Comparison of 2-D and 3-D estimates of placental volume in early pregnancy

Two-dimensional (2D) placental ultrasound measurements - The correlation with placental volume measured by magnetic resonance imaging (MRI)

INTRODUCTION

Information about placental size in ongoing pregnancies may aid the identification of pregnancies with increased risk of adverse outcome. Placental volume can be measured using magnetic resonance imaging (MRI). However, this method is not universally available in antenatal care. Ultrasound is the diagnostic tool of choice in pregnancy. Therefore, we studied whether simple two-dimensional (2D) ultrasound placental measurements were correlated with placental volume measured by MRI.

METHODS

We examined a convenience sample of 104 ongoing pregnancies at gestational week 27, using both ultrasound and MRI. The ultrasound measurements included placental length, width and thickness. Placental volume was measured using MRI. The correlation between each 2D placental ultrasound measurement and placental volume was estimated by applying Pearson's correlation coefficient (r).

RESULTS

Mean placental length was 17.2 cm (SD 2.1 cm), mean width was 14.7 cm (SD 2.1 cm), and mean thickness was 3.2 cm (SD 0.6 cm). Mean placental volume was 536 cm3 (SD 137 cm3). The 2D ultrasound measurements showed poor correlation with placental volume (placental length; r = 0.27, width; r = 0.37, and thickness r = 0.13).

DISCUSSION

Simple 2D ultrasound measurements of the placenta were poorly correlated with placental volume and cannot be used as proximate measures of placental volume. Our finding may be explained by the large variation between pregnancies in intrauterine placental shape.

Multiscale and multimodal imaging of utero-placental anatomy and function in pregnancy

Placental structures at the nano-, micro-, and macro scale each play important roles in contributing to its function. As such, quantifying the dynamic way in which placental structure evolves during pregnancy is critical to both clinical diagnosis of pregnancy disorders, and mechanistic understanding of their pathophysiology. Imaging the placenta, both exvivo and invivo, can provide a wealth of structural and/or functional information. This review outlines how imaging across modalities and spatial scales can ultimately come together to improve our understanding of normal and pathological pregnancies. We discuss how imaging technologies are evolving to provide new insights into placental physiology across disciplines, and how advanced computational algorithms can be used alongside state-of-the-art imaging to obtain a holistic view of placental structure and its associated functions to improve our understanding of placental function in health and disease.

Automated Placenta Segmentation with a Convolutional Neural Network Weighted by Acoustic Shadow Detection

Placental assessment through routine obstetrical ultrasound is often limited to documenting its location and ruling out placenta previa. However, many obstetrical complications originate from abnormal focal or global placental development. Technical difficulties in assessing the placenta as well as a lack of established objective criteria to classify echotexture are barriers to diagnosis of pathology by ultrasound imaging. As a first step towards the development of a computer aided placental assessment tool, we developed a fully automated method for placental segmentation using a convolutional neural network. The network contains a novel layer weighted by automated acoustic shadow detection to recognize artifacts specific to ultrasound. In order to develop a detection algorithm usable in different imaging scenarios, we acquired a dataset containing 1364 fetal ultrasound images from 247 patients acquired over 47 months was taken with different machines, operators, and at a range of gestational ages. Mean Dice coefficients for automated segmentation on the full dataset with and without the acoustic shadow detection layer were 0.92±0.04 and 0.91±0.03 when comparing to manual segmentation. Mean Dice coefficients on the subset of images containing acoustic shadows with and without acoustic shadow detection were 0.87±0.04 and 0.75±0.05. The method requires no user input to tune the detection. The automated placenta segmentation method can serve as a preprocessing step for further image analysis in artificial intelligence methods requiring large scale data processing of placental images.

Volume and vascularity: Using ultrasound to unlock the secrets of the first trimester placenta

Fetal growth restriction (FGR) is a major cause of perinatal morbidity and mortality. Identifying which pregnancies are at risk of FGR facilitates enhanced surveillance and early delivery before fetal demise can ensue. However, existing risk stratification strategies yield an unacceptably low detection rate. A robust and reliable first trimester screening test for FGR would not only enable high-risk women to be appropriately monitored but would facilitate future trials for possible interventions to enhance fetal growth. Both the volume and vascularity of the first trimester placenta has been demonstrated to be linked to adverse pregnancy outcomes including FGR and pre-eclampsia. The investigation of novel ultrasound markers for FGR are discussed along with the development of methods for fully automatic placental volume estimation which has the potential for use as part of a multi-variable population-based screening test.

A retrospective segmentation analysis of placental volume by magnetic resonance imaging from first trimester to term gestation

BACKGROUND

Abnormalities of the placenta affect 5-7% of pregnancies. Because disturbances in fetal growth are often preceded by dysfunction of the placenta or attenuation of its normal expansion, placental health warrants careful surveillance. There are limited normative data available for placental volume by MRI.

OBJECTIVE

To determine normative ranges of placental volume by MRI throughout gestation.

MATERIALS AND METHODS

In this cross-sectional retrospective analysis, we reviewed MRI examinations of pregnant females obtained between 2002 and 2017 at a single institution. We performed semi-automated segmentation of the placenta in images obtained in patients with no radiologic evidence of maternal or fetal pathology, using the Philips Intellispace Tumor Tracking Tool.

RESULTS

Placental segmentation was performed in 112 women and had a high degree of interrater reliability (single-measure intraclass correlation coefficient =0.978 with 95% confidence interval [CI] 0.956, 0.989; P<0.001). Normative data on placental volume by MRI increased nonlinearly from 6 weeks to 39 weeks of gestation, with wider variability of placental volume at higher gestational age (GA). We fit placental volumetric data to a polynomial curve of third order described as placental volume = -0.02*GA³ + 1.6*GA² - 13.3*GA + 8.3. Placental volume showed positive correlation with estimated fetal weight (P=0.03) and birth weight (P=0.05).

CONCLUSION

This study provides normative placental volume by MRI from early first trimester to term gestation. Deviations in placental volume from normal might prove to be an imaging biomarker of adverse fetal health and neonatal outcome, and further studies are needed to more fully understand this metric. Assessment of placental volume should be considered in all routine fetal MRI examinations.

Reference ranges of placental volume measured by virtual organ computer-aided analysis between 10 and 14 weeks of gestation

OBJECTIVE

To establish the reference ranges of the placental volume between 10 and 14 weeks of gestation of Thai fetuses.

METHODS

The placental volumes were acquired in normal pregnancies between 10 and 14 weeks of gestation using transabdominal three-dimensional ultrasound. The placental volume was then analyzed using VOCAL (virtual organ computer-aided analysis) technique with a rotation angle of 30°. The measured values were regressed to identify the best-fit model.

RESULTS

A total of 236 volume datasets met the inclusion criteria and were used for offline analysis. Placental volume significantly increased with increasing crown-rump length (CRL). The best-fit regression models for predicted mean and SD as a function of CRL, available for z score calculation and construction of the percentile chart, are as follows: [Formula: see text] CONCLUSION: Reference ranges of placental volume have been constructed. This normative data may be a useful tool in the evaluation of various conditions affecting placental size, eg, fetal hemoglobin Bart's disease. © 2016 Wiley Periodicals, Inc. J Clin Ultrasound 45:185-191, 2017.

3-D Ultrasound Segmentation of the Placenta Using the Random Walker Algorithm: Reliability and Agreement

Volumetric segmentation of the placenta using 3-D ultrasound is currently performed clinically to investigate correlation between organ volume and fetal outcome or pathology. Previously, interpolative or semi-automatic contour-based methodologies were used to provide volumetric results. We describe the validation of an original random walker (RW)-based algorithm against manual segmentation and an existing semi-automated method, virtual organ computer-aided analysis (VOCAL), using initialization time, inter- and intra-observer variability of volumetric measurements and quantification accuracy (with respect to manual segmentation) as metrics of success. Both semi-automatic methods require initialization. Therefore, the first experiment compared initialization times. Initialization was timed by one observer using 20 subjects. This revealed significant differences (p < 0.001) in time taken to initialize the VOCAL method compared with the RW method. In the second experiment, 10 subjects were used to analyze intra-/inter-observer variability between two observers. Bland-Altman plots were used to analyze variability combined with intra- and inter-observer variability measured by intra-class correlation coefficients, which were reported for all three methods. Intra-class correlation coefficient values for intra-observer variability were higher for the RW method than for VOCAL, and both were similar to manual segmentation. Inter-observer variability was 0.94 (0.88, 0.97), 0.91 (0.81, 0.95) and 0.80 (0.61, 0.90) for manual, RW and VOCAL, respectively. Finally, a third observer with no prior ultrasound experience was introduced and volumetric differences from manual segmentation were reported. Dice similarity coefficients for observers 1, 2 and 3 were respectively 0.84 ± 0.12, 0.94 ± 0.08 and 0.84 ± 0.11, and the mean was 0.87 ± 0.13. The RW algorithm was found to provide results concordant with those for manual segmentation and to outperform VOCAL in aspects of observer reliability. The training of an additional untrained observer was investigated, and results revealed that with the appropriate initialization protocol, results for observers with varying levels of experience were concordant. We found that with appropriate training, the RW method can be used for fast, repeatable 3-D measurement of placental volume.