AI EFW

  • Research type

    Research Study

  • Full title

    Use of Artificial Intelligence for the ultrasound assessment of fetal biometry - Comparison of automated to manual measurement of estimated fetal weight

  • IRAS ID

    345263

  • Contact name

    Asma Khalil

  • Contact email

    asma.khalil@stgeorges.nhs.uk

  • Sponsor organisation

    St George's University Hospitals NHS Foundation Trust

  • Duration of Study in the UK

    1 years, 0 months, 1 days

  • Research summary

    This research project explores the potential of AI ultrasound algorithms in calliper placement to determining estimated fetal weight using a ultrasound device. Obstetric ultrasound, is a non-invasive and cost-effective imaging technique, and plays a pivotal role in assessing fetal biometry for evaluating growth and well-being during pregnancy. Accurate estimation of fetal weight is crucial for determining appropriate obstetric management. The standard procedure involves measuring biparietal diameter, head circumference, abdominal circumference, and femur length, but it is subject to variability and dependence on operator expertise.

    Addressing these challenges, the application of artificial intelligence (AI) in obstetric ultrasound has emerged. AI, particularly machine learning algorithms, is increasingly employed to automate fetal biometry on standardised planes, potentially minimising variability and enhancing efficiency. These algorithms analyse ultrasound images, extracting relevant features to estimate fetal weight. The use of deep learning architectures, such as convolutional neural networks (CNNs), has shown promising results. By leveraging machine learning and deep learning techniques, these systems aim to provide more reliable predictions of fetal weight, contributing to enhanced monitoring and management of pregnancy. The potential benefits include increased efficiency, reduced observer-dependency, and improved precision in assessing fetal growth and well-being. However, integration into clinical practice requires rigorous testing, validation, regulatory approval, and acceptance by healthcare professionals.

  • REC name

    London - South East Research Ethics Committee

  • REC reference

    24/PR/1455

  • Date of REC Opinion

    7 Mar 2025

  • REC opinion

    Further Information Favourable Opinion