Autonomous Cardiac MRI Acquisition

  • Research type

    Research Study

  • Full title

    Autonomous Cardiac MRI Acquisition using artificial neural networks

  • IRAS ID

    284559

  • Contact name

    James C Moon

  • Contact email

    james.moon1@nhs.net

  • Sponsor organisation

    University College London

  • Duration of Study in the UK

    1 years, 0 months, 1 days

  • Research summary

    Cardiac magnetic resonance (CMR) is the gold standard for the diagnosis and evaluation of many diseases, but its long acquisition time makes it a time-consuming and expensive test that is under-utilised in the UK. Current practice is for a radiographer to prescribe successive imaging planes through which the heart is scanned, but this introduces imprecision and limits CMR to large centres with relevant expertise.

    The aim of this project is to automate the scanning process, reducing acquisition time, removing the need for specialist training, democratising the technology and increasing precision.

    We will develop a deep learning algorithm to automate the cardiac MR slice prescription process and implement it directly on the scanner. A scan-rescan approach will be used to quantify the algorithm’s precision and measure its performance against a cardiac radiographer.

    The algorithm will be deployed in stages. First, it will be tested and its performance quantified off-line. We will then deploy the algorithm on the scanner for the second stage, but it will only make suggestions, with the radiographer ultimately doing the scanning. The final stage will see the algorithm make suggestions and if the radiographer accepts them, the scan will be performed automatically.

  • REC name

    South East Scotland REC 01

  • REC reference

    22/SS/0103

  • Date of REC Opinion

    5 Dec 2022

  • REC opinion

    Further Information Favourable Opinion