Abnormal Fetal Anatomy Research Articles

Use of artificial intelligence and deep learning in fetal ultrasound imaging.

Deep learning is considered the leading artificial intelligence tool in image analysis in general. Deep-learning algorithms excel at image recognition, which makes them valuable in medical imaging. Obstetric ultrasound has become the gold standard imaging modality for detection and diagnosis of fetal malformations. However, ultrasound relies heavily on the operator's experience, making it unreliable in inexperienced hands. Several studies have proposed the use of deep-learning models as a tool to support sonographers, in an attempt to overcome these problems inherent to ultrasound. Deep learning has many clinical applications in the field of fetal imaging, including identification of normal and abnormal fetal anatomy and measurement of fetal biometry. In this Review, we provide a comprehensive explanation of the fundamentals of deep learning in fetal imaging, with particular focus on its clinical applicability. © 2022 International Society of Ultrasound in Obstetrics and Gynecology.

Applicability of a semiautomated volumetric approach (5D CNS+™) for detailed antenatal reconstruction of abnormal fetal CNS anatomy

BackgroundThe aim of this study was to evaluate the accuracy and reliability of a semiautomated volumetric approach (5D CNS+™) when examining fetuses with an apparent abnormal anatomy of the central nervous system (CNS).MethodsStored 3D volumes extracted from a cohort of > 1.400 consecutive 2nd and 3rd trimester pregnancies (range 15–36 gestational weeks) were analyzed using the semiautomatic software tool 5D CNS+™, enabling detailed reconstruction of nine diagnostic planes of the fetal brain. All 3D data sets were examined and judged for plane accuracy, the need for manual adjustment, and fetal CNS anomalies affecting successful plane reconstruction.ResultsBased on our data of 91 fetuses with structural cerebral anomalies, we were able to reveal details of a wide range of CNS anomalies with application of the 5D CNS+™ technique. The corresponding anatomical features and consecutive changes of neighboring structures could be clearly demonstrated. Thus, a profound assessment of the entire altered CNS anatomy could be achieved in nearly all cases. The comparison with matched controls showed a significant difference in volume acquisition (p < 0.001) and in need for manual adjustment (p < 0.001) but not in the drop-out rates (p = 0.677) of both groups.Conclusion5D CNS+™ is applicable in the majority of cases with brain lesions and constitutes a reliable tool even if the integrity of the fetal CNS is compromised by structural anomalies. Using volume data that were acquired in identical cutting sections needed for conventional biometry allows for detailed anatomic surveys grossly independent of the examiner’s experience.

3D black blood cardiovascular magnetic resonance atlases of congenital aortic arch anomalies and the normal fetal heart: application to automated multi-label segmentation

BackgroundImage-domain motion correction of black-blood contrast T2-weighted fetal cardiovascular magnetic resonance imaging (CMR) using slice-to-volume registration (SVR) provides high-resolution three-dimensional (3D) images of the fetal heart providing excellent 3D visualisation of vascular anomalies [1]. However, 3D segmentation of these datasets, important for both clinical reporting and the application of advanced analysis techniques is currently a time-consuming process requiring manual input with potential for inter-user variability.MethodsIn this work, we present novel 3D fetal CMR population-averaged atlases of normal and abnormal fetal cardiovascular anatomy. The atlases are created using motion-corrected 3D reconstructed volumes of 86 third trimester fetuses (gestational age range 29-34 weeks) including: 28 healthy controls, 20 cases with postnatally confirmed neonatal coarctation of the aorta (CoA) and 38 vascular rings (21 right aortic arch (RAA), 17 double aortic arch (DAA)). We used only high image quality datasets with isolated anomalies and without any other deviations in the cardiovascular anatomy.In addition, we implemented and evaluated atlas-guided registration and deep learning (UNETR) methods for automated 3D multi-label segmentation of fetal cardiac vessels. We used images from CoA, RAA and DAA cohorts including: 42 cases for training (14 from each cohort), 3 for validation and 6 for testing. In addition, the potential limitations of the network were investigated on unseen datasets including 3 early gestational age (22 weeks) and 3 low SNR cases.ResultsWe created four atlases representing the average anatomy of the normal fetal heart, postnatally confirmed neonatal CoA, RAA and DAA. Visual inspection was undertaken to verify expected anatomy per subgroup. The results of the multi-label cardiac vessel UNETR segmentation showed 100% per-vessel detection rate for both normal and abnormal aortic arch anatomy.ConclusionsThis work introduces the first set of 3D black-blood T2-weighted CMR atlases of normal and abnormal fetal cardiovascular anatomy including detailed segmentation of the major cardiovascular structures. Additionally, we demonstrated the general feasibility of using deep learning for multi-label vessel segmentation of 3D fetal CMR images.

Three-Dimensional 3D Ultrasound and Doppler Angiography Imaging in the Prenatal Assessment on Normal and Abnormal Fetal Cardiac Anatomy

Three-Dimensional 3D Ultrasound and Doppler Angiography Imaging in the Prenatal Assessment on Normal and Abnormal Fetal Cardiac Anatomy

Brain views that benefit from three-dimensional ultrasound.

Fetal central nervous system malformations are among the most common congenital anomalies. Whereas simple axial views are sufficient for basic fetal brain examination, other important views are essential for a more detailed examination, which are sometimes challenging to obtain. Three-dimensional ultrasound can be helpful in obtaining standardized and reproducible images of many difficult fetal brain views. The aim of the present review is to explore the most recent evidence on the utility and technique of three-dimensional ultrasound in the examination of the fetal brain, with particular emphasis on the brain views that benefit from three-dimensional ultrasound. The article describes the various techniques of acquisition and analyses of three-dimensional ultrasound volumes of the fetal brain and their usefulness in the assessment of normal and abnormal fetal brain anatomy. Three-dimensional ultrasound has also permitted the application of many new technologies, such as artificial intelligence and deep machine learning. Recently, thanks to high-quality three-dimensional ultrasound, fetal cortical development can be assessed quantitatively and reliably. Three dimensional ultrasound can help as a complementary tool to two-dimensional ultrasound in the assessment of the fetal brain development and malformations. In addition, it paves the way for the application of promising technologies in the evaluation of fetal brain. A video summarizing the findings of the article. The video illustrates the various approaches and techniques applied for the examination of the fetal brain using three-dimensional ultrasound. Furthermore, the advantages and future perspectives of the application of three-dimensional ultrasound in the examination of the fetal brain are discussed, http://links.lww.com/COOG/A74.

Color and power Doppler combined with Fetal Intelligent Navigation Echocardiography (FINE) to evaluate the fetal heart.

ABSTRACTObjectiveTo evaluate the performance of color and bidirectional power Doppler ultrasound combined with Fetal Intelligent Navigation Echocardiography (FINE) in examining the fetal heart.MethodsA prospective cohort study was conducted of fetuses in the second and third trimesters with a normal heart or with congenital heart disease (CHD). One or more spatiotemporal image correlation (STIC) volume datasets, combined with color or bidirectional power Doppler (S‐flow) imaging, were acquired in the apical four‐chamber view. Each successfully obtained STIC volume was evaluated by STICLoop™ to determine its appropriateness before applying the FINE method. Visualization rates for standard fetal echocardiography views using diagnostic planes and/or Virtual Intelligent Sonographer Assistance (VIS‐Assistance®) were calculated for grayscale (removal of Doppler signal), color Doppler and S‐flow Doppler. In four cases with CHD (one case each of tetralogy of Fallot, hypoplastic left heart and coarctation of the aorta, interrupted inferior vena cava with azygos vein continuation and asplenia, and coarctation of the aorta with tricuspid regurgitation and hydrops), the diagnostic potential of this new technology was presented.ResultsA total of 169 STIC volume datasets of the normal fetal heart (color Doppler, n = 78; S‐flow Doppler, n = 91) were obtained from 37 patients. Only a single STIC volume of color Doppler and/or a single volume of S‐flow Doppler per patient were analyzed using FINE. Therefore, 60 STIC volumes (color Doppler, n = 27; S‐flow Doppler, n = 33) comprised the final study group. Median gestational age at sonographic examination was 23 (interquartile range, 21–27.5) weeks. Color Doppler FINE generated nine fetal echocardiography views (grayscale) using (1) diagnostic planes in 73–100% of cases, (2) VIS‐Assistance in 100% of cases, and (3) a combination of diagnostic planes and/or VIS‐Assistance in 100% of cases. The rate of generating successfully eight fetal echocardiography views with appropriate color and S‐flow Doppler information was 89–100% and 91–100% of cases, respectively, using a combination of diagnostic planes and/or VIS‐Assistance. However, the success rate for the ninth echocardiography view (i.e. superior and inferior venae cavae) was 33% and 30% for color and S‐flow Doppler, respectively. In all four cases of CHD, color Doppler FINE demonstrated evidence of abnormal fetal cardiac anatomy and/or hemodynamic flow.ConclusionsThe FINE method applied to STIC volumes of normal fetal hearts acquired with color or bidirectional power Doppler information can generate successfully eight to nine standard fetal echocardiography views (via grayscale, color Doppler or power Doppler) in the second and third trimesters. In cases of CHD, color Doppler FINE demonstrates successfully abnormal anatomy and/or Doppler flow characteristics. Published 2017. This article is a U.S. Government work and is in the public domain in the USA. Ultrasound in Obstetrics & Gynecology published by John Wiley & Sons Ltd on behalf of the International Society of Ultrasound in Obstetrics and Gynecology.

Advantages of 3D ultrasound in the assessment of fetal abnormalities

Three-/four-dimensional (3D/4D) imaging enables a more detailed survey of the embryo and the fetus compared to two-dimensional (2D) ultrasound. The availability of several display modes and standardized examinations permits the demonstration of both the normal and abnormal fetal anatomy in controlled planes and rendered images from different angles. This allows the demonstration of even subtle fetal defects in an ideal sectional plane in a precisely rendered surface or transparent image viewed from an optimal angle. When counseling the parents, the rendered images can help them understand the severity of an existing malformation or, conversely, ensure them of the absence of any fetal abnormality. This is particularly useful in cases with an increased recurrence risk of a specific fetal malformation.

Frequency and Importance of Incomplete Screening Fetal Anatomic Sonography in Pregnancy.

To determine (1) how often routine screening fetal anatomic sonography fails to completely visualize fetal anatomy; (2) the proportion of women with incomplete ultrasound examinations who are recommended for repeat screening and then undergo repeat sonography; and (3) how often abnormal fetal anatomy is detected on repeat sonography. We conducted a retrospective cohort study at a high-volume academic obstetric ultrasound center. Participants were 16,300 women at 17 through 21 weeks' gestation with a singleton pregnancy presenting for screening anatomic sonography between January 2009 and December 2013. Main outcome measures were (1) incomplete visualization of anatomy at initial screening sonography; (2) among women with incomplete but otherwise normal initial screening ultrasound examinations, recommendation for and performance of repeat sonography; and (3) among women undergoing repeat sonography, discovery of abnormal fetal anatomy within anatomic components that were previously incompletely visualized. The mean maternal age ± SD was 30.8 ± 6.3 years, and the mean gestational age was 18.8 ± 1.0 weeks. Among 16,300 initial screening ultrasound examinations, 2157 (13.2%) had incomplete visualization of fetal anatomy. Of those women eligible for follow-up, 91.5% were recommended for repeat screening, of whom 92.8% had a subsequent examination. Of 1560 repeat screening ultrasound examinations, 8 (0.5%) showed an abnormality in the components of anatomy that were previously visualized incompletely. In this large single-center study, incomplete visualization was common in screening fetal anatomic ultrasound examinations. Recommendations for repeat imaging were nearly universal, but abnormal fetal anatomy was infrequently discovered on repeat screening.

Fetal Intelligent Navigation Echocardiography (FINE): a novel method for rapid, simple, and automatic examination of the fetal heart

To describe a novel method (Fetal Intelligent Navigation Echocardiography (FINE)) for visualization of standard fetal echocardiography views from volume datasets obtained with spatiotemporal image correlation (STIC) and application of 'intelligent navigation' technology. We developed a method to: 1) demonstrate nine cardiac diagnostic planes; and 2) spontaneously navigate the anatomy surrounding each of the nine cardiac diagnostic planes (Virtual Intelligent Sonographer Assistance (VIS-Assistance®)). The method consists of marking seven anatomical structures of the fetal heart. The following echocardiography views are then automatically generated: 1) four chamber; 2) five chamber; 3) left ventricular outflow tract; 4) short-axis view of great vessels/right ventricular outflow tract; 5) three vessels and trachea; 6) abdomen/stomach; 7) ductal arch; 8) aortic arch; and 9) superior and inferior vena cava. The FINE method was tested in a separate set of 50 STIC volumes of normal hearts (18.6-37.2 weeks of gestation), and visualization rates for fetal echocardiography views using diagnostic planes and/or VIS-Assistance® were calculated. To examine the feasibility of identifying abnormal cardiac anatomy, we tested the method in four cases with proven congenital heart defects (coarctation of aorta, tetralogy of Fallot, transposition of great vessels and pulmonary atresia with intact ventricular septum). In normal cases, the FINE method was able to generate nine fetal echocardiography views using: 1) diagnostic planes in 78-100% of cases; 2) VIS-Assistance® in 98-100% of cases; and 3) a combination of diagnostic planes and/or VIS-Assistance® in 98-100% of cases. In all four abnormal cases, the FINE method demonstrated evidence of abnormal fetal cardiac anatomy. The FINE method can be used to visualize nine standard fetal echocardiography views in normal hearts by applying 'intelligent navigation' technology to STIC volume datasets. This method can simplify examination of the fetal heart and reduce operator dependency. The observation of abnormal echocardiography views in the diagnostic planes and/or VIS-Assistance® should raise the index of suspicion for congenital heart disease.

PF.26 Prenatal Detection of Structural Cardiac Defects and Presence of Associated Anomalies: A Prospective Study of 1,244 Fetal Echocardiograms

BackgroundOur unit offers a comprehensive fetal echocardiograhy service to expectant mothers who are at increased risk of having a fetus with a cardiac defect.MethodsA prospective study from January 2007 to...

Virtual reality ultrasound imaging of the normal and abnormal fetal central nervous system

In fetal ultrasound imaging, teaching and experience are of paramount importance to improve prenatal detection rates of fetal abnormalities. Yet both aspects depend on exposure to normal and, in particular, abnormal 'specimens'. We aimed to generate a number of simple virtual reality (VR) objects of the fetal central nervous system for use as educational tools. We applied a recently proposed algorithm for the generation of fetal VR object movies to the normal and abnormal fetal brain and spine. Interactive VR object movies were generated from ultrasound volume data from normal fetuses and fetuses with typical brain or spine anomalies. Pathognomonic still images from all object movies were selected and annotated to enable recognition of these features in the object movies. Forty-six virtual reality object movies from 22 fetuses (two with normal and 20 with abnormal brains) were generated in an interactive display format (QuickTime) and key images were annotated. The resulting .mov files are available for download from the website of this journal. VR object movies can be generated from educational ultrasound volume datasets, and may prove useful for teaching and learning normal and abnormal fetal anatomy.

3D/4D Volumetry in the Second and Third Trimester of Pregnancy

ABSTRACT Purpose of the review The technological improvements have greatly progressed on three-dimensional ultrasonography. This review summarizes these technical changes and the latest advances of their use in prenatal diagnosis. Material and methods Review of the literature. Results The new technical aspects of the volumetry, improvement of different render modes, the postprocessing modalities, and innovations on volume calculations are extensively described, as well as detailed, organ based diagnosis of different malformations in the second and third trimester are summarized. Conclusion Though the traditional 2D ultrasound with high resolution provides a great diagnostic tool in detection of fetal malformations, there is no doubt that the 3D/4D technique offers a new power in prenatal diagnosis. Three-dimensional ultrasound can assist in the diagnosis of different, rare malformations because it offers a potential benefit of understanding spatial relationships of normal and abnormal fetal anatomy.

Sonographic Findings of Trisomy 18 in the Second Trimester of Pregnancy

The purpose of this study was to examine the sonographic findings in fetuses with trisomy 18 in the second trimester of pregnancy. A retrospective review of the cytogenetic laboratory databases at 6 tertiary referral centers identified all cases of trisomy 18. The prenatal sonographic studies in fetuses at 15 to 21 weeks' gestation, done before invasive testing for the karyotype, were reviewed for anatomic and biometric findings. We defined abnormal fetal biometric findings as a biometric measurement (biparietal diameter, abdominal circumference, or femur length) below the fifth percentile in the second trimester. Of 98 fetuses with trisomy 18, 95 (97%) were detected sonographically; an anomaly was found in 92 (94%). A biometric measurement below the fifth percentile was noted in 50 (51%). Cardiac (63%) and central nervous system (34%) anomalies were most frequently detected. Although choroid plexus cysts were commonly seen, no fetuses with trisomy 18 and isolated choroid plexus cysts were found. Targeted sonography identified abnormal fetal anatomy or abnormal biometric findings in 97% of fetuses with trisomy 18 in the second trimester. A biometric measurement below the fifth percentile was noted in half of the cases in the second trimester.

Sonographic Detection of Trisomy 13 in the First and Second Trimesters of Pregnancy

The purpose of this study was to examine sonographic findings in fetuses with trisomy 13. A retrospective review of the cytogenetic laboratory databases at 6 tertiary referral centers identified all cases of trisomy 13. The prenatal sonographic studies in fetuses of less than 22 weeks' gestation, done before invasive testing for karyotype, were reviewed for anatomic and biometric findings. We defined abnormal fetal biometric findings as a biometric measurement (biparietal diameter, abdominal circumference, or femur length) below the fifth percentile in the second trimester. There were 8 cases of trisomy 13 found in the first trimester and 54 cases found in the second trimester, a total of 62 in all. In the first trimester, 6 of 8 had an anomaly identified (4 with cystic hygroma). In the second trimester, 49 of 54 were identified by sonography; 45 had an anomaly, and 4 had an abnormal fetal biometric measurement without an anomaly. The 5 missed diagnoses had early gestational age (<17 weeks; n = 3) or an inadequate survey secondary to poor visualization. Overall, 22 of 54 fetuses with trisomy 13 had an abnormal biometric measurement. The most common anomalies detected in the second trimester were heart defects (n = 34), central nervous system anomalies (n = 30), facial clefts (n = 19), abnormal hands (n = 13), and genitourinary anomalies (n = 9). Targeted sonography identified abnormal fetal anatomy or abnormal biometric measurements in 95% of fetuses with trisomy 13 in the second trimester after 17 weeks' gestation. A biometric measurement below the fifth percentile was noted in nearly half of cases in the second trimester.

OC50: Use of a confidence scale in reporting normal and abnormal fetal anatomy on postmortem MRI

OC50: Use of a confidence scale in reporting normal and abnormal fetal anatomy on postmortem MRI

Tomographic Ultrasound Imaging of the Fetal Heart

In 2003 and 2004, the American College of Radiology, the American Institute of Ultrasound in Medicine, and the American College of Obstetricians and Gynecologists published guidelines for the standard ultrasound examination of the fetus. Each group recommended that the outflow tracts of the fetal heart be examined if technically feasible. One method to accomplish this task is to perform a free-hand sweep of the transducer beam directed in a transverse plane from the 4-chamber view to the fetal neck. One problem with this approach is that the examiner may not direct the beam transversely and, therefore, may not accurately identify the outflow tract anatomy. A new technology, tomographic ultrasound imaging (TUI), allows the examiner to obtain a volume data set that simultaneously displays multiple images at specific distances from the 4-chamber view. This study examined TUI technology for identifying normal and abnormal fetal cardiac anatomy with the use of either static or spatiotemporal image correlation volume data sets. The 4 views used in the screening examination of the outflow tracts of the fetal heart (4-chamber, 5-chamber, 3-vessel, and tracheal views) could be identified with the use of TUI technology in fetuses between 13 and 40 weeks' gestation. Examples of fetuses with abnormal cardiac anatomy of the outflow tracts (tetralogy of Fallot, transposition of the great vessels, and pulmonary stenosis) all showed abnormal anatomy on TUI. Tomographic ultrasound imaging technology enables the fetal examiner to evaluate the 4-chamber view and the outflow tracts in a systematic manner to identify normal and abnormal cardiac anatomy.

2D and 3D Ultrasound in the Evaluation of Normal and Abnormal Fetal Anatomy in the Second and Third Trimesters in a Level III Center

Between July 2000 and December 2003, a total number of 3,472 fetuses was evaluated by two-dimensional (2D) and three-dimensional (3D) ultrasonography. All examinations were carried out as part of a detailed level III ultrasound examination for fetal anomalies. The gestational age was between 11 and 35 weeks. A 3D endovaginal probe (5 - 7 MHz) was used for examinations between 11 and 13 weeks, and an abdominal 3D probe (5 MHz) after 13 weeks. Four different 3D image display modes were employed in visualizing fetal malformations: triplanar orthogonal display; surface display; transparent display; and the combined transparent and color display (= glass body-rendering). In 906 of the 3,472 high-risk pregnancies, fetuses with one to five fetal defects were found (mean 1.17). The total number of detected defects was 1,012, exclusive of 48 fetal heart defects. Fetal heart defects were excluded from this study since a reliable demonstration of these defects was not possible by 3D ultrasound. Comparing the 2D and 3D techniques, 3D sonography proved advantageous in 60.8 % of the defects, with the benefit derived from the exact tomographic survey using the multiplanar view in 69.9 % of these cases, from a more precise demonstration of the defect in the surface view in 25.2 %, from a distinct demonstration in the transparent view in 3.9 %, and from a precise demonstration in the combined transparent and color view in 1.0 %. In 42 of the 1,012 malformations (4.2 %), a defect was accurately identified or verified with 3D ultrasound only. 3D ultrasound proves not only a useful tool in appreciating the severity of a fetal defect, but also provides more convincing evidence of a normal fetus than conventional two-dimensional sonograms in cases with increased risk of a recurrent surface malformation.

Normal and abnormal fetal cardiac anatomy

The heart is often perceived as a difficult organ to understand by ultrasound during fetal life. This is undoubtedly reflected in the low detection rate of cardiac abnormalities as compared to those of most other organ systems in the fetus. In this article we start by updating classical concepts of cardiac embryology, many of which were previously difficult to understand since they were overly simplistic or purely observational. We then lead on to the structure and growth of the fully formed fetal heart where we review the anatomy and ultrasound appearances in detail and provide comparisons with major abnormalities. We emphasise the fact that a solid understanding of cardiac anatomy can enable those involved in fetal medicine to make full use of the views of the heart that are obtained by ultrasound and which are often only transient.

Three-Dimensional Sonography for Assessment of Morphology and Vascularization of the Fetus and Placenta

To analyze the potential of three-dimensional power Doppler sonography in morphologic and functional assessment of the fetus and placenta. Review of the recent literature on three-dimensional sonography in early pregnancy and in the second and third trimester. Three-dimensional sonography plays an important role in obstetrics predominantly for assessing fetal anatomy. Multiplanar images and rotation of the object allow systematic review of anatomic structures, such as limb buds, cerebral cavities, cord insertion, stomach, and bladder. Using this modality, volumes of the gestational sac, yolk sac, and fetal organs can be obtained easily. Three-dimensional power Doppler sonography has the potential to study the intervillous and placental circulation and evaluate the development of the embryonic and fetal cardiovascular system. Three-dimensional ultrasound imaging complements pathologic and histologic evaluation of the developing embryo, giving rise to the new term "three-dimensional sonoembryology." It is evident that three-dimensional ultrasonography improves the visualization of the normal and abnormal fetal anatomy giving a realistic impression of the extent of the defects. These data are useful not only for obstetricians but also for pediatricians and pediatric surgeons.

Second trimester ultrasonography may identify 77 to 97% of fetuses with trisomy 18.

Between 1990 and 1999, 30 second trimester fetuses with trisomy 18 and 2000 control fetuses underwent real-time and color Doppler ultrasonographic examination followed by genetic amniocentesis. Abnormal fetal anatomy was present in 97% of fetuses with trisomy 18, with a false-positive rate of 15.7%. Logistic regression identified six markers (choroid plexus cysts, central nervous system malformations, an abnormal nuchal skin fold, ventricular septal defect, outflow tract abnormalities of the heart, and right-to-left chamber disproportion of the heart) and one interaction between markers (right-to-left chamber disproportion and outflow tract abnormalities) to significantly contribute to the identification of 93% of fetuses with trisomy 18, with a false-positive rate of 8.9%. Noncardiovascular markers (choroid plexus cysts, central nervous system malformations, and abnormal nuchal skin fold) identified 77% of fetuses with trisomy 18, with a false-positive rate of 3.9%. Combining right-to-left chamber disproportion of the heart with choroid plexus cysts, central nervous system malformations, and nuchal skin folds identified 83% of fetuses with trisomy 18, with a false-positive rate of 4.4%.