scholarly journals Automatic linear measurements of the fetal brain on MRI with deep neural networks

2021 ◽  
Author(s):  
Netanell Avisdris ◽  
Bossmat Yehuda ◽  
Ori Ben-Zvi ◽  
Daphna Link-Sourani ◽  
Liat Ben-Sira ◽  
...  
Keyword(s):  
Human Error ◽  
Brain Mri ◽  
Fetal Brain ◽  
Region Of Interest ◽  
Fetal Mri ◽  
Brain Structures ◽  
Automatic Method ◽  
Linear Measurements ◽  
Biparietal Diameter ◽  
Reliable Assessment

Abstract Purpose: Timely, accurate and reliable assessment of fetal brain development is essential to reduce short and long-term risks to fetus and mother. Fetal MRI is increasingly used for fetal brain assessment. Three key biometric linear measurements important for fetal brain evaluation are Cerebral Biparietal Diameter (CBD), Bone Biparietal Diameter (BBD), and Trans-Cerebellum Diameter (TCD), obtained manually by expert radiologists on reference slices, which is time consuming and prone to human error. The aim of this study was to develop a fully automatic method computing the CBD, BBD and TCD measurements from fetal brain MRI.Methods: The input is fetal brain MRI volumes which may include the fetal body and the mother's abdomen. The outputs are the measurement values and reference slices on which the measurements were computed. The method, which follows the manual measurements principle, consists of five stages: 1) computation of a Region Of Interest that includes the fetal brain with an anisotropic 3D U-Net classifier; 2) reference slice selection with a Convolutional Neural Network; 3) slice-wise fetal brain structures segmentation with a multiclass U-Net classifier; 4) computation of the fetal brain midsagittal line and fetal brain orientation, and; 5) computation of the measurements. Results: Experimental results on 214 volumes for CBD, BBD and TCD measurements yielded a mean difference of 1.55mm, 1.45mm and 1.23mm respectively, and a Bland-Altman 95% confidence interval (I of 3.92mm, 3.98mm and 2.25mm respectively. These results are similar to the manual inter-observer variability, and are consistent across gestational ages and brain conditions.Conclusions: The proposed automatic method for computing biometric linear measurements of the fetal brain from MR imaging achieves human level performance. It has the potential of being a useful method for the assessment of fetal brain biometry in normal and pathological cases, and of improving routine clinical practice.

scholarly journals In utero MRI identifies consequences of early-gestation alcohol drinking on fetal brain development in rhesus macaques

2020 ◽  
Vol 117 (18) ◽  
pp. 10035-10044
Author(s):  
Xiaojie Wang ◽  
Verginia C. Cuzon Carlson ◽  
Colin Studholme ◽  
Natali Newman ◽  
Matthew M. Ford ◽  
...  
Keyword(s):  
White Matter ◽  
Brain Development ◽  
Ex Vivo ◽  
Early Recognition ◽  
Brain Mri ◽  
Fetal Brain ◽  
Fetal Mri ◽  
Diffusion Anisotropy ◽  
Self Administration ◽  
White Matter Tracts

One factor that contributes to the high prevalence of fetal alcohol spectrum disorder (FASD) is binge-like consumption of alcohol before pregnancy awareness. It is known that treatments are more effective with early recognition of FASD. Recent advances in retrospective motion correction for the reconstruction of three-dimensional (3D) fetal brain MRI have led to significant improvements in the quality and resolution of anatomical and diffusion MRI of the fetal brain. Here, a rhesus macaque model of FASD, involving oral self-administration of 1.5 g/kg ethanol per day beginning prior to pregnancy and extending through the first 60 d of a 168-d gestational term, was utilized to determine whether fetal MRI could detect alcohol-induced abnormalities in brain development. This approach revealed differences between ethanol-exposed and control fetuses at gestation day 135 (G135), but not G110 or G85. At G135, ethanol-exposed fetuses had reduced brainstem and cerebellum volume and water diffusion anisotropy in several white matter tracts, compared to controls. Ex vivo electrophysiological recordings performed on fetal brain tissue obtained immediately following MRI demonstrated that the structural abnormalities observed at G135 are of functional significance. Specifically, spontaneous excitatory postsynaptic current amplitudes measured from individual neurons in the primary somatosensory cortex and putamen strongly correlated with diffusion anisotropy in the white matter tracts that connect these structures. These findings demonstrate that exposure to ethanol early in gestation perturbs development of brain regions associated with motor control in a manner that is detectable with fetal MRI.

scholarly journals Fetal and Postnatal Brain Imaging for the Detection of ZIKV Encephalopathy in the Fetus/Newborn

2017 ◽  
Vol 4 (suppl_1) ◽  
pp. S22-S22
Author(s):  
Sarah Mulkey ◽  
Gilbert Vezina ◽  
Yamil Fourzali ◽  
Dorothy Bulas ◽  
Margarita Arroyave-Wessel ◽  
...  
Keyword(s):  
Pregnant Women ◽  
Imaging Modality ◽  
Brain Mri ◽  
Cerebellar Atrophy ◽  
Fetal Brain ◽  
Fetal Mri ◽  
Zikv Infection ◽  
Chiari Ii ◽  
Brain Changes ◽  
Prospective Longitudinal

Abstract Background Up to 15% of pregnancies complicated by maternal ZIKV infection result in Zika-virus associated brain abnormalities in the fetus/newborn. Fetal ultrasound (feUS) is the standard imaging modality for the evaluation of fetal anatomy and for brain changes from congenital infection. Fetal MRI (feMRI) may be a useful adjunct. Methods We performed a prospective longitudinal neuroimaging study of fetuses/newborns of pregnant women with clinical and/or lab confirmed (RT-PCR and/or IgM/PRNT) diagnosis of Zika infection in Barranquilla, Colombia (endemic) and in Washington, DC, USA (travel-related). Gestational age (GA) at exposure and timing between ZIKV exposure/symptoms and imaging was documented. Subjects had one to two feMRIs and feUS, depending upon GA at enrollment. The feMRI and feUS protocols were standardized between sites and studies were centrally interpreted at Children’s National. Postnatally, infants received an unsedated brain MRI and head US. Results Forty-eight, ZIKV exposed/infected in first or second trimester pregnant women were enrolled (46 Colombia, 2 USA). Subjects had symptoms of ZIKV infection at mean of 8.4±5.7 week GA. The first feMRI and feUS were performed at 25.1±6.3 week GA. Thirty-six infants had a second feMRI and feUS at 31.1±4.2 week GA. Three of 48 (6%) cases had an abnormal feMRI: (1) heterotopias and abnormal cortical indent; (2) parietal encephalocele and Chiari II; (3) thin corpus callosum, dysplastic brainstem, temporal cysts, subependymal heterotopias, and generalized cerebral/cerebellar atrophy. FeUS in these three cases found (1) normal study; (2) parietal encephalocele and Chiari II; (3) significant ventriculomegaly with decreasing percentiles of head circumference from 32 to 36 week GA (38% to 3.6%). Postnatal head US revealed findings not seen on feUS: choroid plexus or germinal matrix cysts in nine infants and lenticulostriate vasculopathy in one infant. Conclusion FeMRI and feUS provide complimentary information in the assessment of fetal brain changes in ZIKV. In cases of abnormal brain structure, feMRI reveals more extensive areas of brain damage than is seen by US. Further studies are needed to determine whether cystic changes on postnatal head US are related to ZIKV infection, or are incidental findings. Disclosures All authors: No reported disclosures.

scholarly journals 4252 Automated Fetal Brain Volumetry on Clinical Fetal MRI Using Convolutional Neural Network

2020 ◽  
Vol 4 (s1) ◽  
pp. 45-46
Author(s):  
Carol Tran ◽  
Orit Glenn ◽  
Christopher Hess ◽  
Andreas Rauschecker
Keyword(s):  
Neural Network ◽  
Deep Learning ◽  
Convolutional Neural Network ◽  
Network Architecture ◽  
Brain Volume ◽  
Brain Mri ◽  
Fetal Brain ◽  
Fetal Mri ◽  
Total Brain Volume ◽  
Brain Volumes

OBJECTIVES/GOALS: We seek to develop an automated deep learning-based method for segmentation and volumetric quantification of the fetal brain on T2-weighted fetal MRIs. We will evaluate the performance of the algorithm by comparing it to gold standard manual segmentations. The method will be used to create a normative sample of brain volumes across gestational ages. METHODS/STUDY POPULATION: We will adapt a U-Net convolutional neural network architecture for fetal brain MRIs using 3D volumes. After re-sampling 2D fetal brain acquisitions to 3mm3 3D volumes using linear interpolation, the network will be trained to perform automated brain segmentation on 40 randomly-sampled, normal fetal brain MRI scans of singleton pregnancies. Training will be performed in 3 acquisition planes (axial, coronal, sagittal). Performance will be evaluated on 10 test MRIs (in 3 acquisition planes, 30 total test samples) using Dice scores, compared to radiologists’ manual segmentations. The algorithm’s performance on measuring total brain volume will also be evaluated. RESULTS/ANTICIPATED RESULTS: Based on the success of prior U-net architectures for volumetric segmentation tasks in medical imaging (e.g. Duong et al., 2019), we anticipate that the convolutional neural network will accurately provide segmentations and associated volumetry of fetal brains in fractions of a second. We anticipate median Dice scores greater than 0.8 across our test sample. Once validated, the method will retrospectively generate a normative database of over 1500 fetal brain volumes across gestational ages (18 weeks to 30 weeks) collected at our institution. DISCUSSION/SIGNIFICANCE OF IMPACT: Quantitative estimates of brain volume, and deviations from normative data, would be a major advancement in objective clinical assessments of fetal MRI. Such data can currently only be obtained through laborious manual segmentations; automated deep learning methods have the potential to reduce the time and cost of this process.

scholarly journals Ultrasound vs Magnetic Resonance in the Assessment of CNS Anomalies

2013 ◽  
Vol 7 (4) ◽  
pp. 496-499
Author(s):  
Snezana Crnogorac ◽  
Aleksandar Jurišić ◽  
Aleksandar Grdinić
Keyword(s):  
Magnetic Resonance ◽  
Congenital Abnormalities ◽  
Fetal Brain ◽  
Vascular Anatomy ◽  
Fetal Mri ◽  
Brain Structures ◽  
3D Ultrasound ◽  
Brain Maturation ◽  
Normal Brain ◽  
Cns Anomalies

ABSTRACT Central nervous system (CNS) malformations are some of the most comon congenital abnormalities. Long-term follow-up studies suggest that the incidence may be as high as 1 in 100 births. Imaging technologies have been remarkably improved and contributed to prenatal evaluation of fetal CNS development and assessment of CNS abnormalities. The routine examination of the fetal brain can be achieved with axial planes by conventional transabdominal ultrasonography. In order to provide a complete view of the different brain structures a detailed fetal neurosonogram requires additional coronal and sagittal views. Three-dimensional (3D) sonography should be performed transvaginally using the multiplanar approach. Transvaginal high-resolution 3D ultrasound can demonstrate cerebral fine vascular anatomy such as medullary vessels, intracranial calcification, vascular abnormalities. Parallel slicing provides a tomographic visualization of internal morphology similar to magnetic resonance imaging (MRI). Fetal MRI appears to be a useful adjunct to ultrasound to confirm or exclude certain abnormalities. MRI is a valuable complementary tool to detailed neurosonography which allows an evaluation of the normal brain maturation from the second trimester. It also offers a higher diagnostic performance for some congenital abnormalities such as cortical development or posterior fossa assessment. How to cite this article Crnogorac S, JuriÓiƒ A, Grdiniƒ A. Ultrasound vs Magnetic Resonance in the Assessment of CNS Anomalies. Donald School J Ultrasound Obstet Gynecol 2013;7(4):496-499.

scholarly journals VP24.11: Prenatal alcohol exposure affects specific fetal brain structures: an atlas‐based fetal MRI study

2021 ◽  
Vol 58 (S1) ◽  
pp. 203-203
Author(s):  
M. Stuempflen ◽  
E. Schwartz ◽  
M.C. Diogo ◽  
S. Glatter ◽  
B. Pfeiler ◽  
...  
Keyword(s):  
Prenatal Alcohol Exposure ◽  
Fetal Brain ◽  
Fetal Mri ◽  
Alcohol Exposure ◽  
Brain Structures ◽  
Prenatal Alcohol ◽  
Mri Study

Added Value of Fetal MRI in the Evaluation of Fetal Anomalies of the Corpus Callosum: A Retrospective Analysis of 78 Cases

2018 ◽  
Vol 39 (05) ◽  
pp. 513-525 ◽  
Author(s):  
Mirra Manevich-Mazor ◽  
Alina Weissmann-Brenner ◽  
Omer Bar Yosef ◽  
Chen Hoffmann ◽  
Roei Mazor ◽  
...  
Keyword(s):  
Decision Making ◽  
Corpus Callosum ◽  
Clinical Decision Making ◽  
Brain Mri ◽  
Fetal Brain ◽  
Fetal Mri ◽  
Clinical Decision ◽  
Added Value ◽  
Callosal Agenesis

Abstract Objective To evaluate the added value of fetal MRI to ultrasound in detecting and specifying callosal anomalies, and its impact on clinical decision making. Methods Fetuses with a sonographic diagnosis of an anomalous corpus callosum (CC) who underwent a subsequent fetal brain MRI between 2010 and 2015 were retrospectively evaluated and classified according to the severity of the findings. The findings detected on ultrasound were compared to those detected on MRI. An analysis was performed to assess whether fetal MRI altered the group classification, and thus the management of these pregnancies. Results 78 women were recruited following sonographic diagnoses of either complete or partial callosal agenesis, short, thin or thick CC. Normal MRI studies were obtained inµ19 cases (24 %). Among these, all children available for follow-up received an adequate adaptive score in their Vineland II adaptive behavior scale assessment. Analysis of the concordance between US and MRI demonstrated a substantial level of agreement for complete callosal agenesis (kappa: 0.742), moderate agreement for thin CC (kappa: 0.418) and fair agreement for all other callosal anomalies. Comparison between US and MRI-based mild/severe findings classifications revealed that MRI contributed to a change in the management for 28 fetuses (35.9 %), mostly (25 fetuses, 32.1 %) in favor of pregnancy preservation. Conclusion Fetal MRI effectively detects callosal anomalies and enables satisfactory validation of the presence or absence of callosal anomalies identified by ultrasound and adds valuable data that improves clinical decision making.

scholarly journals A Case of Apert Syndrome: Early Detection of Temporal Lobe Abnormalities and Scalp Cyst in Fetal Brain MRI

2020 ◽  
Vol 30 (6) ◽  
Author(s):  
Ahmad Reza Tahmasebpour ◽  
Behnaz Moradi ◽  
Mohammad Ali Kazemi
Keyword(s):  
Temporal Lobe ◽  
Brain Mri ◽  
Fetal Brain ◽  
Fetal Mri ◽  
First Trimester ◽  
Apert Syndrome ◽  
Imaging Features ◽  
Calvarial Bone ◽  
First Case ◽  
Fgfr2 Gene

Introduction: Apert Syndrome is one of the severe forms of craniosynostosis syndromes. Here we present the first case of 20 weeks fetus with temporal lobe abnormalities with a scalp cyst in fetal MRI. Case Presentation: A 34-year-old woman at 19 weeks of pregnancy presented with normal first trimester scan and with acrocephaly, mild ventriculomegaly (10.5 mm), hypertelorism, and mitten glove syndactyly of hands of the fetus in second trimester ultrasound scan. Also a scalp cyst without calvarial bone defect was found. One week later, fetal brain MRI on 1.5 T scanner confirmed 2D ultrasound findings. Also bilateral temporal lobe overconvolution and low set ears were detected by MRI. These imaging features strongly suggested Apert or a related craniosynostosis syndrome. Amniocentesis result revealed the heterozygous FGFR2 gene mutation consistent with Apert syndrome. Conclusions: Fetal MRI and ultrasound are complementary tools for full evaluation of different aspects of a syndromic condition in fetus that is very important for proper genetic testing and counseling.

scholarly journals The Reliability of Fetal MRI in the Assessment of Brain Malformations

2014 ◽  
Vol 37 (2) ◽  
pp. 93-101 ◽  
Author(s):  
Nora Frick ◽  
Claudius Fazelnia ◽  
Kathrin Kanzian ◽  
Wolfgang Hitzl ◽  
Thorsten Fischer ◽  
...  
Keyword(s):  
Corpus Callosum ◽  
Brain Mri ◽  
Intraclass Correlation ◽  
Fetal Brain ◽  
Fetal Mri ◽  
Intraobserver Reliability ◽  
Mri Findings ◽  
The Third ◽  
Brain Malformations ◽  
Mri Measurements

Objectives: To assess the inter- and intraobserver reliability of different fetal MRI measurements in cases of fetal brain malformations and to examine the concordance between ultrasonography (US) and MRI findings. Methods: Fetal brain MRIs and US findings of 56 pregnant women were retrieved from the institutional database. Standardized fetal brain MRI measurements were performed by 4 observers, and the inter- and intraobserver reliability was determined. Additionally, US and MRI findings were retrospectively compared. Results: The interobserver intraclass correlation coefficient (ICC) was above 0.9 for the cerebellum and posterior horn of the lateral ventricle. The measurements regarding the third ventricle (0.50), the fourth ventricle (0.58), and the corpus callosum (0.63) showed poor reliability. Overall, the intraobserver reliability was greater than the interobserver reliability. US and MRI findings were discordant in 29% of the cases with MRI rendering an extended diagnosis in 18%, a change of diagnosis in 3.6%, and excluding pathological findings suspected on US in 7.1%. Conclusions: Fetal MRI is a valuable complement to US in the investigation of fetal brain malformations. The reliability of most parameters was high, except for the measurements of the third and fourth ventricles and the corpus callosum.

New normal range of fetal cavum septum pellucidum in the second trimester of gestation

2020 ◽  
Author(s):  
M.V. Medvedev, O.I. Kozlova, À.Yu. Romanova
Keyword(s):  
Brain Development ◽  
Reference Range ◽  
Fetal Brain ◽  
Septum Pellucidum ◽  
Second Trimester ◽  
Normal Range ◽  
Cavum Septum Pellucidum ◽  
New Normal ◽  
Biparietal Diameter ◽  
Fetal Brain Development

Fetal brain was retrospectively evaluated in 418 normal fetuses at 16–28 weeks of gestation. The multiplanar mode to obtain the axial cerebral plane and measured the width of the cavum septum pellucidum (CSP) and biparietal diameter (BD). All measurements of CSP were done from as the widest diameter across both borders in an inter-to inter fashion. The CSP width is increasing at second trimester of gestation. Normal range plotted on the reference range (mean, 5th and 95th percentiles) of fetal width CSP by measuring of its size may be useful for assessment of fetal brain development in the second trimester of gestation.

scholarly journals Automatic linear measurements of the fetal brain on MRI with deep neural networks

2021 ◽  
Author(s):  
Netanell Avisdris ◽  
Bossmat Yehuda ◽  
Ori Ben-Zvi ◽  
Daphna Link-Sourani ◽  
Liat Ben-Sira ◽  
...  
Keyword(s):  
Neural Networks ◽  
Deep Neural Networks ◽  
Fetal Brain ◽  
Linear Measurements
Sign in / Sign up

Export Citation Format

Share Document