Learning-based prediction of gestational age from ultrasound images of the fetal brain

Namburete, Ana I. L.; Stebbing, Richard V.; Kemp, B.; Yaqub, Mohammad; Papageorghiou, Aris T.; Noble, J. Alison

doi:10.1016/j.media.2014.12.006

Cited by 75 publications

(67 citation statements)

References 58 publications

(86 reference statements)

Supporting

Mentioning

Contrasting

Order By: Relevance

“…Further, these measures could be developed as machine-learning algorithms for more accuracy while predicting preterm births. 69 She emphasized that using ultrasound and new predictive tools, one could go beyond what meets the eye to develop non-invasive markers for placental measurements and to access the functionality of this tissue.…”

Section: 67mentioning

confidence: 99%

Provocative ideas on human placental biology: A prerequisite for prevention and treatment of neonatal health challenges

Sehgal

Bhatnagar

Pallavi

2017

American J Rep Immunol

View full text Add to dashboard Cite

this meeting were the critical evaluation of placental physiology and its development.Special emphasis was placed on understanding the consequences and implications of placental development in sustenance of pregnancy and in pregnancy-associated complications such as preeclampsia, intrauterine growth restriction, and preterm birth.This meeting brought together experienced as well as novice clinicians and biologists who have a keen interest in the field of placental biology, including development of new technologies and methods for evaluating the role of placenta in predicting pregnancy outcomes. The meeting primarily focused on (i) high-throughput "-omics" approaches, (ii) maternal nutrition and placental function, (iii) placental infection and inflammation, (iv) real-time evaluation of placental development: tools for placental research, and (v) epidemiologic relevance of placental-based research. Unanimous consensus emerged among the participants to carry out additional work focused on these areas. In this article, we summarize the talks and review the published literature on the above-mentioned niches. As a direct outcome of this meeting, a request for applications has been announced by the Department of Biotechnology, Government of India, for pursuing research in this vital but understudied domain. K E Y W O R D Sclinical imaging, epidemiology, maternal nutrition, omics, placenta | LAYING THE BACKGROUNDProf. Renu Dhingra, Department of Anatomy, All India Institute of Medical Sciences, New Delhi, introduced the basics of placental anatomy and development. Placenta is a noteworthy organ that has evolved to support fetus in utero and is likely to be the key determinant of fetal growth. Formation of placenta requires a developmental progression, which proceeds in a specific order over time, specified by the trophoblast but dependent on maternal environment for correct expression.The trophoblast of the embedded/implanted blastocyst differentiates into two cellular layers inner mononuclear cytotrophoblast and outer multinucleated syncytiotrophoblast. Development of this discoid, chorioallantoic, and haemochorial human placenta is then characterized by lacunar and villous stages thus giving rise to primary, secondary, and tertiary chorionic villi. The development of placenta is not autonomous but is affected by maternal, periconceptional, genetic, and immune factors, which further influence the process of implantation, spiral artery remodeling, uteroplacental blood flow, and thus placental supply of nutrients and oxygen to fetus. Placental structural and functional abnormalities may not only cause numerous adverse pregnancy outcomes but also affect the long-term health of both mother and offspring. Thus, increasing the understanding of its structure and

show abstract

Section: 67mentioning

confidence: 99%

Provocative ideas on human placental biology: A prerequisite for prevention and treatment of neonatal health challenges

Sehgal

Bhatnagar

Pallavi

2017

American J Rep Immunol

View full text Add to dashboard Cite

show abstract

“…The fetal brain age of the healthy control cases was calculated by the age prediction algorithm. This cohort of normal fetuses showed a calculated brain age by the algorithm which did not differ statistically from the true GA based on first‐trimester ultrasound, suggesting the model is applicable to our cohort. The predicted brain age increased in a perfectly linear way in the second trimester and the algorithm tends slightly to underestimate the brain age during the third trimester (Figure ).…”

Section: Resultsmentioning

confidence: 74%

“…Plane localization was annotated manually in each 3D volume using the ITK‐SNAP tool . The algorithmic details on the process of predicting brain maturation from a 3D ultrasound volume were previously described . Briefly, a 3D surface‐based coordinate system is spatially aligned to the cranial pixels in the image.…”

Section: Methodsmentioning

confidence: 99%

See 1 more Smart Citation

Cortical development in fetuses with congenital heart defects using an automated brain‐age prediction algorithm

Everwijn

Namburete

Geloven

et al. 2019

Acta Obstet Gynecol Scand

Self Cite

View full text Add to dashboard Cite

Introduction Congenital heart defects are associated with neurodevelopmental delay. It is hypothesized that fetuses affected by congenital heart defect have altered cerebral oxygen perfusion and are therefore prone to delay in cortical maturation. The aim of this study was to determine the difference in fetal brain age between consecutive congenital heart defect cases and controls in the second and third trimester using ultrasound. Material and methods Since 2014, we have included 90 isolated severe congenital heart defect cases in the Heart And Neurodevelopment (HAND)‐study. Every 4 weeks, detailed neurosonography was performed in these fetuses, including the recording of a 3D volume of the fetal brain, from 20 weeks onwards. In all, 75 healthy fetuses underwent the same protocol to serve as a control group. The volumes were analyzed by automated age prediction software which determines gestational age by the assessment of cortical maturation. Results In total, 477 volumes were analyzed using the age prediction software (199 volumes of 90 congenital heart defect cases; 278 volumes of 75 controls). Of these, 16 (3.2%) volume recordings were excluded because of imaging quality. The age distribution was 19‐33 weeks. Mixed model analysis showed that the age predicted by brain maturation was 3 days delayed compared with the control group (P = .002). Conclusions This study shows that fetuses with isolated cases of congenital heart defects show some delay in cortical maturation as compared with healthy control cases. The clinical relevance of this small difference is debatable. This finding was consistent throughout pregnancy and did not progress during the third trimester.

show abstract

“…Antenatal scans (for the basic examination at mid-pregnancy) are acquired in utero with either a 2D or a 3D transducer positioned to obtain axial slices of the fetal brain. However, advanced fetal neurosonography examines the fetal brain in three planes (axial, sagittal, and coronal) to allow better understanding of brain development [7,8]. Direct visualization of sagittal planes on fetuses is possible.…”

Section: Introductionmentioning

confidence: 99%

Plane Localization in 3-D Fetal Neurosonography for Longitudinal Analysis of the Developing Brain

Yaqub

Rueda

Kopuri

et al. 2016

IEEE J. Biomed. Health Inform.

Self Cite

View full text Add to dashboard Cite

The parasagittal (PS) plane is a 2-D diagnostic plane used routinely in cranial ultrasonography of the neonatal brain. This paper develops a novel approach to find the PS plane in a 3-D fetal ultrasound scan to allow image-based biomarkers to be tracked from prebirth through the first weeks of postbirth life. We propose an accurate plane-finding solution based on regression forests (RF). The method initially localizes the fetal brain and its midline automatically. The midline on several axial slices is used to detect the midsagittal plane, which is used as a constraint in the proposed RF framework to detect the PS plane. The proposed learning algorithm guides the RF learning method in a novel way by: 1) using informative voxels and voxel informative strength as a weighting within the training stage objective function, and 2) introducing regularization of the RF by proposing a geometrical feature within the training stage. Results on clinical data indicate that the new automated method is more reproducible than manual plane finding obtained by two clinicians.

show abstract

Learning-based prediction of gestational age from ultrasound images of the fetal brain

Abstract: Graphical abstract

Cited by 75 publications

References 58 publications

Provocative ideas on human placental biology: A prerequisite for prevention and treatment of neonatal health challenges

Provocative ideas on human placental biology: A prerequisite for prevention and treatment of neonatal health challenges

Cortical development in fetuses with congenital heart defects using an automated brain‐age prediction algorithm

Plane Localization in 3-D Fetal Neurosonography for Longitudinal Analysis of the Developing Brain

Contact Info

Product

Resources

About