Evaluating the accuracy and precision of sonographic fetal weight estimation models in extremely early-onset fetal growth restriction

Evaluation of sonographic and clinical measures in early versus late third trimester for birth weight prediction

OBJECTIVE

To evaluate the optimal timing for fetal weight estimation during the third trimester.

METHODS

This retrospective cohort study involved fetal weight estimations from both early (28+0-36+6 weeks) and late (37+0 weeks and beyond) third trimester. These estimations were converted to predicted birth weights using the gestation-adjusted projection formula. Birth weight predictions were compared with actual birth weights, to identify the most effective timing for weight prediction.

RESULTS

The study included 3549 cases, revealing mean percentage errors (MPE) of -3.69% for early sonographic assessments, -2.5% for late sonographic assessments, and -1.9% for late clinical assessments. A significant difference was found between early and late sonographic estimations (P < 0.001), whereas late sonographic and clinical assessments did not differ significantly (P = 0.771). Weight predictions for fetuses below the 10th and above the 90th centiles were less accurate than for those within the 10th-90th centiles (P < 0.001). In women with obesity, late clinical estimations were less precise (MPE of -5.85) compared with non-obese women (MPE of -1.66, P < 0.001). For women with diabetes, early sonographic estimations were more accurate (MPE of -1.31) compared with non-diabetic patients (MPE of -3.94, P < 0.001) though this difference did not persist later in pregnancy.

CONCLUSION

Sonographic and clinical weight predictions in the late third trimester were more accurate than earlier third-trimester sonographic assessments, hence continuous follow up and assessments closer to term are important. In women with diabetes, no adjustments in weight prediction methods are necessary. Accurately predicting birth weights for abnormally small or large fetuses remains challenging, indicating the need for improved screening and diagnostic strategies.

Application of ultrasonographic human estimated foetal weight formulas to cynomolgus monkeys (Macaca fascicularis) at 129-132 days of gestation: A comparative study of estimated and actual birthweight

BACKGROUND

Cynomolgus monkeys (Macaca fascicularis) are essential in biomedical research, including reproductive studies. However, the application of human estimated foetal weight (EFW) formulas using ultrasonography (USG) in these non-human primates is not well established.

OBJECTIVES

This study aims to evaluate the applicability of human EFW formulas for estimating foetal weight in cynomolgus monkeys at approximately 130 days of gestation.

METHODS

Our study involved nine pregnant cynomolgus monkeys. We measured foetal parameters, including biparietal diameter, head circumference, abdominal circumference and femur length using USG. The EFW was calculated using 11 human EFW formulas. The actual birthweight (ABW) was recorded following Cesarean section, the day after the EFW calculation. For comparing EFW and ABW, we employed statistical methods such as mean absolute percentage error (APE) and Bland-Altman analysis.

RESULTS

The ABW ranged between 200.36 and 291.33 g. Among the 11 formulas, the Combs formula showed the lowest APE (4.3%) and highest correlation with ABW (p < 0.001). Notably, EFW and ABW differences for the Combs formula were ≤5% in 66.7% and ≤10% in 100% of cases. The Bland-Altman analysis supported these results, showing that all cases fell within the limits of agreement.

CONCLUSIONS

The Combs formula is applicable for estimating the weight of cynomolgus monkey fetuses with USG at approximately 130 days of gestation. Our observations suggest that the Combs formula can be applied in the prenatal care and biomedical research of this species.

Automatic Localization of the Pons and Vermis on Fetal Brain MR Imaging Using a U-Net Deep Learning Model

BACKGROUND AND PURPOSE

An MRI of the fetus can enhance the identification of perinatal developmental disorders, which improves the accuracy of ultrasound. Manual MRI measurements require training, time, and intra-variability concerns. Pediatric neuroradiologists are also in short supply. Our purpose was developing a deep learning model and pipeline for automatically identifying anatomic landmarks on the pons and vermis in fetal brain MR imaging and suggesting suitable images for measuring the pons and vermis.

MATERIALS AND METHODS

We retrospectively used 55 pregnant patients who underwent fetal brain MR imaging with a HASTE protocol. Pediatric neuroradiologists selected them for landmark annotation on sagittal single-shot T2-weighted images, and the clinically reliable method was used as the criterion standard for the measurement of the pons and vermis. A U-Net-based deep learning model was developed to automatically identify fetal brain anatomic landmarks, including the 2 anterior-posterior landmarks of the pons and 2 anterior-posterior and 2 superior-inferior landmarks of the vermis. Four-fold cross-validation was performed to test the accuracy of the model using randomly divided and sorted gestational age-divided data sets. A confidence score of model prediction was generated for each testing case.

RESULTS

Overall, 85% of the testing results showed a ≥90% confidence, with a mean error of <2.22 mm, providing overall better estimation results with fewer errors and higher confidence scores. The anterior and posterior pons and anterior vermis showed better estimation (which means fewer errors in landmark localization) and accuracy and a higher confidence level than other landmarks. We also developed a graphic user interface for clinical use.

CONCLUSIONS

This deep learning-facilitated pipeline practically shortens the time spent on selecting good-quality fetal brain images and performing anatomic measurements for radiologists.

Maternal PlGF and umbilical Dopplers predict pregnancy outcomes at diagnosis of early-onset fetal growth restriction

BACKGROUNDSevere, early-onset fetal growth restriction (FGR) causes significant fetal and neonatal mortality and morbidity. Predicting the outcome of affected pregnancies at the time of diagnosis is difficult, thus preventing accurate patient counseling. We investigated the use of maternal serum protein and ultrasound measurements at diagnosis to predict fetal or neonatal death and 3 secondary outcomes: fetal death or delivery at or before 28+0 weeks, development of abnormal umbilical artery (UmA) Doppler velocimetry, and slow fetal growth.METHODSWomen with singleton pregnancies (n = 142, estimated fetal weights [EFWs] below the third centile, less than 600 g, 20+0 to 26+6 weeks of gestation, no known chromosomal, genetic, or major structural abnormalities) were recruited from 4 European centers. Maternal serum from the discovery set (n = 63) was analyzed for 7 proteins linked to angiogenesis, 90 additional proteins associated with cardiovascular disease, and 5 proteins identified through pooled liquid chromatography and tandem mass spectrometry. Patient and clinician stakeholder priorities were used to select models tested in the validation set (n = 60), with final models calculated from combined data.RESULTSThe most discriminative model for fetal or neonatal death included the EFW z score (Hadlock 3 formula/Marsal chart), gestational age, and UmA Doppler category (AUC, 0.91; 95% CI, 0.86-0.97) but was less well calibrated than the model containing only the EFW z score (Hadlock 3/Marsal). The most discriminative model for fetal death or delivery at or before 28+0 weeks included maternal serum placental growth factor (PlGF) concentration and UmA Doppler category (AUC, 0.89; 95% CI, 0.83-0.94).CONCLUSIONUltrasound measurements and maternal serum PlGF concentration at diagnosis of severe, early-onset FGR predicted pregnancy outcomes of importance to patients and clinicians.TRIAL REGISTRATIONClinicalTrials.gov NCT02097667.FUNDINGThe European Union, Rosetrees Trust, Mitchell Charitable Trust.

Geometric Reliability of Super-Resolution Reconstructed Images from Clinical Fetal MRI in the Second Trimester

Fetal Magnetic Resonance Imaging (MRI) is an important noninvasive diagnostic tool to characterize the central nervous system (CNS) development, significantly contributing to pregnancy management. In clinical practice, fetal MRI of the brain includes the acquisition of fast anatomical sequences over different planes on which several biometric measurements are manually extracted. Recently, modern toolkits use the acquired two-dimensional (2D) images to reconstruct a Super-Resolution (SR) isotropic volume of the brain, enabling three-dimensional (3D) analysis of the fetal CNS.We analyzed 17 fetal MR exams performed in the second trimester, including orthogonal T2-weighted (T2w) Turbo Spin Echo (TSE) and balanced Fast Field Echo (b-FFE) sequences. For each subject and type of sequence, three distinct high-resolution volumes were reconstructed via NiftyMIC, MIALSRTK, and SVRTK toolkits. Fifteen biometric measurements were assessed both on the acquired 2D images and SR reconstructed volumes, and compared using Passing-Bablok regression, Bland-Altman plot analysis, and statistical tests.Results indicate that NiftyMIC and MIALSRTK provide reliable SR reconstructed volumes, suitable for biometric assessments. NiftyMIC also improves the operator intraclass correlation coefficient on the quantitative biometric measures with respect to the acquired 2D images. In addition, TSE sequences lead to more robust fetal brain reconstructions against intensity artifacts compared to b-FFE sequences, despite the latter exhibiting more defined anatomical details.Our findings strengthen the adoption of automatic toolkits for fetal brain reconstructions to perform biometry evaluations of fetal brain development over common clinical MR at an early pregnancy stage.

Review of deep learning and artificial intelligence models in fetal brain magnetic resonance imaging

Central nervous system abnormalities in fetuses are fairly common, happening in 0.1% to 0.2% of live births and in 3% to 6% of stillbirths. So initial detection and categorization of fetal Brain abnormalities are critical. Manually detecting and segmenting fetal brain magnetic resonance imaging (MRI) could be time-consuming, and susceptible to interpreter experience. Artificial intelligence (AI) algorithms and machine learning approaches have a high potential for assisting in the early detection of these problems, improving the diagnosis process and follow-up procedures. The use of AI and machine learning techniques in fetal brain MRI was the subject of this narrative review paper. Using AI, anatomic fetal brain MRI processing has investigated models to predict specific landmarks and segmentation automatically. All gestation age weeks (17-38 wk) and different AI models (mainly Convolutional Neural Network and U-Net) have been used. Some models' accuracy achieved 95% and more. AI could help preprocess and post-process fetal images and reconstruct images. Also, AI can be used for gestational age prediction (with one-week accuracy), fetal brain extraction, fetal brain segmentation, and placenta detection. Some fetal brain linear measurements, such as Cerebral and Bone Biparietal Diameter, have been suggested. Classification of brain pathology was studied using diagonal quadratic discriminates analysis, K-nearest neighbor, random forest, naive Bayes, and radial basis function neural network classifiers. Deep learning methods will become more powerful as more large-scale, labeled datasets become available. Having shared fetal brain MRI datasets is crucial because there aren not many fetal brain pictures available. Also, physicians should be aware of AI's function in fetal brain MRI, particularly neuroradiologists, general radiologists, and perinatologists.

Non-invasive fetal electrocardiography, electrohysterography and speckle-tracking echocardiography in the second trimester: study protocol of a longitudinal prospective cohort study (BEATS-study)

Background

Worldwide, hypertensive disorders of pregnancy (HDP), fetal growth restriction (FGR) and preterm birth remain the leading causes of maternal and fetal pregnancy-related mortality and (long-term) morbidity. Fetal cardiac deformation changes can be the first sign of placental dysfunction, which is associated with HDP, FGR and preterm birth. In addition, preterm birth is likely associated with changes in electrical activity across the uterine muscle. Therefore, fetal cardiac function and uterine activity can be used for the early detection of these complications in pregnancy. Fetal cardiac function and uterine activity can be assessed by two-dimensional speckle-tracking echocardiography (2D-STE), non-invasive fetal electrocardiography (NI-fECG), and electrohysterography (EHG). This study aims to generate reference values for 2D-STE, NI-fECG and EHG parameters during the second trimester of pregnancy and to investigate the diagnostic potential of these parameters in the early detection of HDP, FGR and preterm birth.

Methods

In this longitudinal prospective cohort study, eligible women will be recruited from a tertiary care hospital and a primary midwifery practice. In total, 594 initially healthy pregnant women with an uncomplicated singleton pregnancy will be included. Recordings of NI-fECG and EHG will be made weekly from 22 until 28 weeks of gestation and 2D-STE measurements will be performed 4-weekly at 16, 20, 24 and 28 weeks gestational age. Retrospectively, pregnancies complicated with pregnancy-related diseases will be excluded from the cohort. Reference values for 2D-STE, NI-fECG and EHG parameters will be assessed in uncomplicated pregnancies. After, 2D-STE, NI-fCG and EHG parameters measured during gestation in complicated pregnancies will be compared with these reference values.

Discussion

This will be the a large prospective study investigating new technologies that could potentially have a high impact on antepartum fetal monitoring.

Trial registration

Registered on 26 March 2020 in the Dutch Trial Register (NL8769) via https://www.trialregister.nl/trials and registered on 21 October 2020 to the Central Committee on Research Involving Human Subjects (NL73607.015.20) via https://www.toetsingonline.nl/to/ccmo_search.nsf/Searchform?OpenForm.

Automatic linear measurements of the fetal brain on MRI with deep neural networks

PURPOSE

Timely, accurate and reliable assessment of fetal brain development is essential to reduce short and long-term risks to fetus and mother. Fetal MRI is increasingly used for fetal brain assessment. Three key biometric linear measurements important for fetal brain evaluation are cerebral biparietal diameter (CBD), bone biparietal diameter (BBD), and trans-cerebellum diameter (TCD), obtained manually by expert radiologists on reference slices, which is time consuming and prone to human error. The aim of this study was to develop a fully automatic method computing the CBD, BBD and TCD measurements from fetal brain MRI.

METHODS

The input is fetal brain MRI volumes which may include the fetal body and the mother's abdomen. The outputs are the measurement values and reference slices on which the measurements were computed. The method, which follows the manual measurements principle, consists of five stages: (1) computation of a region of interest that includes the fetal brain with an anisotropic 3D U-Net classifier; (2) reference slice selection with a convolutional neural network; (3) slice-wise fetal brain structures segmentation with a multi-class U-Net classifier; (4) computation of the fetal brain midsagittal line and fetal brain orientation, and; (5) computation of the measurements.

RESULTS

Experimental results on 214 volumes for CBD, BBD and TCD measurements yielded a mean [Formula: see text] difference of 1.55 mm, 1.45 mm and 1.23 mm, respectively, and a Bland-Altman 95% confidence interval ([Formula: see text] of 3.92 mm, 3.98 mm and 2.25 mm, respectively. These results are similar to the manual inter-observer variability, and are consistent across gestational ages and brain conditions.

CONCLUSIONS

The proposed automatic method for computing biometric linear measurements of the fetal brain from MR imaging achieves human-level performance. It has the potential of being a useful method for the assessment of fetal brain biometry in normal and pathological cases, and of improving routine clinical practice.