Advancing Maternal and Fetal Imaging
The Intelligent Imaging in Fetal Health Research Group forms part of our department's Maternal & Fetal Health theme and is led by Prof. Aris Papegeorghiou.
Intelligent Imaging in Fetal Health
Why this project is important?
Complications during pregnancy and childbirth remain a leading cause of death and disability for mothers and babies worldwide, particularly in low-resource settings. Millions of women still lack access to high-quality pregnancy ultrasound, limiting early detection of fetal anomalies, accurate gestational age assessment, and timely clinical decision-making.
By combining intelligent imaging, artificial intelligence, and global health research, this project addresses critical gaps in access, expertise, and equity - helping to ensure that lifesaving diagnostic tools are available where they are needed most and improving outcomes for families across the world.
our research into Intelligent Imaging
Our research on Intelligent Imaging in Fetal Health, led by Prof Aris Papageorghiou, encompasses two key areas:
- Pregnancy imaging laboratory: To advance global fetal health through intelligent imaging
- Global Maternal and Fetal Health: To address maternal and perinatal health challenges to provide evidence-based solutions to improve care and outcomes for mothers and babies worldwide.
Video: Bounding box annotation of step 1 of the CALOPUS protocol
The CALOPUS project (Computer Assisted low-cost point of care ultrasound) is a UK-India Collaborative comprising a team of Clinicians and Engineers from our department, the Institute of Biomechanical Engineering in Oxford and the Translational Health Science and Technology Institute in Delhi.
Pregnancy Imaging Laboratory
BAOBAB - Biometry Automation in Obstetrics and Beyond.
The World Health Organization recommends one routine ultrasound scan for all pregnant women. However, in sub-Saharan Africa, few women have access to high quality pregnancy ultrasound. The main barriers identified are the lack of affordable, robust ultrasound equipment; and a lack of trained / skilled ultrasound operators.
CAIFE (Clinical Artificial Intelligence Fetal Echocardiography)
We are working to create an ultrasound systems which can recognise the difference between a healthy and unhealthy fetal heart using machine learning. Detection of congenial heart defects during pregnancy allows early diagnosis and planning for treatment post-delivery.
The CAIFE project is part of the University of Oxford’s COCHE Centre, which supports research into AI-driven fetal echocardiography and congenital heart disease detection. Find out more about COCHE.
CALOPUS (Computer Assisted low-cost point of care ultrasound)
We are developing a low-cost point of care ultrasound device that would enable minimally trained healthcare providers to obtain clinically relevant information from a simple scanning protocol. We will realise this through the integration of point-of-care ultrasound and automation technology.
Our aims are to automate key factors for delivery of pregnancy care: assessing viability; fetal presentation; identify multiple pregnancies; placental location; assess the adequacy of amniotic fluid; and basic fetal measurement.
CEREBRA (Clinical Evaluation of artificial intelligence-based REconstruction of the fetal BRAin)
The fetal brain develops rapidly throughout pregnancy, and deviations in this process may be associated with later neurodevelopmental outcomes. Being able to assess brain development accurately before birth could therefore improve the early identification of babies at risk. Convential two-dimensional (2D) ultrasound is the standard imaging for fetal brain assessment during pregnancy because it is widely available in most maternity settings, but provides limited spatial information. Conversely, three-dimensional (3D) ultrasound and fetal MRI have a high spatial context, but require specialised equipment and expertise, restricting their availability in routine clinical practice.
The CEREBRA study aims to develop and clinically validate an artificial intelligence (AI) framework capable of reconstructing detailed 3D fetal brain volumes from routine 2D ultrasound videoclips acquired during prenatal examinations, evaluating the accuracy of AI-generated 2D-to-3D reconstructions against conventional 3D volumes.
This research has the potential to transform prenatal neuroimaging by making advanced fetal brain assessment accessible using standard ultrasound equipment, reducing dependence on specialised imaging technologies, and expand access to high-quality prenatal brain assessment in both high-resource and low-resource healthcare settings.
Fetal anomaly screening
Screening for fetal anomalies is routinely performed in the second trimester at 18-21 weeks of gestation. Recent data, including a meta-analysis by our group, suggest that screening for fetal anomalies in the first trimester is feasible, and will detect just over half of all prenatally detected anomalies.
PULSE (Perception Ultrasound By Learning Sonographic Experience)
It is an ambitious, innovative, interdisciplinary research project exploring the use of Artificial Intelligence-based technologies to reduce the need for highly trained ultrasound operators.
It is a joint research project with the Department of Engineering Science at the University of Oxford.
PURE-FIRST
In the UK, pregnant women are offered two scans during their pregnancy: one at 11-14 weeks and another at 18-20 weeks gestation. The current medical guidelines emphasise fetal anatomical screening during the second scan. However, emerging evidence, including a comprehensive meta-analysis conducted by our research group, suggests that early assessment of the baby’s anatomy may be possible with the right technology.
The PURE - FIRST study aims to build on our successful feasibility study by recruiting an additional 300 participants. Our goal is to explore the usability of 3D ultrasound in acquiring a standardised set of 2D images for examining fetal structures between 11-14 weeks gestation.
This research holds the promise of enhancing diagnosis and enabling earlier detection of fetal conditions, benefiting both expectant mothers and healthcare professionals.
TRACER (Transcerebellar Diameter)
In this project we are developing a simple, low-cost, ultrasound-based gestational age (GA) estimation device. The TraCer device uses commercially available ultrasound equipment but innovative deep-learning based algorithms to help tackle issues surrounding maternal and newborn health in resource poor settings. This low-cost device will enable minimally trained health care workers to estimate gestational age, which will be invaluable in helping to manage the ongoing pregnancy.
Global Maternal and Perinatal Health
HAPIN
The Household Air Pollution Intervention Network (HAPIN) Trial is an international multi-center study aimed at assessing the impact of a liquefied petroleum gas (LPG) cooking stove and fuel intervention on health. HAPIN Trial centers are located in four countries: Guatemala, India, Peru and Rwanda
OMPHI
The Oxford Maternal & Perinatal Health Institute (OMPHI) works alongside Nuffield Department of Women's & Reproductive Health to bring together world experts to resolve priority maternal and perinatal health problems on a global scale, such as the INTERGROWTH-21ST, INTERBIO 21ST AND INTERPRACTICE-21ST studies.
Useful links
Global Health theme
Nuffield Department of Women's and Reproductive Health manages over 30 research groups that fall within either Global Health, Cancer, Maternal & Fetal Health; Big data; and Reproductive Medicine & Genetics.
©
Copyright: Shutterstock
Maternal & Fetal Health
Our Maternal & Fetal Health research covers the following research groups: Lactation, Intelligent Imaging in Fetal Health, the Clinical Research Group, Oxford Labour Monitoring, Placental Imaging and Pre-eclampsia.
Medical Research Council
MRC funds research at the forefront of science to prevent illness, develop therapies and improve human health.
Latest publications
Physiological and biological response to heat exposure in pregnancy: a systematic review and meta-analysis.
Journal article
Bonell A. et al, (2027), Lancet Planet Health
CleanCTG: A deep learning model for multi-artefact detection and reconstruction in Cardiotocography
Journal article
Wong S. et al, (2026), Biomedical Signal Processing and Control, 123, 110654 - 110654
Dose-effect analysis of facial bone morphology following radiation therapy for head and neck rhabdomyosarcoma
Journal article
Hol MLF. et al, (2026), Radiotherapy and Oncology, 222
A double-blind multi-centre randomised placebo-controlled trial of doxycycline in women with recurrent miscarriage and chronic endometritis defined by CD138 positive stromal cells.
Journal article
Odendaal J. et al, (2026), Hum Reprod
Electronic Patient-Reported Outcome Monitoring With Alert-Based Interventions in Metastatic Breast Cancer
Journal article
Karsten MM. et al, (2026), JAMA Oncology
The research team
-
Aris Papageorghiou
Professor of Fetal Medicine and Director of Research of the Oxford Maternal and Perinatal Health Institute (OMPHI).
-
Jehan Karim
Clinical Research Fellow
-
Risa Miyazaki Sankar
Project Coordinator
-
Jayne Lander
Research Sonographer
How can you help?
You can support the ongoing work of the Intelligent Imaging in Fetal Health project through donations, collaborations and research support. If you wish to support our work, please contact us or email Professor Aris Papageorghiou using the button below.