UCL Discovery
UCL home » Library Services » Electronic resources » UCL Discovery

Texture-Based Analysis of Fetal Organs in Fetal Growth Restriction

Zeidan, AM; Gilliland, PR; Patel, A; Ou, Z; Flouri, D; Mufti, N; Maksym, K; ... Melbourne, A; + view all (2021) Texture-Based Analysis of Fetal Organs in Fetal Growth Restriction. In: Uncertainty for Safe Utilization of Machine Learning in Medical Imaging, and Perinatal Imaging, Placental and Preterm Image Analysis. (pp. pp. 253-262). Springer Nature: Cham, Switzerland. Green open access

[thumbnail of Texture based analysis of FGR.pdf]
Preview
Text
Texture based analysis of FGR.pdf - Published Version

Download (1MB) | Preview

Abstract

Fetal growth restriction (FGR) is common, affecting around 10% of all pregnancies. Growth restricted fetuses fail to achieve their genetically predetermined size and often weigh <10th centile for gestation. However, even appropriately grown fetuses can be affected, with the diagnosis of FGR missed before birth. Babies with FGR have a higher rate of stillbirth, neonatal morbidity such as breathing problems, and neurodevelopmental delay. FGR is usually due to placental insufficiency leading to poor placental perfusion and fetal hypoxia. MRI is increasingly used to image the fetus and placenta. Here we explore the use of novel multi-compartment Intravoxel Incoherent Motion Model (IVIM)-based models for MRI fetal and placental analysis, to improve understanding of FGR and quantify abnormalities and biomarkers in fetal organs. In 12 normally grown and 12 FGR gestational-age matched pregnancies (Median 28+ 4 wks±3+ 3 wks) we acquired T2 relaxometry and diffusion MRI datasets. Decreased perfusion, pseudo-diffusion coefficient, and fetal blood T2 values in the placenta and fetal liver were significant features distinguishing between FGR and normal controls (p-value <0.05). This may be related to the preferential shunting of fetal blood away from the fetal liver to the fetal brain that occurs in placental insufficiency. These features were used to predict FGR diagnosis and gestational age at delivery using simple machine learning models. Texture analysis was explored to compare Haralick features between control and FGR fetuses, with the placenta and liver yielding the most significant differences between the groups. This project provides insights into the effect of FGR on fetal organs emphasizing the significant impact on the fetal liver and placenta, and the potential of an automated approach to diagnosis by leveraging simple machine learning models.

Type: Proceedings paper
Title: Texture-Based Analysis of Fetal Organs in Fetal Growth Restriction
Event: 3rd International Workshop, UNSURE 2021, and 6th International Workshop, PIPPI 2021
ISBN-13: 9783030877347
Open access status: An open access version is available from UCL Discovery
DOI: 10.1007/978-3-030-87735-4_24
Publisher version: https://doi.org/10.1007/978-3-030-87735-4_24
Language: English
Additional information: This version is the author accepted manuscript. For information on re-use, please refer to the publisher's terms and condit
UCL classification: UCL
UCL > Provost and Vice Provost Offices > School of Life and Medical Sciences
UCL > Provost and Vice Provost Offices > School of Life and Medical Sciences > Faculty of Population Health Sciences > UCL EGA Institute for Womens Health
UCL > Provost and Vice Provost Offices > School of Life and Medical Sciences > Faculty of Population Health Sciences > UCL EGA Institute for Womens Health > Maternal and Fetal Medicine
UCL > Provost and Vice Provost Offices > UCL BEAMS
UCL > Provost and Vice Provost Offices > UCL BEAMS > Faculty of Engineering Science
UCL > Provost and Vice Provost Offices > UCL BEAMS > Faculty of Engineering Science > Dept of Med Phys and Biomedical Eng
URI: https://discovery.ucl.ac.uk/id/eprint/10139816
Downloads since deposit
93Downloads
Download activity - last month
Download activity - last 12 months
Downloads by country - last 12 months

Archive Staff Only

View Item View Item