Fetal Volume Research Articles

Fetal MRI deep learning segmentation of body and lung in congenital diaphragmatic hernia

Abstract Purpose To determine if deep learning (DL) segmentation of total fetal body volume (TFBV) and total fetal lung volume (TFLV) in fetuses with congenital diaphragmatic hernia has comparable performance to manual segmentation. Materials and Methods A total of 208 fetal MRI studies with congenital diaphragmatic hernia, acquired between August 2007 and September 2023, were retrospectively included. TFBV and TFLV were extracted from manual tissue segmentations in balanced gradient echo and single shot T2-weighted turbo spin echo sequences. MRI studies were split into training (n = 188) and hold-out test data (n = 20). Wilcoxon signed-rank test was used to compare manual and DL-based segmentations by 2 U-Nets. Manual and DL segmentation times were noted and compared using Student’s t-test. The observed/expected ratio of the total lung volume (O/E TLV) as a prognostic marker for postnatal survival was calculated. Outcome predictions of O/E TLV for postnatal death were assessed with univariate regression analysis. Results Manual segmentation times were higher compared to DL segmentations (30 ± 7 minutes versus 0.25 ± 0.05 minutes, P < .001). Manual and DL-based TFBV were similar (1317 ± 498 mL versus 1306 ± 491 mL; P = .04; Dice score: 0.98 ± 0.01). TFLV (19.4 ± 11.5 mL versus 18.7 ± 12.4 mL; P = .11; Dice score: 0.84 ± 0.09) and O/E TLV (39.3 ± 18.1 mL versus 37.7 ± 19.1 mL, P = .13) were not significantly different. Postnatal mortality was negatively associated with higher manual O/E TLV (odds ratio: 0.97; 95% confidence interval [CI], 0.96–0.98; P < .001) and DL O/E TLV (odds ratio: 0.97; 95% CI, 0.96–0.98; P < .001). Conclusion DL for body and lung segmentation in fetuses with congenital diaphragmatic hernia allows reliable and rapid calculations of the observed/expected ratio and equally predicts prognostic outcome.

Energetic cost of gestation and prenatal growth in humpback whales.

Improving our understanding of energy allocation in reproduction is key for accurately parameterizing bioenergetic models to assess population responses to environmental perturbations and anthropogenic disturbance. We quantified the energetic cost of gestation in humpback whales (Megaptera novaeangliae) using historical whaling records, non-invasive unoccupied aerial system (UAS) photogrammetry and postmortem tissue samples. First, we estimated relative birth size using body length measurements of 678mother-fetus pairs from historical whaling records and 987mother-calf pairs measured in situ using UAS-photogrammetry. The total energetic cost of gestation includes fetal growth (FG), heat increment of gestation and placental tissue development. FG was modelled from conception to birth, with fetal volume and mass estimated using the volume-to-length relationship of perinatal calves and published humpback whale tissue composition estimates. Tissue-specific energy content was quantified using post mortem bone, muscle, viscera and blubber samples from a neonatal humpback whale. Placental tissue development was estimated using humpback whale placental tissue and published equations. Relative birth length was found to be 33.75% (95% CI: 32.10-34.61) of maternal length. FG rates and absolute birth size increased with maternal length, with exponential growth in fetal length, volume and mass resulting in minimal energetic costs over the first two quadmesters (0.01-1.08%) before increasing significantly in the final quadmester (98.92%). Gestational heat constituted the greatest energetic cost (90.42-94.95%), followed by fetal (4.58-7.76%) and placental (0.37-1.83%) tissue growth. Our findings highlight the energetic costs endured by capital breeding females preceding parturition, with the most substantial energetic costs of gestation coinciding with migration and fasting. KEY POINTS: We quantified the energetic cost of gestation using body length measurements of mother-fetus pairs from historical whaling records, length estimates of mother-calf pairs measured in situ using aerial photogrammetry and post mortem tissue samples. Fetal growth rates and birth size increased with maternal length, with fetal length, volume and mass increasing exponentially over gestation. Energetic costs over the first two quadmesters were negligible (0.01-1.08%) before increasing significantly in the final quadmester (98.92%). Though larger females incur nearly twice the energetic cost of smaller females, they are likely buffered by greater absolute energy reserves, suggesting smaller females may be less resilient to perturbations in energy balance. We demonstrate the significant energetic costs incurred by pregnant humpback whales, with most of the energetic expenditure occurring over the final 100days of gestation. Late-pregnant females are, therefore, particularly vulnerable to disruptions in energy balance, given periods of greatest energetic stress coincide with fasting and migration.

Placental volume at gestational week 27 and subsequent fetal growth: An observational study

ObjectivesTo study if placental volume and placental to fetal ratio at gestational week (GW) 27 correlate with subsequent fetal growth. We also investigated whether the 1/3 smallest and 1/3 largest fetuses have different growth potential depending on placental volume. MethodsPlacental and fetal volume was measured by magnetic resonance imaging (MRI) at GW 27 and 37 in 86 singleton pregnancies. Placental to fetal ratio was calculated as placental volume/fetal volume. Growth was calculated as [(fetal volume at GW 37 – fetal volume at GW 27)/number of days between the MRI examinations]. To explore whether a higher placental volume affected growth of small and large fetuses differently, we performed separate analyses of the 1/3 smallest and 1/3 largest fetuses with placental volume under and above the median at GW 27. ResultsWe found a positive correlation of both placental volume and placental to fetal ratio at GW 27 with average growth velocity, r = 0.51 (p < 0.001) and r = 0.33 (p = 0.002) respectively. The correlation between fetal volume at GW 27 and average growth velocity was r = 0.48 (p < 0.001). The small fetuses had significantly lower average growth velocity if the placental volume was low compared to if the placental volume was high, 22 (SD 3) cm3/day versus 25 (SD 3) cm3/day, p = 0.02. Among the large fetuses, placental volume did not significantly affect growth. ConclusionsPlacental volume and placental to fetal ratio at GW 27 were positively correlated with subsequent fetal growth. Possibly, placental size is an indicator of fetal growth potential, especially among small fetuses.

Lung volumes are increased in fetuses with transposition of the great arteries on intrauterine MRI.

Fetal brain size is decreased in some children with complex CHDs, and the distribution of blood and accompanying oxygen and nutrients is regionally skewed from early fetal life dependent on the CHD. In transposition of the great arteries, deoxygenated blood preferentially runs to the brain, whereas the more oxygenated blood is directed towards the lungs and the abdomen. Knowledge of whether this impactsintrauterine organ development is limited. We investigated lung, liver, and total intracranial volume in fetuses with transposition of the great arteries using MRI.Eight fetuses with dextro-transposition and without concomitant disease or chromosomal abnormalities and 42 fetuses without CHD or other known diseases were scanned once or twice at gestational age 30 through 39 weeks. The MRI scans were conducted on a 1.5T system, using a 2D balanced steady-state free precession sequence. Slices acquired covered the entire fetus, slice thickness was 10 mm, pixel size 1.5 × 1.5 mm, and scan duration was 30 sec.The mean lung z score was significantly larger in fetuses with transposition compared with those without a CHD; mean difference is 1.24, 95% CI:(0.59;1.89), p < 0.001. The lung size, corrected for estimated fetal weight, was larger than in the fetuses without transposition; mean difference is 8.1 cm3/kg, 95% CI:(2.5;13.7 cm3/kg), p = 0.004.In summary, fetuses with dextro-transposition of the great arteries had both absolute and relatively larger lung volumes than those without CHD. No differences were seen in liver and total intracranial volume. Despite the small number of cases, the results are interesting and warrant further investigation.

Aortic isthmus flow reversal in fetal coarctation of the aorta and the associated factors.

The aim of this study was to investigate the presence of aortic isthmus flow reversal and its associated factors in fetuses with positive and false-positive coarctation of the aorta (CoA) compared with normal controls. Pregnant women with fetuses suspected of CoA and normal control were enrolled, and these women experienced prenatal ultrasound scan and followed up for 6 months after birth to confirm the presence of CoA. All the ultrasound parameters were analyzed. A total of 134 pregnant women were enrolled, with 43 CoA-positive fetuses and 91 CoA false-positive fetuses, and 334 matched pregnant women were enrolled in the control group. Aortic isthmus flow reversal occurred in 28 (65.1%) fetuses in the CoA-positive group, significantly (p < 0.05) more than in the false-positive (37 or 40.7%) or control group (64 or 19.2%). Aortic isthmus flow reversal was mostly in the full systole (n = 17 or 60.7%) or late systole and early-middle diastole (n = 10 or 35.7%) in the CoA-positive fetuses (n = 27 or 96.4%), significantly (p < 0.001) different from that in the false-positive or control group. The aortic isthmus flow reversal peak systolic velocity (PSV), flow volume, and ratio of reversed flow/forward flow were significantly (p < 0.05) increased in the CoA-positive and false-positive groups than in the control group. The aortic isthmus flow reversal incidence was significantly (p < 0.05) correlated with the middle cerebral artery (MCA) PSV in the total three groups or in the false-positive group but was significantly (p < 0001) negatively correlated with the MCA resistance index (RI) in the CoA-positive group. The incidence of the aortic isthmus flow reversal was significantly (p < 0.05) positively correlated with the umbilical artery (UA) RI in the false-positive group and with the UA RI in the total three groups. Independently associated factors for aortic isthmus flow reversal were isthmic flow volume/CCO (combined cardiac output) in the CoA-positive group. Reversal of flow in the aortic isthmus is much more common in true-positive cases of CoA as compared to controls, and isthmic flow reversal in the full systolic phase only suggests presence of CoA. The aortic isthmic reversed flow volume accounts for over half of the isthmic forward flow volume in the CoA-positive fetuses than in the normal controls.

Multiethnic growth standards for fetal body composition and organ volumes derived from 3D ultrasonography

BackgroundA major goal of contemporary obstetrical practice is to optimize fetal growth and development throughout pregnancy. To date, fetal growth during prenatal care is assessed by performing ultrasonographic measurement of two-dimensional fetal biometry to calculate an estimated fetal weight. Our group previously established two-dimensional fetal growth standards using sonographic data from a large cohort with multiple sonograms. A separate objective of that investigation involved the collection of fetal volumes from the same cohort. ObjectiveThe Fetal 3D Study was designed to establish standards for fetal soft tissue and organ volume measurements by three-dimensional ultrasonography and compare growth trajectories with conventional two-dimensional measures where applicable. Study DesignThe NICHD Fetal 3D Study included research-quality images of singletons collected in a prospective, racially and ethnically diverse, low-risk cohort of pregnant individuals at 12 U.S. sites, with up to five scans per fetus (N=1,730 fetuses). Abdominal subcutaneous tissue thickness was measured from two-dimensional images and fetal limb soft tissue parameters extracted from three-dimensional multiplanar views. Cerebellar, lung, liver and kidney volumes were measured using virtual organ computer aided analysis (VOCAL). Fractional arm and thigh total volumes, and fractional lean limb volumes were measured, with fractional limb fat volume calculated by subtracting lean from total. For each measure, weighted curves (5th, 50th, 95th percentiles) were derived from 15-41 weeks’ using linear mixed models for repeated measures with cubic splines. ResultsSubcutaneous thickness of the abdomen, arm, and thigh increased linearly, with slight acceleration around 27-29 weeks. Fractional volumes of the arm, thigh, and lean limb volumes increased along a quadratic curvature, with acceleration around 29-30 weeks. In contrast, growth patterns for two-dimensional humerus and femur lengths demonstrated a logarithmic shape, with fastest growth in the 2nd trimester. The mid-arm area curve was similar in shape to fractional arm volume, with an acceleration around 30 weeks, whereas the curve for the lean arm area was more gradual. The abdominal area curve was similar to the mid-arm area curve with an acceleration around 29 weeks. The mid-thigh and lean area curves differed from the arm areas by exhibiting a deceleration at 39 weeks. The growth curves for the mid arm and thigh circumferences were more linear with some decelerations. Cerebellar two-dimensional diameter increased linearly, whereas cerebellar three-dimensional volume growth gradually accelerated until 32 weeks and then decelerated. Lung, kidney, and liver volumes all demonstrated gradual early growth followed by a linear acceleration beginning at 25 weeks for lungs, 26-27 weeks for kidneys, and 29 weeks for liver. ConclusionGrowth patterns and timing of maximal growth for three-dimensional lean and fat measures, limb and organ volumes differed from patterns revealed by traditional two-dimensional growth measures, suggesting these parameters reflect unique facets of fetal growth. Growth in these three-dimensional measures may be altered by genetic, nutritional, metabolic or environmental influences and pregnancy complications, in ways not identifiable using corresponding two-dimensional measures. Further investigation into the relationships of these three-dimensional standards to abnormal fetal growth, adverse perinatal outcomes, and health status in postnatal life is warranted.

Estimated Fetal Radiation Dose From 18 F-FDG PET/CT During the Second and Third Trimesters of Pregnancy.

Data published in the literature concerning the doses received by fetuses exposed to a 18 F-FDG PET are reassuring but were obtained from small and heterogeneous cohorts, and very few data are available concerning the fetal dose received after exposure to both PET and CT. The present study aimed to estimate the fetal dose received following a PET/CT exposure using methods that include anthropomorphic phantoms of pregnant women applied on a large cohort. This retrospective multicenter study included 18 pregnant patients in the second and third trimesters. For PET exposure, the fetal volume and mean concentration of radioactivity in the fetus were measured by manually drawing regions of interest. Those data, combined with the time-integrated activities of the fetus and the mother's organs, were entered into the OLINDA/EXM software 2.0 to assess the fetal dose due to PET exposure. To estimate the fetal dose received due to CT exposure, 2 softwares were used: CT-Expo (based on geometric phantom models of nonpregnant patients) and VirtualDose (using pregnant patient phantoms). The fetal dose exposure for PET/CT examination in the second trimester ranged from 5.7 to 15.8 mGy using CT-Expo (mean, 11.6 mGy) and from 5.1 to 11.6 mGy using VirtualDose (mean, 8.6 mGy). In the third trimester, it ranged from 7.9 to 16.6 mGy using CT-Expo (mean, 10.7 mGy) and from 6.1 to 10.7 mGy using VirtualDose (mean, 7.6 mGy). The estimated fetal doses were in the same range of those previously published and are well below the threshold for deterministic effects. Pregnancy does not constitute an absolute contraindication for a clinically justified hybrid 18 F-FDG PET/CT.

Placental size at gestational week 27 and 37: The associations with pulsatility index in the uterine and the fetal-placental arteries

IntroductionFetal growth restriction is known to be related to decreased fetal and placental blood flow. It is not known, however, whether placental size is related to fetal and placental blood flow. We studied the correlations of intrauterine placental volume and placental-fetal-ratio with pulsatility index (PI) in the uterine arteries, fetal middle cerebral artery, and umbilical artery. MethodsWe followed a convenience sample of 104 singleton pregnancies, and we measured placental and fetal volumes using magnetic resonance imaging (MRI) at gestational week 27 and 37 (n = 89). Pulsatility index (PI) was measured using Doppler ultrasound. We calculated cerebroplacental ratio as fetal middle cerebral artery PI/umbilical artery PI and placental-fetal-ratio as placental volume (cm3)/fetal volume (cm3). ResultsAt gestational week 27, placental volume was negatively correlated with uterine artery PI (r = −0.237, p = 0.015, Pearson's correlation coefficient), and positively correlated with fetal middle cerebral artery PI (r = 0.247, p = 0.012) and cerebroplacental ratio (r = 0.208, p = 0.035). Corresponding correlations for placental-fetal-ratio were −0.273 (p = 0.005), 0.233 (p = 0.018) and 0.183 (p = 0.064). Umbilical artery PI was not correlated with placental volume. At gestational week 37, we found weaker and no significant correlations between placental volume and the pulsatility indices. ConclusionsOur results suggest that placental size is correlated with placental and fetal blood flow at gestational week 27.

Comparative Study between Crown-Rump Length and Fetal Volume in First Trimester for Accurate Estimation of Gestational Age

Comparative Study between Crown-Rump Length and Fetal Volume in First Trimester for Accurate Estimation of Gestational Age

The NICHD Fetal 3D Study: A Pregnancy Cohort Study of Fetal Body Composition and Volumes.

There's a paucity of robust normal fractional limb and organ volume standards from a large and diverse ethnic population. The Fetal 3D Study was designed to develop research and clinical applications for fetal soft tissue and organ volume assessment. The NICHD Fetal Growth Studies (2009-2013) collected 2D and 3D fetal volumes. In the Fetal 3D Study (2015-2019), sonographers performed longitudinal 2D and 3D measurements for specific fetal anatomical structures in research ultrasounds of singletons and dichorionic twins. The primary aim was to establish standards for fetal body composition and organ volumes, overall and by maternal race/ethnicity, and determine whether these standards vary for twins versus singletons. We describe the study design, methods, and details about reviewer training. Basic characteristics of this cohort, with their corresponding distributions of fetal 3D measurements by anatomical structure, are summarized. This investigation is responsive to critical data gaps in understanding serial changes in fetal subcutaneous fat, lean body mass, and organ volume in association with pregnancy complications. In the future, this cohort can answer critical questions regarding the potential influence of maternal characteristics, lifestyle factors, nutrition, and biomarker and chemical data on longitudinal measures of fetal subcutaneous fat, lean body mass, and organ volumes.

Placental size at gestational week 36: Comparisons between ongoing pregnancies and deliveries.

We aimed to compare placental size and placental size relative to fetal size (ratio) in ongoing pregnancies examined by magnetic resonance imaging (MRI) at gestational week 36 with placental size among all deliveries at gestational week 36 during the same time period. Ongoing unselected singleton pregnancies (n = 89) were examined by MRI at median gestational week 36+5 days during 2017-2018, and placental and fetal volumes (cm3 ) were calculated. The placental size and ratio in ongoing pregnancies were compared with placental size and ratio among all deliveries in Norway at gestational week 36 (median gestational week 36+4 days) during 2016-2019 (n = 5582). For comparison of size, we converted volume (cm3 ) in ongoing pregnancies into grams as: cm3 × 1.05 (density of placental and fetal tissue). In ongoing pregnancies, median placental size was 873 (interquartile range [IQR] 265) grams and median size of all delivered placentas was 613 (IQR 290) grams. Placental size was smaller among the delivered placentas independent of delivery mode: 760 (IQR 387) grams among elective cesarean deliveries (n = 465) and 590 (IQR 189) grams among vaginal deliveries after spontaneous onset of labor (n = 2478). Median ratio in ongoing pregnancies was higher than among deliveries: 0.31 (IQR 0.08) vs 0.21 (IQR 0.08). The ratio was higher in ongoing pregnancies independent of delivery mode: 0.24 (IQR 0.17) among elective cesarean deliveries vs 0.21 (IQR 0.05) among vaginal deliveries after spontaneous onset of labor. The placenta is larger in ongoing pregnancies than among deliveries. This finding suggests that placental size decreases during labor and delivery, possibly by transfer of blood to the fetus. Our finding also suggests that reference values of placental size based on delivered placentas are not valid for ongoing pregnancies.

Cleft palate in fetuses: feasibility of early diagnosis by Crystal and Realistic Vue rendering 3D ultrasound technology in the first trimester.

This study aimed to evaluate the feasibility of direct visualization of a normal fetal palate and detect cleft palate in the first trimester with a novel three-dimensional ultrasound (3D US) technique, Crystal and Realistic Vue (CRV) rendering technology. Two-dimensional (2D) images and 3D volumes of healthy and cleft palate fetuses at 11-13+6 weeks were obtained prospectively. 2D ultrasound views included the coronal view of the retronasal triangle and the midsagittal view of the face. 3D-CRV views were analyzed by multiplanar mode display. The pregnancy outcomes of all fetuses were determined during the follow-up period. In our study, 124 fetuses were recruited, including 100 healthy fetuses and 24 cleft palate fetuses. The cleft palate with lip was observed in 23 fetuses (bilateral in 15, unilateral in 6, median in 2), and one cleft palate was only found in the abnormal group. The bilateral (n = 12) and median (n = 2) cleft palates with lips and the cleft palate alone (n = 1) were associated with other anatomical or chromosomal abnormalities, and one unilateral cleft palate with cleft lip had concomitant NT thickening. In the cleft palate fetus group, 16 fetuses suffered intrauterine death, which was associated with other structural or chromosomal abnormalities in 14 fetuses, seven cases were terminated after consultation, and one was delivered at term. The coronal view of the retronasal triangle and the midsagittal view was easily obtained in all fetuses. 3D-CRV images of palatal parts were clearly obtained in all cases. Unilateral, bilateral, and median cleft palates with cleft lips were visually demonstrated and classified by the 3D-CRV technique. It is feasible to identify the palate by 3D-CRV in the first trimester in both healthy and cleft palate fetuses. Together with 2D ultrasonography as a complementary diagnostic tool, 3D-CRV is helpful in classifying the cleft palate with a reasonable degree of certainty.

Three-Dimensional Ultrasound Evaluation of Lung Volume in Fetuses with Abdominal Wall Defect

Introduction: Abdominal wall defects (AWDs) interfere with postnatal respiratory parameters. We aimed to evaluate lung volume (LV) in fetuses with AWD using three-dimensional (3D) ultrasound (US) and to correlate AWD with the type (omphalocele and gastroschisis) and size of the defect and neonatal morbidity and mortality. Methods: This prospective observational study included 72 pregnant women with fetuses with AWD and a gestational age <25 weeks. The data on abdominal volume, 3D US LV, and herniated volume were acquired every 4 weeks up to 33 weeks. LV was compared with normal reference curves and correlated with abdominal and herniated volumes. Results: Omphalocele (p < 0.001) and gastroschisis (p < 0.001) fetuses had smaller LV than normal fetuses. LV was positively correlated with abdominal volume (omphalocele, r = 0.86; gastroschisis, r = 0.88), whereas LV was negatively correlated with omphalocele-herniated volume/abdominal volume (p < 0.001, r = −0.51). LV was smaller in omphalocele fetuses that died (p = 0.002), were intubated (p = 0.02), or had secondary closure (p < 0.001). In gastroschisis, a smaller LV was observed in fetuses discharged using oxygen (p = 0.002). Conclusion: Fetuses with AWD had smaller 3D LV than normal fetuses. Fetal abdominal volume was inversely correlated with LV. In omphalocele fetuses, a smaller LV was associated with neonatal mortality and morbidity.

Impaired Distensibility of the Proximal Aorta in Fetuses With Tetralogy of Fallot.

Background Increased aortic wall stiffness, which even persists after repair, has been reported in patients with tetralogy of Fallot (TOF). We aimed to observe the distensibility of the ascending aorta and descending aorta in fetuses with TOF and explore its relation with aortic blood flow volume and aortic and pulmonary annular size. Methods and Results Twenty-three fetuses with TOF and 23 gestational age-matched normal fetuses were included in this prospective cross-sectional study. The distensibilities of the ascending aorta and descending aorta were assessed by aortic strain (AS), which was defined as follows: 100×(maximum internal diameter in the systolic phase-minimum internal diameter in the diastolic phase)/minimum internal diameter in the diastolic phase. The maximum internal diameter in the systolic phase and minimum internal diameter in the diastolic phase of the ascending aorta and descending aorta were measured by M-mode echocardiography. Associations between AS and aortic blood flow volume and aortic and pulmonary valve diameters were assessed in both groups. AS of the ascending aorta in TOF group was lower than that in controls (20.48%±4.19% versus 28.17%±4.54%; P<0.001), whereas there was no significant difference in the descending aorta. The multivariate regression model demonstrated that AS was significantly related to aortic valve size (P=0.014) and aortic blood flow volume (P=0.022) in fetuses with TOF, whereas only aortic blood flow volume was significantly correlated with AS in the control group (P=0.01). No significant association was found between AS and pulmonary valve size. Conclusions Impaired distensibility of proximal aorta was observed in fetuses with TOF. Both intrinsic abnormalities of the aortic wall and aortic volume overload probably play roles in the altered aortic distensibility.

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.

Automatic placental and fetal volume estimation by a convolutional neural network

IntroductionWe aimed to develop an artificial intelligence (AI) deep learning algorithm to efficiently estimate placental and fetal volumes from magnetic resonance (MR) scans. MethodsManually annotated images from an MRI sequence was used as input to the neural network DenseVNet. We included data from 193 normal pregnancies at gestational week 27 and 37. The data were split into 163 scans for training, 10 scans for validation and 20 scans for testing. The neural network segmentations were compared to the manual annotation (ground truth) using the Dice Score Coefficient (DSC). ResultsThe mean ground truth placental volume at gestational week 27 and 37 was 571 cm3 (Standard Deviation (SD) 293 cm3) and 853 cm3 (SD 186 cm3), respectively. Mean fetal volume was 979 cm3 (SD 117 cm3) and 2715 cm3 (SD 360 cm3). The best fitting neural network model was attained at 22,000 training iterations with mean DSC 0.925 (SD 0.041). The neural network estimated mean placental volumes at gestational week 27–870 cm3 (SD 202 cm3) (DSC 0.887 (SD 0.034), and to 950 cm3 (SD 316 cm3) at gestational week 37 (DSC 0.896 (SD 0.030)). Mean fetal volumes were 1292 cm3 (SD 191 cm3) and 2712 cm3 (SD 540 cm3), with mean DSC of 0.952 (SD 0.008) and 0.970 (SD 0.040). The time spent for volume estimation was reduced from 60 to 90 min by manual annotation, to less than 10 s by the neural network. ConclusionThe correctness of neural network volume estimation is comparable to human performance; the efficiency is substantially improved.

Fetal body composition and volumes study

Classification of abnormal fetal growth as “restriction” or “overgrowth” during an ongoing pregnancy is an important clinical challenge. Fetal soft tissue may reflect some of the earliest changes that occur in pathologic growth compared to traditional 2-dimensional (2D) estimates of fetal biometry. The Fetal 3D Study was designed to develop research and clinical applications for fetal soft tissue and organ volume assessment. Data collected in the NICHD Fetal Growth Studies included 2D fetal biometrics and 3D fetal volumes which were banked. In the Fetal 3D Study, sonographers performed longitudinal 2D and 3D measures targeting specific fetal anatomic structures. Each woman with a singleton had up to six research ultrasound scans while twins had up to seven. Of 2,802 with a singleton, 2,751 (98.2%) had 2D abdomen or 3D available and were included in the Fetal 3D Study. Of these, 2,435 (88.5%) had at least one 3D available (while 11.5% had only 2D abdomen) and 2,333 (84.8%) had at least one 3D that was measured. Out of 171 with a twin, there were 165 (96.5%) included: all had at least one 3D volume available and 152 (92.1%) had at least one 3D volume measured. Volume types with highest number of measures available were for the cerebellum, abdomen (liver and kidney) and thigh, based on protocol prioritization. After the first trimester, availability of 3D decreased with advancing gestational age (Table). For fetal organs with left and right sides (lungs, kidneys, and adrenal glands), it was more common that either side was able to be measured rather than both sides. Reliable 2D and 3D fetal biometry measurements depended on several factors including examiner training and experience, image quality, technique used to scan anatomic structures, fetal movement and position, and availability of 3D ultrasound software tools that allow rapid and reproducible measurements. Standardized procedures resulted in a large quantity of longitudinal fetal soft tissue and organ volume measurements from a diverse pregnant U.S. sample.

Prenatal Sonographic Three-dimensional Virtual Organ Computer-assisted Analysis Thymic Volume Calculation May Predict Intrauterine Growth Restriction.

Intrauterine growth restriction (IUGR) refers to fetuses that are small for their gestational age. There is no effective test to predict this disease. The aim of our study is whether fetal three-dimensional (3D) ultrasonography (USG)-assisted thymus volume (TV) measurement predicts IUGR cases. Fetal 3D USG thymus measurement between 15 and 24 weeks of gestation was performed in a total of 100 women of reproductive age. Fetal TV was measured using the virtual organ computer-assisted analysis system program. All cases were followed up in terms of pregnancy complications until delivery. IUGR was developed in six cases in total. In cases with IUGR, mean fetal TV was found to be statistically significantly lower than in healthy cases without it. When the fetal TV was taken as 0.1645, the sensitivity was calculated as 89.5% and the specificity as 50% for predicting IUGR. The use of low fetal volume parameters is a significant and good indicator for predicting IUGR according to the binary logistic regression analysis result. According to the results of this study, 3D fetal TV measurement may be used in routine second-trimester sonographic anomaly screening to predict the development of fetal IUGR. In this way, fetal mortality and morbidity caused by IUGR may be reduced.

Automatic Segmentation of the Fetus in 3D Magnetic Resonance Images Using Deep Learning: Accurate and Fast Fetal Volume Quantification for Clinical Use

Magnetic resonance imaging (MRI) provides images for estimating fetal volume and weight, but manual delineations are time consuming. The aims were to (1) validate an algorithm to automatically quantify fetal volume by MRI; (2) compare fetal weight by Hadlock’s formulas to that of MRI; and (3) quantify fetal blood flow and index flow to fetal weight by MRI. Forty-two fetuses at 36 (29–39) weeks gestation underwent MRI. A neural network was trained to segment the fetus, with 20 datasets for training and validation, and 22 for testing. Hadlock’s formulas 1–4 with biometric parameters from MRI were compared with weight by MRI. Blood flow was measured using phase-contrast MRI and indexed to fetal weight. Bland–Altman analysis assessed the agreement between automatic and manual fetal segmentation and the agreement between Hadlock’s formulas and fetal segmentation for fetal weight. Bias and 95% limits of agreement were for automatic versus manual measurements 4.5 ± 351 ml (0.01% ± 11%), and for Hadlock 1–4 vs MRI 108 ± 435 g (3% ± 14%), 211 ± 468 g (7% ± 15%), 106 ± 425 g (4% ± 14%), and 179 ± 472 g (6% ± 15%), respectively. Umbilical venous flow was 406 (range 151–650) ml/min (indexed 162 (range 52–220) ml/min/kg), and descending aortic flow was 763 (range 481–1160) ml/min (indexed 276 (range 189–386) ml/min/kg). The automatic method showed good agreement with manual measurements and saves considerable analysis time. Hadlock 1–4 generally agree with MRI. This study also illustrates the confounding effects of fetal weight on absolute blood flow, and emphasizes the benefit of indexed measurements for physiological assessment.

Fetal Dose from PET and CT in Pregnant Patients.

When pregnancy is discovered during or after a diagnostic examination, the physician or the patient may request an estimate of the radiation dose received by the fetus as per guidelines and standard operating procedures. This study provided the imaging community with dose estimates to the fetus from PET/CT with protocols that are adapted to University of Michigan low-dose protocols for patients known to be pregnant. Methods: There were 9 patients analyzed with data for the first, second, and third trimesters, the availability of which is quite rare. These images were used to calculate the size-specific dose estimate (SSDE) from the CT scan portion and the SUV and 18F-FDG uptake dose from the PET scan portion using the MIRD formulation. The fetal dose estimates were tested for correlation with each of the following independent measures: gestational age, fetal volume, average water-equivalent diameter of the patient along the length of the fetus, SSDE, SUV, and percentage of dose from 18F-FDG. Stepwise multiple linear regression analysis was performed to assess the partial correlation of each variable. To our knowledge, this was the first study to determine fetal doses from CT and PET images. Results: Fetal self-doses from 18F for the first, second, and third trimesters were 2.18 mGy (single data point), 0.74-1.82 mGy, and 0.017-0.0017 mGy, respectively. The combined SSDE and fetal self-dose ranged from 1.2 to 8.2 mGy. These types of images from pregnant patients are rare. Conclusion: Our data indicate that the fetal radiation exposure from 18F-FDG PET and CT performed, when medically necessary, on pregnant women with cancer is low. All efforts should be made to minimize fetal radiation exposure by modifying the protocol.