Impact of maternal infection on outcomes in extremely preterm infants.

BACKGROUND: Infants born less than 29 weeks, or extremely preterm (EPT), experience increased morbidity and mortality. We hypothesized that exposure to maternal infection might contribute to neurodevelopmental impairment (NDI) or death at 2 years of age. METHODS: We conducted a retrospective cohort study of EPT infants from January 2010 to December 2020. Maternal data extracted included maternal infections, classified as extrauterine or intrauterine. Placental pathologic and infant data were extracted. The primary outcome was NDI or death at 2 years of age. RESULTS: 548 EPT infants were born to 496 pregnant people: 379 (69%) were not exposed to any documented maternal infection prenatally, 124 (23%) to extrauterine infection, and 45 (8%) to intrauterine infection. Neither diagnosis of maternal extrauterine nor intrauterine infection was associated with NDI or death at 2 years of age (p > 0.05). Acute histologic chorioamnionitis was associated with NDI or death at 2 years of age (p = 0.033). CONCLUSIONS: Maternal infection was not associated with NDI or death at 2 years of age in EPT infants. However, acute histologic chorioamnionitis was associated with this outcome. Further work should investigate the differential influence of infection and immune response with this pathology as relates to outcomes in EPT infants. IMPACT: Maternal infection was not associated with neurodevelopmental impairment (NDI) or death at 2 years of age in extremely preterm (EPT) infants. This is reassuring support that mechanisms at the maternal-fetal interface largely protect the EPT infant. However, pathologic findings of acute histologic chorioamnionitis were associated with NDI and death at 2 years of age. Further work should investigate the differential influence of infection and immune response with acute histologic chorioamnionitis on pathology as relates to outcomes in EPT infants.

Longitudinal assessment of placental perfusion in normal and hypertensive pregnancies using pseudo-continuous arterial spin-labeled MRI: preliminary experience.

OBJECTIVES: To evaluate longitudinal placental perfusion using pseudo-continuous arterial spin-labeled (pCASL) MRI in normal pregnancies and in pregnancies affected by chronic hypertension (cHTN), who are at the greatest risk for placental-mediated disease conditions. METHODS: Eighteen normal and 23 pregnant subjects with cHTN requiring antihypertensive therapy were scanned at 3 T using free-breathing pCASL-MRI at 16-20 and 24-28 weeks of gestational age. RESULTS: Mean placental perfusion was 103.1 ± 48.0 and 71.4 ± 18.3 mL/100 g/min at 16-20 and 24-28 weeks respectively in normal pregnancies and 79.4 ± 27.4 and 74.9 ± 26.6 mL/100 g/min in cHTN pregnancies. There was a significant decrease in perfusion between the first and second scans in normal pregnancies (p = 0.004), which was not observed in cHTN pregnancies (p = 0.36). The mean perfusion was not statistically different between normal and cHTN pregnancies at both scans, but the absolute change in perfusion per week was statistically different between these groups (p = 0.044). Furthermore, placental perfusion was significantly lower at both time points (p = 0.027 and 0.044 respectively) in the four pregnant subjects with cHTN who went on to have infants that were small for gestational age (52.7 ± 20.4 and 50.4 ± 20.9 mL/100 g/min) versus those who did not (85 ± 25.6 and 80.0 ± 25.1 mL/100 g/min). CONCLUSION: pCASL-MRI enables longitudinal assessment of placental perfusion in pregnant subjects. Placental perfusion in the second trimester declined in normal pregnancies whereas it remained unchanged in cHTN pregnancies, consistent with alterations due to vascular disease pathology. Perfusion was significantly lower in those with small for gestational age infants, indicating that pCASL-MRI-measured perfusion may be an effective imaging biomarker for placental insufficiency. CLINICAL RELEVANCE STATEMENT: pCASL-MRI enables longitudinal assessment of placental perfusion without administering exogenous contrast agent and can identify placental insufficiency in pregnant subjects with chronic hypertension that can lead to earlier interventions. KEY POINTS: • Arterial spin-labeled (ASL) magnetic resonance imaging (MRI) enables longitudinal assessment of placental perfusion without administering exogenous contrast agent. • ASL-MRI-measured placental perfusion decreased significantly between 16-20 week and 24-28 week gestational age in normal pregnancies, while it remained relatively constant in hypertensive pregnancies, attributed to vascular disease pathology. • ASL-MRI-measured placental perfusion was significantly lower in subjects with hypertension who had a small for gestational age infant at 16-20-week gestation, indicating perfusion as an effective biomarker of placental insufficiency.

Prenatal Ultrasound Findings of Circumvallate Placenta and Pregnancy Outcomes.

OBJECTIVE: Circumvallate placenta has a suggested association with adverse pregnancy outcomes (antenatal bleeding, placental abruption, preterm birth, emergency cesarean, small for gestational age infants, and stillbirth). The aim was to determine if prenatal diagnosis of circumvallate placenta is associated with these adverse pregnancy outcomes. STUDY DESIGN: Pregnancies with a singleton gestation prenatally diagnosed with circumvallate placenta between January 1, 2012 and March 31, 2021 were identified. Adverse pregnancy outcomes were obtained. Rates of adverse pregnancy outcomes were compared among those with prenatally diagnosed circumvallate placentas to those without this prenatal diagnosis with a 4:1 control matched group. Pregnancies with known fetal anomalies or other placental abnormalities were excluded. Statistical analyses included Student's t-test and Χ 2 with p < 0.05 considered significant. RESULTS: Prenatal ultrasound findings of circumvallate placenta were seen in 179 pregnant people (0.20% of all anatomic US studies and 0.17% of all deliveries). Diagnosis was made at a mean gestational age of 19.8 ± 2.4 weeks. Adverse pregnancy outcomes were similar between groups. CONCLUSION: Prenatal ultrasound findings of circumvallate placenta do not correlate with adverse pregnancy outcomes. Given overall good prognosis, prenatal diagnosis of circumvallate placenta may not warrant additional surveillance during pregnancy. KEY POINTS: · The risk of prenatally diagnosed circumvallate placenta was previously unclear.. · Prenatally diagnosed circumvallate placenta is not associated with adverse pregnancy outcomes.. · No change in management may be necessary with prenatally diagnosed circumvallate placenta..

Placental vascular malperfusion lesions in fetal congenital heart disease.

BACKGROUND: Fetuses with congenital heart disease are at increased risk of perinatal morbidity and mortality, which is highly influenced by their prenatal health. Placental function is vital for the health of the fetus, but increased rates of pathologic lesions of the placenta have been observed in pregnancies complicated by fetal congenital heart disease. OBJECTIVE: This study aimed to determine the prevalence of both gross and histologic placental pathologies in a cohort of pregnancies complicated by fetal congenital heart disease vs healthy controls using the Amsterdam Placental Workshop Group Consensus Statement sampling and definitions of placental lesions. STUDY DESIGN: This single-center retrospective cohort study included placental examinations from pregnancies diagnosed prenatally with fetal congenital heart disease between 2010 and 2019; moreover, control placentas were collected from pregnancies without maternal or fetal complications. Placentas were sampled and evaluated according to the Amsterdam Placental Workshop Group Consensus Statement and gross and histopathologic diagnoses determined. RESULTS: Approximately 80% of fetuses diagnosed with congenital heart disease (n=305) had a placental examination for comparison with controls (n=40). Of note, 239 placentas (78%) in the group with fetal congenital heart disease had at least 1 gross or histopathologic lesion compared with 11 placentas (28%) in the control group (P<.01). One-third of placentas complicated by fetal congenital heart disease met the criteria for small for gestational age, and 48% of placentas had one or more chronic lesions, including maternal vascular malperfusion (23% vs 0%; P<.01), villitis of unknown etiology (22% vs 0%; P<.01), fetal vascular malperfusion (20% vs 0%; P<.01), and other chronic lesions (16% vs 0%; P<.01). Acute inflammation was equally present in both the group with fetal congenital heart disease and the control group (28% vs 28%; P=1.00). Although gestational age and birthweight z score were similar between the 2 groups, birth head circumference was 1.5 cm less in pregnancies complicated by fetal congenital heart disease with a significantly lower z score compared with the control group (-0.52±1.22 vs 0.06±0.69; P<.01). CONCLUSION: Vascular malperfusion lesions and chronic forms of inflammation occur at markedly higher rates in placentas complicated by fetal congenital heart disease, which may contribute to the decreased head circumference at birth. Further work in neuroplacentology is needed to explore connections among cardiac defects, placental vascular malperfusion lesions, and fetal brain development.

Neuroplacentology in congenital heart disease: placental connections to neurodevelopmental outcomes.

Children with congenital heart disease (CHD) are living longer due to effective medical and surgical management. However, the majority have neurodevelopmental delays or disorders. The role of the placenta in fetal brain development is unclear and is the focus of an emerging field known as neuroplacentology. In this review, we summarize neurodevelopmental outcomes in CHD and their brain imaging correlates both in utero and postnatally. We review differences in the structure and function of the placenta in pregnancies complicated by fetal CHD and introduce the concept of a placental inefficiency phenotype that occurs in severe forms of fetal CHD, characterized by a myriad of pathologies. We propose that in CHD placental dysfunction contributes to decreased fetal cerebral oxygen delivery resulting in poor brain growth, brain abnormalities, and impaired neurodevelopment. We conclude the review with key areas for future research in neuroplacentology in the fetal CHD population, including (1) differences in structure and function of the CHD placenta, (2) modifiable and nonmodifiable factors that impact the hemodynamic balance between placental and cerebral circulations, (3) interventions to improve placental function and protect brain development in utero, and (4) the role of genetic and epigenetic influences on the placenta-heart-brain connection. IMPACT: Neuroplacentology seeks to understand placental connections to fetal brain development. In fetuses with CHD, brain growth abnormalities begin in utero. Placental microstructure as well as perfusion and function are abnormal in fetal CHD.

Postpartum Depression Risk following Prenatal Diagnosis of Major Fetal Structural Anomalies.

OBJECTIVES: Our primary objective was to evaluate how prenatal diagnosis of a major fetal structural anomaly and resulting pregnancy outcome affected postpartum depression risk, as assessed by the Edinburgh Postnatal Depression Scale (EPDS). Secondary objectives were to review the rate of mental health follow-up and subsequent diagnosis of postpartum depression in screen-positive women. STUDY DESIGN: Singleton pregnancies with prenatal diagnosis of one or more major fetal structural anomalies were ascertained from prospectively maintained databases that included perinatal outcomes and subsequent EPDS responses from January 2010 to May 2018. EPDS scores of 13 or higher were considered positive and prompted referral for mental health follow-up, which was verified by medical record review. Statistical analyses were performed using Student's t-test, χ2, and odds ratios (ORs) with p < 0.05 considered significant. RESULTS: A total of 1,306 women had a prenatal diagnosis of one or more major fetal structural anomalies, 896 (68%) also had a postpartum EPDS screening, and 82 (9.2%) screened positive. Positive EPDS screening was more common with anomalies of multiple organ systems (16.5 vs 7.8%, p = 0.002) and aneuploidy (17.1 vs 9.3%, p = 0.02). Pregnancies complicated by fetal death, neonatal death, and termination for anomaly were significantly more likely to screen positive than those with neonatal survival to discharge (OR, 3.1 [95% confidence interval [CI], 1.6-6.2], 3.0 [95% CI, 1.5-5.8], and 4.4 [95% CI, 2.1-8.9], respectively, p ≤ 0.002). Of the 35 (43%) screen-positive women who attended follow-up appointments with mental health providers, 18 (51%) were diagnosed with a depressive disorder, accounting overall for 22% of those with a positive EPDS screen. CONCLUSION: Among women with a prenatal diagnosis of a major fetal structural anomaly, those experiencing a perinatal loss or pregnancy termination have an increased risk of positive EPDS screen result compared with who have a neonate surviving to discharge. A depressive disorder was diagnosed postpartum in 22% of these women with a positive EPDS screen. Our findings highlight the mental health needs in this vulnerable population. KEY POINTS: · Adverse pregnancy outcome increased positive EPDS screen risk among women with prenatal anomalies.. · A depressive disorder was diagnosed postpartum in 22% of such women with a positive EPDS screen.. · Our findings highlight the mental health needs in this vulnerable population..

Use of Fetal Magnetic Resonance Imaging After Sonographic Identification of Major Structural Anomalies.

OBJECTIVES: To characterize population-based use of fetal magnetic resonance imaging (MRI) incorporating recent American College of Radiology (ACR)-Society of Perinatal Radiologists (SPR) guidelines about fetal anomalies for which MRI may provide valuable additional information when sonography is limited. METHODS: We conducted a retrospective review of nonreferred singleton pregnancies that received prenatal care and had prenatal sonographic diagnosis of 1 or more major structural anomalies at our hospital between January 2010 and May 2018. Detailed sonography was performed in all anomaly cases. Fetal anomaly information was obtained from a prospectively maintained database, and medical records were reviewed to determine the rationale for why MRI was or was not performed, according to the indication. RESULTS: A total of 104,597 singleton pregnancies underwent sonographic assessments of anatomy at our institution during the study period. Major structural anomalies were identified in 1650 (1.6%) of these pregnancies. Potential indications for fetal MRI per ACR-SPR guidelines were identified in 339 cases. However, fetal MRI was performed in only 253 cases, 15% of those with major anomalies and 75% with a potential indication. Magnetic resonance imaging was not performed in 41 (20%) of identified pregnancies because of an improved prognosis on serial sonography (36), because of a poor prognosis (3), or because it would not alter management (2). CONCLUSIONS: Fetal MRI was used in 15% of those pregnancies with prenatal diagnosis of a major structural anomaly. This amounted to fewer than 0.3% of singleton deliveries. Judicious application of ACR-SPR guidelines in the context of serial sonography results in a relatively small number of fetal MRI examinations in a nonreferred population.

Number of Risk Factors in Down Syndrome Pregnancies.

OBJECTIVE: The objective of this study was to evaluate risk factor prevalence in pregnancies with fetal Down syndrome, in an effort to characterize efficacy of population-based screening. STUDY DESIGN: Retrospective review of singleton pregnancies with delivery of live born or stillborn infant with Down syndrome from 2009 through 2015. Risk factor categories included maternal age ≥35 years, abnormal serum screening, identification of ≥1 ultrasound marker at 16 to 22 weeks (nuchal thickness ≥6 mm, echogenic intracardiac focus, echogenic bowel, renal pelvis dilatation, femur length 50% of fetuses in women <35 years and in >75% of those 35 years and older. CONCLUSION: In a population-based cohort, sensitivity of second-trimester Down syndrome screening was 93%, with multiple risk factors present in nearly three-fourths of cases.

Magnetic Resonance Imaging-Based Radiomics of Axial and Sagittal Orientation in Pregnant Patients with Suspected Placenta Accreta Spectrum.

RATIONALE AND OBJECTIVES: Placenta accreta spectrum (PAS) is associated with significant morbidity and mortality. Current radiomic analysis of PAS magnetic resonance (MR) images is often performed on a single imaging plane. However, depending on the chosen imaging plane, radiomic features extracted from the same patient may vary due to the differing orientations and anatomical contexts, potentially leading to inconsistent results. In this study, we applied region of interest (ROI)-based radiomic analysis on axial and sagittal MR images in pregnant patients at high risk for PAS. Our objective was to compare MR textural features extracted from these imaging planes and to correlate these findings with surgical outcomes, aiming to enhance the accuracy of PAS diagnosis and treatment planning. MATERIALS AND METHODS: This is a retrospective review of MR images of pregnancies with prenatally suspected PAS. Volumetric placental, uterus, and internal os of the cervix regions of interest (ROI) were manually segmented on axial and sagittal MR images for each patient. Radiomic features were extracted following the image biomarker standardization initiative guideline. Agreement in features extracted from axial and sagittal images were assessed using Spearman's rank correlation coefficient. RESULTS: Of the 101 pregnant patients that met the study inclusion criteria, 65 underwent cesarean hysterectomy for PAS. 77 percent of the radiomics features had strong Spearman rank correlations (>0.8) between axial and sagittal images, indicating that these imaging planes provide similar radiomics information. The diagnostic performance of features extracted from axial and sagittal planes was quantified under the receiver operating characteristics curve (AUC). We found that axial and sagittal planes have similar performance for the prediction of hysterectomy. Shape elongation, Placental Location within the Uterus (PLU), and heterogeneity features were significant predictors for hysterectomy regardless of the imaging plane. CONCLUSION: Our study found that radiomics features extracted from axial and sagittal MR image plane in the same patient have excellent agreement and strong correlation. We identified several features present in both axial and sagittal images that were predictive in detecting PAS-suspected patient who required hysterectomy. These features may represent the underlying placental pathophysiology.

Magnetic resonance imaging improves diagnosis of placenta accreta spectrum requiring hysterectomy compared to ultrasound.

BACKGROUND: Magnetic resonance imaging has been used increasingly as an adjunct for ultrasound imaging for placenta accreta spectrum assessment and preoperative surgical planning, but its value has not been established yet. The ultrasound-based placenta accreta index is a well-validated standardized approach for placenta accreta spectrum evaluation. Placenta accreta spectrum-magnetic resonance imaging markers have been outlined in a joint guideline from the Society of Abdominal Radiology and the European Society of Urogenital Radiology. OBJECTIVE: This study aimed to compare placenta accreta spectrum-magnetic resonance imaging parameters with the ultrasound-based placenta accreta index in pregnancies at high risk for placenta accreta spectrum and to assess the additional diagnostic value of magnetic resonance imaging for placenta accreta spectrum that requires a cesarean hysterectomy. STUDY DESIGN: This was a single-center, retrospective study of pregnant patients who underwent magnetic resonance imaging, in addition to ultrasonography, because of suspected placenta accreta spectrum. The ultrasound-based placenta accreta index and placenta accreta spectrum-magnetic resonance imaging parameters were obtained. Student's t test and Fisher's exact test were used to compare the groups in terms of the primary outcome (hysterectomy vs no hysterectomy). The diagnostic performance of magnetic resonance imaging and the ultrasound-based placenta accreta index was assessed using multivariable logistic regressions, receiver operating characteristics curves, the DeLong test, McNemar test, and the relative predictive value test. RESULTS: A total of 82 patients were included in the study, 41 of whom required a hysterectomy. All patients who underwent a hysterectomy met the International Federation of Gynecology and Obstetrics clinical evidence of placenta accreta spectrum at the time of delivery. Multiple parameters of the ultrasound-based placenta accreta index and placenta accreta spectrum-magnetic resonance imaging were able to predict hysterectomy, and the parameter of greatest dimension of invasion by magnetic resonance imaging was the best quantitative predictor. At 96% sensitivity for hysterectomy, the cutoff values were 3.5 for the ultrasound-based placenta accreta index and 2.5 cm for the greatest dimension of invasion by magnetic resonance imaging. Using this sensitivity, the parameter of greatest dimension of invasion measured by magnetic resonance imaging had higher specificity (P=.0016) and a higher positive predictive value (P=.0018) than the ultrasound-based placenta accreta index, indicating an improved diagnostic threshold. CONCLUSION: In a suspected high-risk group for placenta accreta spectrum, magnetic resonance imaging identified more patients who will not need a hysterectomy than when using the ultrasound-based placenta accrete index only. Magnetic resonance imaging has the potential to aid patient counseling, surgical planning, and delivery timing, including preterm delivery decisions for patients with placenta accreta spectrum requiring hysterectomy.

The human placenta project: Funded studies, imaging technologies, and future directions.

The placenta plays a critical role in fetal development. It serves as a multi-functional organ that protects and nurtures the fetus during pregnancy. However, despite its importance, the intricacies of placental structure and function in normal and diseased states have remained largely unexplored. Thus, in 2014, the National Institute of Child Health and Human Development launched the Human Placenta Project (HPP). As of May 2023, the HPP has awarded over $101 million in research funds, resulting in 41 funded studies and 459 publications. We conducted a comprehensive review of these studies and publications to identify areas of funded research, advances in those areas, limitations of current research, and continued areas of need. This paper will specifically review the funded studies by the HPP, followed by an in-depth discussion on advances and gaps within placental-focused imaging. We highlight the progress within magnetic reasonance imaging and ultrasound, including development of tools for the assessment of placental function and structure.

Topography-based feature extraction of the human placenta from prenatal MR images.

Magnetic resonance imaging (MRI) has gained popularity in the field of prenatal imaging due to the ability to provide high quality images of soft tissue. In this paper, we presented a novel method for extracting different textural and morphological features of the placenta from MRI volumes using topographical mapping. We proposed polar and planar topographical mapping methods to produce common placental features from a unique point of observation. The features extracted from the images included the entire placenta surface, as well as the thickness, intensity, and entropy maps displayed in a convenient two-dimensional format. The topography-based images may be useful for clinical placental assessments as well as computer-assisted diagnosis, and prediction of potential pregnancy complications.

Deep learning based automatic segmentation of the placenta and uterine cavity on prenatal MR images.

Magnetic resonance imaging (MRI) has potential benefits in understanding fetal and placental complications in pregnancy. An accurate segmentation of the uterine cavity and placenta can help facilitate fast and automated analyses of placenta accreta spectrum and other pregnancy complications. In this study, we trained a deep neural network for fully automatic segmentation of the uterine cavity and placenta from MR images of pregnant women with and without placental abnormalities. The two datasets were axial MRI data of 241 pregnant women, among whom, 101 patients also had sagittal MRI data. Our trained model was able to perform fully automatic 3D segmentation of MR image volumes and achieved an average Dice similarity coefficient (DSC) of 92% for uterine cavity and of 82% for placenta on the sagittal dataset and an average DSC of 87% for uterine cavity and of 82% for placenta on the axial dataset. Use of our automatic segmentation method is the first step in designing an analytics tool for to assess the risk of pregnant women with placenta accreta spectrum.

Preterm Birth and Corticotrophin-Releasing Hormone as a Placental Clock.

Preterm birth worldwide remains a significant cause of neonatal morbidity and mortality, yet the exact mechanisms of preterm parturition remain unclear. Preterm birth is not a single condition, but rather a syndrome with a multifactorial etiology. This multifactorial nature explains why individual predictive measures for preterm birth have had limited sensitivity and specificity. One proposed pathway for preterm birth is via placentally synthesized corticotrophin-releasing hormone (CRH). CRH is a peptide hormone that increases exponentially in pregnancy and has been implicated in preterm birth because of its endocrine, autocrine, and paracrine roles. CRH has actions that increase placental production of estriol and of the transcription factor nuclear factor-κB, that likely play a key role in activating the myometrium. CRH has been proposed as part of a placental clock, with early activation of placental production resulting in preterm birth. This article will review the current understanding of preterm birth, CRH as an initiator of human parturition, and the evidence regarding the use of CRH in the prediction of preterm birth.

Pulmonary hypertension complicating pregnancy: cardiac remodeling and residual concerns.

OBJECTIVES: To assess pulmonary artery pressure and cardiac remodeling in pregnancy in women with pulmonary hypertension and compare these findings with studies done beyond three months postpartum. STUDY DESIGN: Pregnant women with pulmonary hypertension from 2006 to 2017 were studied. Pulmonary hypertension was diagnosed when the pulmonary artery pressure exceeded 30 mmHg as estimated by right ventricular systolic pressure (RVSP) on echocardiography or 20 mmHg measured directly by mean pulmonary artery pressure (PAPm) with right-heart catheterization (RHC). Disease severity was assigned using threshold cutoffs. Indices of cardiac remodeling were compared during pregnancy after 20 weeks' gestation and again beyond three months postpartum when available. Pulmonary artery pressures obtained by echocardiography versus right-heart catheterization were also compared. RESULTS: Forty-six pregnancies complicated by pulmonary hypertension in 41 women were identified. The study included 43 pregnancies that resulted in a livebirth. There were 20 women in whom studies were performed after 20 weeks' gestation and again at least 3 months postpartum or later. Pulmonary artery pressures determined during pregnancy versus beyond three months postpartum were not significantly different when measured by echocardiography (RVSP 53.5 ± 20.5 mmHg and 46.7 ± 20.4 mmHg, p = .26) in this limited cohort. In the 10 women in whom pulmonary artery pressures were measured with both echocardiography and right-heart catheterization, the former was found to significantly overestimate directly measured pulmonary artery pressure (63.3 ± 20.7 versus 37.7 ± 12.3 mmHg, p < .001). CONCLUSION: Pulmonary artery pressures did not appreciably change during pregnancy after 20 weeks' gestation compared with pressures measured again beyond three months postpartum. Women with pulmonary hypertension did not show evidence of remodeling of left ventricular mass or relative wall thickness when measured in pregnancy after 20 weeks' gestation compared with beyond three months postpartum in this limited cohort. These findings suggest that cardiac remodeling in women with pulmonary hypertension is different from that of normally pregnant women and confirms the need for careful long-term follow-up.

Automatic Segmentation of Uterine Cavity and Placenta on MR Images Using Deep Learning.

Magnetic resonance imaging (MRI) is useful for the detection of abnormalities affecting maternal and fetal health. In this study, we used a fully convolutional neural network for simultaneous segmentation of the uterine cavity and placenta on MR images. We trained the network with MR images of 181 patients, with 157 for training and 24 for validation. The segmentation performance of the algorithm was evaluated using MR images of 60 additional patients that were not involved in training. The average Dice similarity coefficients achieved for the uterine cavity and placenta were 92% and 80%, respectively. The algorithm could estimate the volume of the uterine cavity and placenta with average errors of less than 1.1% compared to manual estimations. Automated segmentation, when incorporated into clinical use, has the potential to quantify, standardize, and improve placental assessment, resulting in improved outcomes for mothers and fetuses.

CascadeNet for hysterectomy prediction in pregnant women due to placenta accreta spectrum.

In severe cases, placenta accreta spectrum (PAS) requires emergency hysterectomy, endangering the life of both mother and fetus. Early prediction may reduce complications and aid in management decisions in these high-risk pregnancies. In this work, we developed a novel convolutional network architecture to combine MRI volumes, radiomic features, and custom feature maps to predict PAS severe enough to result in hysterectomy after fetal delivery in pregnant women. We trained, optimized, and evaluated the networks using data from 241 patients, in groups of 157, 24, and 60 for training, validation, and testing, respectively. We found the network using all three paths produced the best performance, with an AUC of 87.8, accuracy 83.3%, sensitivity of 85.0, and specificity of 82.5. This deep learning algorithm, deployed in clinical settings, may identify women at risk before birth, resulting in improved patient outcomes.

Placenta Accreta Spectrum and Hysterectomy Prediction Using MRI Radiomic Features.

In women with placenta accreta spectrum (PAS), patient management may involve cesarean hysterectomy at delivery. Magnetic resonance imaging (MRI) has been used for further evaluation of PAS and surgical planning. This work tackles two prediction problems: predicting presence of PAS and predicting hysterectomy using MR images of pregnant patients. First, we extracted approximately 2,500 radiomic features from MR images with two regions of interest: the placenta and the uterus. In addition to analyzing two regions of interest, we dilated the placenta and uterus masks by 5, 10, 15, and 20 mm to gain insights from the myometrium, where the uterus and placenta overlap in the case of PAS. This study cohort includes 241 pregnant women. Of these women, 89 underwent hysterectomy while 152 did not; 141 with suspected PAS, and 100 without suspected PAS. We obtained an accuracy of 0.88 for predicting hysterectomy and an accuracy of 0.92 for classifying suspected PAS. The radiomic analysis tool is further validated, it can be useful for aiding clinicians in decision making on the care of pregnant women.