Fetal Imaging Research Articles

Role of palliative care in fetal neurological consultations: Guiding through uncertainty and hope.

Fetal neurology is a rapidly evolving and expanding field. Discussions about diagnosis, prognosis, treatment options, and goals of care often begin in the antenatal period. However, there are inherent challenges to fetal counseling of neurological diagnoses due to limitations of fetal imaging, prognostic uncertainty, and variability in neurodevelopmental outcomes. In the midst of uncertainty, families are challenged with preparing a care plan for their baby while simultaneously experiencing profound grief. The paradigms of perinatal palliative care can assist with the grieving process and help frame diagnostic testing and complex decision-making within the context of a family's spiritual, cultural, and social belief system. This ultimately leads to a shared decision-making process and value driven medical care. While perinatal palliative care programs have expanded, many families faced with such diagnoses never meet with a palliative care team prior to delivery. Moreover, there is significant variability in the availability of palliative care services throughout the country. Using an illustrative vignette of a patient with a prenatally diagnosed encephalocele, this review aims to provide a basic framework of perinatal palliative care for fetal neurology diagnoses that emphasizes 1) importance of clear, consistent, and transparent communication among all subspecialists and families, 2) creation of a palliative care birth plan, 3) importance of consistent care providers and longitudinal points of contact prenatally and post-delivery, 4) close communication between the prenatal and post-natal providers to allow for optimal continuity of care, and 5) recognize that information, care plans, and goals of care often evolve over time.

Longitudinal Study to Assess the Reliability and Predictive Validity of Ultrasound Measurements in Tracking Fetal Growth and Development Throughout Pregnancy

The utilization of ultrasound in obstetrics is extremely common due to its accurate fetal imaging capabilities. By early identifying anomalies such intrauterine growth restrictions and macrosomia, ultrasonography scanning during pregnancy primarily aims to reduce the risk of obstetric problems. Fetal weight is currently estimated using morphometric formulas. They employ fundamental biometric variables. Hadlock's formula, which is used for estimation of fetal weight, has 20 percent error rate, though. Due to this particular cause, the researchers from all around world had already searching for the additional sonographic characteristics having a stronger predictive value that correlate with fetal weight. According to recent scientific studies, assessing fetal weight can benefit from using novel parameters of sonograph such measurements of the thickness of soft tissue. The fetus's body can be measured in a number of locations, including upper arm, the thigh, abdomen, and the subscapular region. Diverse measurements have varying degrees of connection with some other anthropometric & sonographic factors, including body mass & gestational age. Numerous research using novel formulas for calculating fetal weight have been produced in response to the reports. For measuring fetal weight, measurements other than those including soft tissue, including such those lean and adipose tissue or utilising 3D ultrasonography are acquired. For the purpose of sonographic pregnancy assessment, ultrasound examination of the thicknesses of subcutaneous tissue in the several body regions might evidence to become reliable indicator of the fetal weight. Keywords: Pregnancy, postpartum hypoglycaemia, foetus, Intra-uterine, pregnancy ultrasound

Cardiac function evaluated by two-dimensional speckle tracking imaging in fetuses with congenital heart disease of ventricular afterload increase

Aims To study myocardial deformation in fetuses with ventricular afterload increase compared with gestational age-matched controls using speckle tracking echocardiography. Methods and results Eighty-nine fetuses were retrospectively selected from the pregnancy screen by echocardiography. There are 41 fetuses with gestational age-matched normal heart served as the control group, 25 fetuses with congenital heart disease (CHD) leading to left ventricular (LV) afterload increase as group LVA and 23 fetuses with CHD leading to right ventricular(RV) afterload increases as group RVA. LV and RV fractional shortening (FS) were measured by conventional methods. The longitudinal strain (LS) and strain rate (LSr) were analyzed by EchoPac software. Group LVA and RVA compared with control group, the LV FS was no significant difference, but LS and LSr values of LV were lower in fetuses with LVA compared to the control group (LS:−15.97(−12.50,−22.52)vs −27.53(−24.33,−29.16) %, p < .01; systolic strain rate (SRs):-1.34(−1.12,−2.16) vs −2.55(−2.28,−2.92) 1/sec, p < .01; early diastolic strain rate (SRe):1.70 ± 0.57 vs 2.46 ± 0.61 1/sec, p < 0.01; late diastolic strain rate (SRa):1.62 ± 0.82 vs 2.39 ± 0.81 1/sec, p < .01). LS and LSr values of LV or RV were lower in fetuses with RVA compared to the control group (LV: LS:−21.52 ± 6.68 vs −26.79 ± 3.22%, p < .01; SRs:-2.11 ± 0.78 vs −2.56 ± 0.43 1/sec; p = .02; RV: LS:−17.64 ± 7.58 vs −26.38 ± 3.97%, p < .01; SRs:−1.62 ± 0.67 vs −2.37 ± 0.44 1/sec; p < .01). Conclusion The results of this study showed that the ventricular LS, LSr, SRs, SRe, SRa values were lower in fetuses with LV or RV afterload increasing CHD estimated by speckle tracking imaging but LV and RV FS were normal,which indicated the strain imaging is feasible in evaluating cardiac function of fetus, and may be more sensitive.

Possibilities of high-field magnetic resonance imaging (3 T) in fetal visualization using meta device

Background. Fetal and extra fetal diagnostics is currently performed using 3 Tesla magnetic-resonance imaging scanners. Examination is more informative during the third trimester of pregnancy, when fetal movements are less significant. 3 Tesla MR-images demonstrate better characteristics than 1,5 Tesla ones, however, there is a risk of heating the patient during scanning, which is especially dangerous for pregnant women.Objective. The aim of the study is to improve fetal and extrafetal structures visualization by means of developed metamaterial pad (metadevice).Design and methods. In the study, a metadevice was considered to improve fetal and extrafetal imaging in a field with magnetic induction of 3 T. 12 pregnant women between 29 and 39 weeks gestation (33,4 ± 4,8 weeks) were examined, standart magnetic resonance images of Single Shot Turbo (SST)/Fast Spin Echo(FSE)) were obtained. Standart abdomen coil was used to receive examination data. Metadevice and the coil were placed on the center of the examined area. The images were evaluated by radiologists on a 5-point Likert scale.Results of metadevice testing showed diagnostic quality improvement, increase in radio-frequency magnetic field homogeneity, decreased SAR value and reduction in body heating effect during MR-scanning.Conclusion. Metadevice-assisted MRI can lower heating risks, reduce dielectric artifacts and improve imaging quality of the fetus and extrafetal structures.

Neurosonography Compared to Fetal Magnetic Resonance Imaging: A Systematic Review and Meta-Analysis on the Diagnostic Agreement and Added Value

Objective: The aim of this systematic review and meta-analysis was to compare the additional value of fetal neurosonography (NS) and fetal magnetic resonance imaging (MRI) in fetuses at risk for brain anomalies. Materials and Methods: This systematic review article was conducted based on PRISMA guidelines. On January 30, 2021, a systematic search was conducted using Embase, Medline, Web of Science, Scopus, and the Cochrane Library, with no language restrictions. The purpose was to identify all articles comparing NS with fetal MRI, in cases of suspected brain abnormalities. The statistical analysis was performed using STATA-15 and Meta-Disk 1.4 software. Results: Eight articles were included in this review. The overall agreement rate between NS and MRI was 81%. Data from NS changed the management of 6% of patients, and MRI data added data to the results of NS, in 9% of cases. In cases where the fetal MRI was normal, the added value of the postnatal MRI was 4%. Conclusion: When brain abnormalities are suspected, based on NS, MRI can play a significant role in the diagnostic path by clarifying the findings and significantly increasing the detection of abnormalities, especially when abnormalities are suspected in the posterior, midline, or cortical areas of the brain.

Classification of normal and abnormal fetal heart ultrasound images and identification of ventricular septal defects based on deep learning.

Congenital heart defects (CHDs) are the most common birth defects. Recently, artificial intelligence (AI) was used to assist in CHD diagnosis. No comparison has been made among the various types of algorithms that can assist in the prenatal diagnosis. Normal and abnormal fetal ultrasound heart images, including five standard views, were collected according to the International Society of Ultrasound in Obstetrics and Gynecology (ISUOG) Practice guidelines. You Only Look Once version 5 (YOLOv5) models were trained and tested. An excellent model was screened out after comparing YOLOv5 with other classic detection methods. On the training set, YOLOv5n performed slightly better than the others. On the validation set, YOLOv5n attained the highest overall accuracy (90.67 %). On the CHD test set, YOLOv5n, which only needed 0.007 s to recognize each image, had the highest overall accuracy (82.93 %), and YOLOv5l achieved the best accuracy on the abnormal dataset (71.93 %). On the VSD test set, YOLOv5l had the best performance, with a 92.79 % overall accuracy rate and 92.59 % accuracy on the abnormal dataset. The YOLOv5 models achieved better performance than the Fast region-based convolutional neural network (RCNN) & ResNet50 model and the Fast RCNN & MobileNetv2 model on the CHD test set (p<0.05) and VSD test set (p<0.01). YOLOv5 models are able to accurately distinguish normal and abnormal fetal heart ultrasound images, especially with respect to the identification of VSD, which have the potential to assist ultrasound in prenatal diagnosis.

RETRACTED ARTICLE: Down syndrome markers classification via dense neural network in ultrasound foetal image

Down syndrome is a genetically born disorder among infants that occurs during the development of the foetus. Trisomy 21, a chromosome imbalance disorder is a leading cause of the down syndrome. Numerous machine learning (ML) models have been used to identify down syndrome in ultrasound images of foetuses, but the development of deep learning, offers an enormous advantage over ML models in accuracy. However, the existing models have focused on down syndrome as a nasal bone (NB) length or nuchal translucency (NT). In this paper, a novel automatic dense convolution neural network (DConN) is proposed to isolate and measure the down syndrome marker particularly NB length and NT. It is necessary to extract texture features precisely from ultrasound images to classify them accurately. Initially, the test image is processed using an anisotropic diffusion filter to remove the noise. The pre-processed foetal images are subjected to region of interest extraction to isolate the Down syndrome makers from the ultrasound image. The proposed DConN is used to classify the normal and abnormal foetal based on NT and NB length of the foetal in US images. The performance metrics namely sensitivity, accuracy, specificity, F1 score, and precision are considered for validating the effectiveness of the proposed model. From the experimental the proposed DconN achieves the overall accuracy of 99.01%. The proposed method improves the overall accuracy of 3.9%, 1.6% and 0.41% better than cascaded ML, SIFT + GRNN and Modified AdaBoost, respectively.

The Left Outflow Tract in Fetal Cardiac Screening Examination: Introduction of Quality Criteria Is Not Always Associated With an Improvement of Practice When Supervised by Humans.

Since 2016, the French CNEOF included the left ventricular outflow tract (LVOT) in the second and third trimester of pregnancy in addition to the four-chamber view and the parasagittal view of the right outflow tract. The objective of this study was to define quality criteria for fetal LVOT assessment and to perform a human audit of past and current practices, before and after the implementation of those quality criteria at a large scale. Seven quality criteria were investigated and rated from 0 to 1 during three periods of interest. Files were randomly selected from three centers, and average total and specific scores were calculated. LVOT pictures were present in more than 94.3% of reports. The average quality score was 5.49/7 (95% confidence interval [CI]: 5.36-5.62), 5.91/7 (95% CI: 5.80-6.03), and 5.70/7 (95% CI: 5.58-5.82) for the three centers in the three periods of interest. There was no significant difference following the introduction of the quality criteria, 2017 versus 2020, P = .054. Fetal LVOT images were present in most of ultrasound reports but the introduction of the proposed quality criteria under human supervision seems not associated with a significant change in practice.

Does 3D imaging of the fetal spine improve confidence in interpreting images in the second trimester?

AbstractIntroductionThis study investigated the addition of 3D ultrasound imaging to 2D ultrasound imaging when assessing the fetal spine in the second trimester in relation to: the diagnostic confidence of image assessors in interpretation, sonographer perceptions of the challenges in acquiring 3D images, and the additional time required to acquire 3D images.MethodsSix image assessors rated their diagnostic confidence when assessing 2D and 3D images of the fetal spine images acquired from second trimester morphology scans. Sonographer perceptions were investigated using a questionnaire assigned to eight sonographers. The mean time required to take 3D images of the fetal spine was retrospectively calculated using the time stamps from the ultrasound images of 100 second trimester morphology scans.ResultsCommon reasons for assessor's lack of confidence in reporting were poor quality or insufficient images of the upper spine (cervical/thoracic), the scapulae and/or the ribs. Diagnostic confidence of image assessors increased significantly (&lt;.001) when 3D imaging was added to 2D imaging. All sonographers who completed the questionnaire stated that they found 3D ultrasound of the fetal spine useful in addition to 2D. 87.5% of these sonographers sometimes found 3D ultrasound challenging, mostly due to fetal position, or maternal obesity. The mean additional time required to perform 3D ultrasound to assess the fetal spine was 2 minutes and 19 seconds.ConclusionAdding 3D ultrasound of the fetal spine to a 2D second trimester obstetric morphology scan increased the diagnostic confidence of image assessors with only a small additional time requirement.

Transuterine Ultrasound-Guided Fetal Embolization of Vein of Galen Malformation, Eliminating Postnatal Pathophysiology.

Transuterine Ultrasound-Guided Fetal Embolization of Vein of Galen Malformation, Eliminating Postnatal Pathophysiology.

Fetal MRI at 3 T: Principles to Optimize Success.

Fetal MRI has emerged as a cornerstone of prenatal imaging, helping to establish the correct diagnosis in pregnancies affected by congenital anomalies. In the past decade, 3 T imaging was introduced as an alternative to increase the signal-to-noise ratio (SNR) of the pulse sequences and improve anatomic detail. However, imaging at a higher field strength is not without challenges. Many artifacts that are barely appreciable at 1.5 T are amplified at 3 T. A systematic approach to imaging at 3 T that incorporates appropriate patient positioning, a thoughtful protocol design, and sequence optimization minimizes the impact of these artifacts and allows radiologists to reap the benefits of the increased SNR. The sequences used are the same at both field strengths and include single-shot T2-weighted, balanced steady-state free-precession, three-dimensional T1-weighted spoiled gradient-echo, and echo-planar imaging. Synergistic use of these acquisitions to sample various tissue contrasts and in various planes provides valuable information about fetal anatomy and pathologic conditions. In the authors' experience, fetal imaging at 3 T outperforms imaging at 1.5 T for most indications when performed under optimal circumstances. The authors condense the cumulative experience of fetal imaging specialists and MRI technologists who practice at a large referral center into a guideline covering all major aspects of fetal MRI at 3 T, from patient preparation to image interpretation. © RSNA, 2023 Quiz questions for this article are available in the supplemental material.

Normal reference values for magnetic resonance imaging measurements of the fetal internal jugular veins in middle and late pregnancy

BackgroundAt present, there is a lack of normal magnetic resonance imaging (MRI) morphometric reference values for fetal internal jugular veins during middle and late pregnancy.ObjectiveWe used MRI to assess the morphology and cross-sectional area of the internal jugular veins of fetuses during middle and late pregnancy and to explore the clinical value of these parameters.Materials and methodsThe MRI images of 126 fetuses in middle and late pregnancy were retrospectively analysed to determine the optimal sequence for imaging the internal jugular veins. Morphological observation of the fetal internal jugular veins in each gestational week was carried out, lumen cross-sectional area was measured and the relationship between these data and gestational age was analysed.ResultsThe balanced steady-state free precession sequence was superior to other MRI sequences used for fetal imaging. The cross section of fetal internal jugular veins was predominantly circular in both the middle and late stages of pregnancy, however the prevalence of an oval cross section was significantly higher in the late gestational age group. The cross-sectional area of the lumen of the fetal internal jugular veins increased with increasing gestational age. Fetal jugular vein asymmetry was common, with the right jugular vein being dominant in the high gestational age group.ConclusionWe provide normal reference values for fetal internal jugular veins measured by MRI. These values may form the basis for clinical assessment of abnormal dilation or stenosis.

The potential of 1.5 T magnetic resonance imaging for the evaluation of fetal anomalies of the great vessels.

To determine the efficacy of 1.5 T magnetic resonance imaging (MRI) for the diagnosis of anomalies of the fetal great arteries with comparison to fetal ultrasound, and to compare image quality between 1.5 T and 3.0 T MRI in fetal imaging of the great arteries. We compared the results of postnatal exam or surgery and evaluated the application value of prenatal 1.5 T MRI in the assessment of fetal great-vessel anomalies. To further determine the diagnostic potential of 1.5 T MRI, 23 pregnant women with suspected fetal cardiovascular abnormalities who had undergone ultrasound and 3.0 T MRI were enrolled and compared, respectively. Prenatal MRI was superior to ultrasound in demonstrating aortic arch and branch abnormalities (sensitivity, 92.86% vs. 83.33%; specificity, 66.67% vs. 20%). The mean quality ratings for fetal MRI at 1.5 T was higher than 3.0 T (P < 0.001). Other than the fast scan speed afforded by 3.0 T MRI, the signal noise ratio (SNR) of 1.5 T MRI were higher than those of 3.0 T MRI; however, the difference in contrast to noise ratio (CNR) between the two imaging modalities was not statistically significant. 1.5 T MRI can achieve an overall assessment of fetal great-vessel anomalies, especially aortic arch and branch abnormalities. Therefore, 1.5 T MRI can be considered a supplementary imaging modality for the prenatal assessment of extracardiac great vessels malformations.

The nnU-Net based method for automatic segmenting fetal brain tissues.

The magnetic resonance (MR) images of fetuses make it possible for doctors to detect out pathological fetal brains in early stages. Brain tissue segmentation is prerequisite for making brain morphology and volume analyses. nnU-Net is an automatic segmentation method based on deep learning. It can adaptively configure itself, so as to adapt to a specific task via preprocessing, network architecture, training, and post-processing. Therefore, we adapt nnU-Net to segment seven types of fetal brain tissues, including external cerebrospinal fluid, gray matter, white matter, ventricle, cerebellum, deep gray matter, and brainstem. With regard to the characteristics of the FeTA 2021 data, some adjustments are made to the original nnU-Net, so that it can segment seven types of fetal brain tissues precisely as far as possible. The average segmentation results on FeTA 2021 training data demonstrate that our advanced nnU-Net is superior to the peers including SegNet, CoTr, AC U-Net and ResUnet. Its average segmentation results are 0.842, 11.759 and 0.957 in terms of Dice, HD95 and VS criteria. Moreover, the experimental results on FeTA 2021 test data further demonstrate that our advanced nnU-Net has obtained good segmentation performance of 0.774, 14.699 and 0.875 in terms of Dice, HD95 and VS, ranked the third in FeTA 2021 challenge. Our advanced nnU-Net realized the task for segmenting the fetal brain tissues using MR images of different gestational ages, which can help doctors to make correct and seasonable diagnoses.

Poor Correlation between Fetal Tissue Doppler Imaging and Pulsed Wave Myocardial Performance Indices

Introduction: Both tissue Doppler imaging (TDI) and pulsed wave Doppler (PWD) Myocardial Performance Indices (MPIs) have been proposed as tools for functional fetal cardiology. We wished to determine if there was any correlation between TDI-MPI and PWD-MPI. Methods: A cohort of uncomplicated women with morphologically normal singleton fetuses between 22 and 39 weeks of gestation was recruited. A single sonologist acquired Doppler waveforms for evaluation of both left and right TDI-MPI and PWD-MPI. The PWD-MPI values were calculated using a previously published algorithm and the TDI-MPI time intervals were measured manually by a single operator. Results: Achievability and repeatability were high for both modalities. TDI produced significantly lower right MPI values yet significantly higher left MPI values, potentially reflecting their evaluation of physiologically different events, blood flow versus myocardial contraction. Conclusion: This study demonstrates that MPIs measured from PWD and TDI have a weak correlation and cannot be used interchangeably, even with the exclusion of suboptimal TDI-MPI scans from the analysis. Given the lack of correlation between the two methods, the high variation in TDI waveform, and the lack of unified approach to TDI analysis, we feel further research is needed before adoption of this technique.

Deep learning model for prenatal congenital heart disease (CHD) screening generalizes to the community setting and outperforms clinical detection.

Congenital heart defects (CHD) are still missed despite nearly universal prenatal ultrasound screening programs, which may result in severe morbidity or even death. Deep machine learning (DL) can automate image recognition from ultrasound. The aim of this study was to apply a previously developed DL model trained on images from a tertiary center, to fetal ultrasound images obtained during the second-trimester standard anomaly scan in a low-risk population. All pregnancies with isolated severe CHD in the Northwestern region of the Netherlands between 2015 and 2016 with available stored images were evaluated, as well as a sample of normal fetuses' examinations from the same region. We compared initial clinical diagnostic accuracy (made in real time), model accuracy, and performance of blinded human experts with access only to the stored images (like the model). We analyzed performance by study characteristics such as duration, quality (independently scored by study investigators), number of stored images, and availability of screening views. A total of 42 normal fetuses and 66 cases of isolated CHD at birth were analyzed. Of the abnormal cases, 31 were missed and 35 were detected at the time of the clinical anatomy scan (sensitivity 53 percent). Model sensitivity and specificity was 91 and 93 percent, respectively. Blinded human experts (n=3) achieved sensitivity and specificity of 55±10 percent (range 47-67 percent) and 71±13 percent (range 57-83 percent), respectively. There was a statistically significant difference in model correctness by expert-grader quality score (p=0.04). Abnormal cases included 19 lesions the model had not encountered in its training; the model's performance (15/19 correct) was not statistically significantly different on previously encountered vs. never before seen lesions (p=0.07). A previously trained DL algorithm out-performed human experts in detecting CHD in a cohort in which over 50 percent of CHD cases were initially missed clinically. Notably, the DL algorithm performed well on community-acquired images in a low-risk population, including lesions it had not been previously exposed to. Furthermore, when both the model and blinded human experts had access to stored images alone, the model outperformed expert humans. Together, these findings support the proposition that use of DL models can improve prenatal detection of CHD.

Voxel-based morphometric magnetic resonance imaging evaluation of small head fetus: A comparative study with normal developmental fetus.

To explore the application value of voxel-based morphometric (VBM) in prenatal diagnosis of microcephaly. A retrospective study of magnetic resonance imaging of fetuses with microcephaly was performed using a single-shot fast spin echo sequence; semiautomatic segmentation of grey matter (GM), white matter (WM), and cerebrospinal fluid (CSF); calculation of their volumes; and VBM analysis of their GM. Two independent samples t-test was used to statistically analyse the fetal GM volume in the microcephaly and normal control groups. Total intracranial volume (TIV), GM volume, WM volume, and CSF volume were linearly regressed against gestational age and compared between the two groups. In the fetus with microcephaly, GM volume of frontal lobe, temporal lobe, cuneus, anterior central gyrus, and posterior central gyrus decreased significantly (P < 0.001, corrected by family-wise error at mass level). The GM volume of microcephaly was significantly lower than that of the control group (except for 28 weeks of gestation) (P < 0.05). TIV, GM volume, WM volume, and CSF volume were all positively correlated with gestational age, and the curves in the microcephaly group were all lower than those in the control group. Compared with the normal control group, the GM volume of microcephaly fetuses decreased, and there were significant differences in many brain regions through VBM analysis.

Application of Automatic Segmentation on Super-Resolution Reconstruction MR Images of the Abnormal Fetal Brain.

Fetal brain MR imaging is clinically used to characterize fetal brain abnormalities. Recently, algorithms have been proposed to reconstruct high-resolution 3D fetal brain volumes from 2D slices. By means of these reconstructions, convolutional neural networks have been developed for automatic image segmentation to avoid labor-intensive manual annotations, usually trained on data of normal fetal brains. Herein, we tested the performance of an algorithm specifically developed for segmentation of abnormal fetal brains. This was a single-center retrospective study on MR images of 16 fetuses with severe CNS anomalies (gestation, 21-39 weeks). T2-weighted 2D slices were converted to 3D volumes using a super-resolution reconstruction algorithm. The acquired volumetric data were then processed by a novel convolutional neural network to perform segmentations of white matter and the ventricular system and cerebellum. These were compared with manual segmentation using the Dice coefficient, Hausdorff distance (95th percentile), and volume difference. Using interquartile ranges, we identified outliers of these metrics and further analyzed them in detail. The mean Dice coefficient was 96.2%, 93.7%, and 94.7% for white matter and the ventricular system and cerebellum, respectively. The Hausdorff distance was 1.1, 2.3, and 1.6 mm, respectively. The volume difference was 1.6, 1.4, and 0.3 mL, respectively. Of the 126 measurements, there were 16 outliers among 5 fetuses, discussed on a case-by-case basis. Our novel segmentation algorithm obtained excellent results on MR images of fetuses with severe brain abnormalities. Analysis of the outliers shows the need to include pathologies underrepresented in the current data set. Quality control to prevent occasional errors is still needed.

Deep Learning-Based Fetal Development Ultrasound Image Segmentation and Registration

Deep Learning-Based Fetal Development Ultrasound Image Segmentation and Registration

Effects of Fetal Images Produced in Virtual Reality on Maternal-Fetal Attachment: Randomized Controlled Trial

Maternal-fetal attachment (MFA) has been reported to be associated with the postpartum mother-infant relationship. Seeing the fetus through ultrasound might influence MFA, and the effect could be increased by more realistic images, such as those generated in virtual reality (VR). The aim was to determine the effect of fetal images generated in VR on MFA and depressive symptoms through a prenatal-coaching mobile app. This 2-arm parallel randomized controlled trial involved a total of 80 pregnant women. Eligible women were randomly assigned to either a mobile app-only group (n=40) or an app plus VR group (n=40). The VR group experienced their own baby's images generated in VR based on images obtained from fetal ultrasonography. The prenatal-coaching mobile app recommended health behavior for the pregnant women according to gestational age, provided feedback on entered data for maternal weight, blood pressure, and glucose levels, and included a private diary service for fetal ultrasound images. Both groups received the same app, but the VR group also viewed fetal images produced in VR; these images were stored in the app. All participants filled out questionnaires to assess MFA, depressive symptoms, and other basic medical information. The questionnaires were filled out again after the interventions. Basic demographic data were comparable between the 2 groups. Most of the assessments showed comparable results for the 2 groups, but the mean score to assess interaction with the fetus was significantly higher for the VR group than the control group (0.4 vs 0.1, P=.004). The proportion of participants with an increased score for this category after the intervention was significantly higher in the VR group than the control group (43% vs 13%, P=.005). The feedback questionnaire revealed that scores for the degree of perception of fetal appearance all increased after the intervention in the VR group. The use of a mobile app with fetal images in VR significantly increased maternal interaction with the fetus. ClinicalTrials.gov NCT04942197; https://clinicaltrials.gov/ct2/show/NCT04942197.