Dataset Information

Validation of a semiautomated volumetric approach for fetal neurosonography using 5DCNS+ in clinical data from >?1100 consecutive pregnancies.

ABSTRACT: OBJECTIVE:The aim of this study was to evaluate the validity of a semiautomated volumetric approach (5DCNS+) for the detailed assessment of the fetal brain in a clinical setting. METHODS:Stored 3D volumes of >?1100 consecutive 2nd and 3rd trimester pregnancies (range 15-36 gestational weeks) were analyzed using a workflow-based volumetric approach 5DCNS+, enabling semiautomated reconstruction of diagnostic planes of the fetal central nervous system (CNS). All 3D data sets were examined for plane accuracy, the need for manual adjustment, and fetal-maternal characteristics affecting successful plane reconstruction. We also examined the potential of these standardized views to give additional information on proper gyration and sulci formation with advancing gestation. RESULTS:Based on our data, we were able to show that gestational age with an OR of 1.085 (95% CI 1.041-1.132) and maternal BMI with an OR of 1.022 (95% CI 1.041-1.054) only had a slight impact on the number of manual adjustments needed to reconstruct the complete volume, while maternal age and fetal position during acquisition (p?=?0.260) did not have a significant effect. For the vast majority (958/1019; 94%) of volumes, using 5DCNS+ resulted in proper reconstruction of all nine diagnostic planes. In less than 1% (89/9171 planes) of volumes, the program failed to give sufficient information. 5DCNS+ was able to show the onset and changing appearance of CNS folding in a detailed and timely manner (lateral/parietooccipital sulcus formation seen in

SUBMITTER: Welp A

PROVIDER: S-EPMC7649164 | biostudies-literature | 2020 Dec

REPOSITORIES: biostudies-literature

ACCESS DATA

Publications

Validation of a semiautomated volumetric approach for fetal neurosonography using 5DCNS+ in clinical data from > 1100 consecutive pregnancies.

Welp Amrei A Gembicki Michael M Rody Achim A Weichert Jan J

Child's nervous system : ChNS : official journal of the International Society for Pediatric Neurosurgery 20200430 12

<h4>Objective</h4>The aim of this study was to evaluate the validity of a semiautomated volumetric approach (5DCNS+) for the detailed assessment of the fetal brain in a clinical setting.<h4>Methods</h4>Stored 3D volumes of > 1100 consecutive 2nd and 3rd trimester pregnancies (range 15-36 gestational weeks) were analyzed using a workflow-based volumetric approach 5DCNS+, enabling semiautomated reconstruction of diagnostic planes of the fetal central nervous system (CNS). All 3D data sets were exa ...[more]

PMID: 32350601

Similar Datasets

Project description:Three-dimensional (3D) fetal neurosonography is used clinically to detect cerebral abnormalities and to assess growth in the developing brain. However, manual identification of key brain structures in 3D ultrasound images requires expertise to perform and even then is tedious. Inspired by how sonographers view and interact with volumes during real-time clinical scanning, we propose an efficient automatic method to simultaneously localize multiple brain structures in 3D fetal neurosonography. The proposed View-based Projection Networks (VP-Nets), uses three view-based Convolutional Neural Networks (CNNs), to simplify 3D localizations by directly predicting 2D projections of the key structures onto three anatomical views. While designed for efficient use of data and GPU memory, the proposed VP-Nets allows for full-resolution 3D prediction. We investigated parameters that influence the performance of VP-Nets, e.g. depth and number of feature channels. Moreover, we demonstrate that the model can pinpoint the structure in 3D space by visualizing the trained VP-Nets, despite only 2D supervision being provided for a single stream during training. For comparison, we implemented two other baseline solutions based on Random Forest and 3D U-Nets. In the reported experiments, VP-Nets consistently outperformed other methods on localization. To test the importance of loss function, two identical models are trained with binary corss-entropy and dice coefficient loss respectively. Our best VP-Net model achieved prediction center deviation: 1.8 ± 1.4 mm, size difference: 1.9 ± 1.5 mm, and 3D Intersection Over Union (IOU): 63.2 ± 14.7% when compared to the ground truth. To make the whole pipeline intervention free, we also implement a skull-stripping tool using 3D CNN, which achieves high segmentation accuracy. As a result, the proposed processing pipeline takes a raw ultrasound brain image as input, and output a skull-stripped image with five detected key brain structures.

Project description:BackgroundThe common use of singleton fetal growth standard to access twin growth might lead to over-monitoring and treatment. We aimed to develop fetal growth standards for Chinese twins based on ultrasound measurements, and compare it with Zhang's and other twin fetal growth charts.MethodsA cohort of uncomplicated twin pregnancies were prospectively followed in 2014-2017. Smoothed estimates of fetal growth percentiles for both monochorionic (MC) and dichorionic (DC) twins were obtained using a linear mixed model. We also created growth charts for twins using a model-based approach proposed by Zhang et al. Our twin standards were compared with Hadlock's (singleton) in predicting adverse perinatal outcomes.ResultsA total of 398 twin pregnancies were included, with 214 MC and 582 DC live-born twins. The MC twins were slightly lighter than the DC twins, with small differences throughout the gestation. Our ultrasound-based fetal weight standards were comparable to that using Zhang's method. Compared with previous references/standards from the US, Brazil, Italy and UK, our twins had very similar 50th percentiles, but narrower ranges between the 5th and 95th or 10th and 90th percentiles. Compared with the Hadlock's standard, the risks of neonatal death and adverse perinatal outcomes for small for gestational age (SGA) versus non-SGA were substantially elevated using our standards.ConclusionsA normal fetal growth standard for Chinese twins was created. The differences between MC and DC twins were clinically insignificant. The 50th weight percentiles of the Chinese twins were identical to those in other races/ethnicities but the ranges were markedly narrower. Our standard performed much better than the Hadlock's in predicting low birth weight infants associated with adverse perinatal outcomes in twin pregnancies. The present study also indicated that Zhang's method is applicable to Chinese twins, and other areas may use Zhang's method to generate their own curves for twins if deemed necessary.

Project description:The potential toxicity of background exposure to perfluoroalkyl substances (PFASs) is currently under active investigation. Such investigations typically rely on a single measure of PFAS concentration, yet the longer-term reliability of a single measure has not been well characterized, especially among reproductive-aged women. Our aim was to investigate the association between PFAS plasma concentrations of 100 women in two consecutive pregnancies and explore changes in plasma concentration related to reproductive factors. The women in our study were enrolled in the Norwegian Mother and Child Cohort Study (MoBa) from 2003 to 2009. About half of them breastfed exclusively for 6 months and the rest of the participants did not breastfeed between the two consecutive pregnancies (median time between pregnancies: 18 months). Maternal blood was collected at mid-pregnancy and plasma was analyzed for 10 PFASs. Statistical analyses were restricted to 6 PFASs that were quantifiable in more than 80% of the samples. We estimated the correlation between repeated PFAS measurements, the percentage change between pregnancies and the effect of several reproductive factors in multivariate linear regression models of PFAS concentrations in the second pregnancy. The Pearson correlation coefficient between repeated PFAS measurements was, for perfluorooctane sulfonate (PFOS), 0.80; perfluorooctanoate (PFOA), 0.50; perfluorohexane sulfonate (PFHxS), 0.74; perfluorononanoate (PFNA), 0.39; perfluoroundecanoate (PFUnDA), 0.71; and perfluorodecanoate (PFDA), 0.60. Adjustment for maternal age, delivery year, and time and breastfeeding between pregnancies did not substantially affect the observed correlations. We found 44-47% median reductions in the concentrations of PFOS, PFOA and PFHxS between pregnancies, while the change in concentrations between pregnancies was smaller and more variable for PFNA, PFUnDA and PFDA. The variation in plasma concentrations in the second pregnancy was mainly accounted for by the concentration in the first pregnancy; for PFOS, PFOA, and PFNA, breastfeeding also accounted for a substantial proportion. In conclusion, we found the reliability of PFAS measurements in maternal plasma to be moderate to high, and in these data, several factors, especially breastfeeding, were related to plasma concentrations.

Dataset Information

Validation of a semiautomated volumetric approach for fetal neurosonography using 5DCNS+ in clinical data from >?1100 consecutive pregnancies.

Publications

Validation of a semiautomated volumetric approach for fetal neurosonography using 5DCNS+ in clinical data from > 1100 consecutive pregnancies.

Similar Datasets

OmicsDI is part of the ELIXIR infrastructure

Tweets