, and an ICC of 0.97 (95% CI: 0.93-0.99) for recall. Multi-center clinical validation showed no significant differences in model precision or recall across different clinics and applications.

CONCLUSIONS

The results validated the hypothesis that the richness of data in the training dataset is a key factor impacting model generalizability. These findings highlight the importance of diversity in a training dataset for model evaluation and suggest that future deep learning models in andrology and reproductive medicine should incorporate comprehensive feature sets for enhanced generalizability across clinics.

Accuracy of prenatal and postnatal biomarkers for estimating gestational age: a systematic review and meta-analysis

Background

Knowledge of gestational age (GA) is key in clinical management of individual obstetric patients, and critical to be able to calculate rates of preterm birth and small for GA at a population level. Currently, the gold standard for pregnancy dating is measurement of the fetal crown rump length at 11-14 weeks of gestation. However, this is not possible for women first presenting in later pregnancy, or in settings where routine ultrasound is not available. A reliable, cheap and easy to measure GA-dependent biomarker would provide an important breakthrough in estimating the age of pregnancy. Therefore, the aim of this study was to determine the accuracy of prenatal and postnatal biomarkers for estimating gestational age (GA).

Methods

Systematic review prospectively registered with PROSPERO (CRD42020167727) and reported in accordance with the PRISMA-DTA. Medline, Embase, CINAHL, LILACS, and other databases were searched from inception until September 2023 for cohort or cross-sectional studies that reported on the accuracy of prenatal and postnatal biomarkers for estimating GA. In addition, we searched Google Scholar and screened proceedings of relevant conferences and reference lists of identified studies and relevant reviews. There were no language or date restrictions. Pooled coefficients of correlation and root mean square error (RMSE, average deviation in weeks between the GA estimated by the biomarker and that estimated by the gold standard method) were calculated. The risk of bias in each included study was also assessed.

Findings

Thirty-nine studies fulfilled the inclusion criteria: 20 studies (2,050 women) assessed prenatal biomarkers (placental hormones, metabolomic profiles, proteomics, cell-free RNA transcripts, and exon-level gene expression), and 19 (1,738,652 newborns) assessed postnatal biomarkers (metabolomic profiles, DNA methylation profiles, and fetal haematological components). Among the prenatal biomarkers assessed, human chorionic gonadotrophin measured in maternal serum between 4 and 9 weeks of gestation showed the highest correlation with the reference standard GA, with a pooled coefficient of correlation of 0.88. Among the postnatal biomarkers assessed, metabolomic profiling from newborn blood spots provided the most accurate estimate of GA, with a pooled RMSE of 1.03 weeks across all GAs. It performed best for term infants with a slightly reduced accuracy for preterm or small for GA infants. The pooled RMSEs for metabolomic profiling and DNA methylation profile from cord blood samples were 1.57 and 1.60 weeks, respectively.

Interpretation

We identified no antenatal biomarkers that accurately predict GA over a wide window of pregnancy. Postnatally, metabolomic profiling from newborn blood spot provides an accurate estimate of GA, however, as this is known only after birth it is not useful to guide antenatal care. Further prenatal studies are needed to identify biomarkers that can be used in isolation, as part of a biomarker panel, or in combination with other clinical methods to narrow prediction intervals of GA estimation.

Funding

The research was funded by the Bill and Melinda Gates Foundation (INV-000368). ATP is supported by the Oxford Partnership Comprehensive Biomedical Research Centre with funding from the NIHR Biomedical Research Centre funding scheme. The views expressed are those of the authors and not necessarily those of the UK National Health Service, the NIHR, the Department of Health, or the Department of Biotechnology. The funders of this study had no role in study design, data collection, analysis or interpretation of the data, in writing the paper or the decision to submit for publication.

Design of a targeted blood transcriptional panel for monitoring immunological changes accompanying pregnancy

Background

Immunomodulatory processes exert steering functions throughout pregnancy. Detecting diversions from this physiologic immune clock may help identify pregnant women at risk for pregnancy-associated complications. We present results from a data-driven selection process to develop a targeted panel of mRNAs that may prove effective in detecting pregnancies diverting from the norm.

Methods

Based on a de novo dataset from a resource-constrained setting and a dataset from a resource-rich area readily available in the public domain, whole blood gene expression profiles of uneventful pregnancies were captured at multiple time points during pregnancy. BloodGen3, a fixed blood transcriptional module repertoire, was employed to analyze and visualize gene expression patterns in the two datasets. Differentially expressed genes were identified by comparing their abundance to non-pregnant postpartum controls. The selection process for a targeted gene panel considered (i) transcript abundance in whole blood; (ii) degree of correlation with the BloodGen3 module; and (iii) pregnancy biology.

Results

We identified 176 transcripts that were complemented with eight housekeeping genes. Changes in transcript abundance were seen in the early stages of pregnancy and similar patterns were observed in both datasets. Functional gene annotation suggested significant changes in the lymphoid, prostaglandin and inflammation-associated compartments, when compared to the postpartum controls.

Conclusion

The gene panel presented here holds promise for the development of predictive, targeted, transcriptional profiling assays. Such assays might become useful for monitoring of pregnant women, specifically to detect potential adverse events early. Prospective validation of this targeted assay, in-depth investigation of functional annotations of differentially expressed genes, and assessment of common pregnancy-associated complications with the aim to identify these early in pregnancy to improve pregnancy outcomes are the next steps.

Artificial intelligence as a new answer to old challenges in maternal-fetal medicine and obstetrics

BACKGROUND

Following the latest trends in the development of artificial intelligence (AI), the possibility of processing an immense amount of data has created a breakthrough in the medical field. Practitioners can now utilize AI tools to advance diagnostic protocols and improve patient care.

OBJECTIVE

The aim of this article is to present the importance and modalities of AI in maternal-fetal medicine and obstetrics and its usefulness in daily clinical work and decision-making process.

METHODS

A comprehensive literature review was performed by searching PubMed for articles published from inception up until August 2023, including the search terms "artificial intelligence in obstetrics", "maternal-fetal medicine", and "machine learning" combined through Boolean operators. In addition, references lists of identified articles were further reviewed for inclusion.

RESULTS

According to recent research, AI has demonstrated remarkable potential in improving the accuracy and timeliness of diagnoses in maternal-fetal medicine and obstetrics, e.g., advancing perinatal ultrasound technique, monitoring fetal heart rate during labor, or predicting mode of delivery. The combination of AI and obstetric ultrasound can help optimize fetal ultrasound assessment by reducing examination time and improving diagnostic accuracy while reducing physician workload.

CONCLUSION

The integration of AI in maternal-fetal medicine and obstetrics has the potential to significantly improve patient outcomes, enhance healthcare efficiency, and individualized care plans. As technology evolves, AI algorithms are likely to become even more sophisticated. However, the successful implementation of AI in maternal-fetal medicine and obstetrics needs to address challenges related to interpretability and reliability.

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

Artificial intelligence (AI) has gained prominence in medical imaging, particularly in obstetrics and gynecology (OB/GYN), where ultrasound (US) is the preferred method. It is considered cost effective and easily accessible but is time consuming and hindered by the need for specialized training. To overcome these limitations, AI models have been proposed for automated plane acquisition, anatomical measurements, and pathology detection. This study aims to overview recent literature on AI applications in OB/GYN US imaging, highlighting their benefits and limitations. For the methodology, a systematic literature search was performed in the PubMed and Cochrane Library databases. Matching abstracts were screened based on the PICOS (Participants, Intervention or Exposure, Comparison, Outcome, Study type) scheme. Articles with full text copies were distributed to the sections of OB/GYN and their research topics. As a result, this review includes 189 articles published from 1994 to 2023. Among these, 148 focus on obstetrics and 41 on gynecology. AI-assisted US applications span fetal biometry, echocardiography, or neurosonography, as well as the identification of adnexal and breast masses, and assessment of the endometrium and pelvic floor. To conclude, the applications for AI-assisted US in OB/GYN are abundant, especially in the subspecialty of obstetrics. However, while most studies focus on common application fields such as fetal biometry, this review outlines emerging and still experimental fields to promote further research.

Application and Progress of Artificial Intelligence in Fetal Ultrasound

Prenatal ultrasonography is the most crucial imaging modality during pregnancy. However, problems such as high fetal mobility, excessive maternal abdominal wall thickness, and inter-observer variability limit the development of traditional ultrasound in clinical applications. The combination of artificial intelligence (AI) and obstetric ultrasound may help optimize fetal ultrasound examination by shortening the examination time, reducing the physician's workload, and improving diagnostic accuracy. AI has been successfully applied to automatic fetal ultrasound standard plane detection, biometric parameter measurement, and disease diagnosis to facilitate conventional imaging approaches. In this review, we attempt to thoroughly review the applications and advantages of AI in prenatal fetal ultrasound and discuss the challenges and promises of this new field.