Abstract #3797

Watch me move: Generalizable Fetal Brain Segmentations for Automatic Fetal Head Motion Tracking throughout an MRI Scan

Jordina Aviles Verdera^1,2, Kelly Payette^1,2,3, Sara Neves Silva^1,2, Daniel Cromb², Raphael Tomi-Tricot^1,2,4, Megan Hall^2,5, Simi Bansal², Kamilah St Clair^1,2, Serena Counsell^1,2, Lisa Story^2,5, Mary A Rutherford^1,2, Joseph V Hajnal^1,2, and Jana Hutter^1,2,6

¹Imaging Physics and Engineering Research Department, School of Biomedical Engineering and Imaging, King's College London, London, United Kingdom, ²Early Life Imaging Research Department, School of Biomedical Engineering and Imaging, King's College London, London, United Kingdom, ³Center for MR-Research, University Children's Hospital Zurich, University of Zurich, Zurich, Switzerland, ⁴MR Research Collaborations, Siemens Healthcare Limited, Camberley, United Kingdom, ⁵Academic Women's Health Department, King's College London, London, United Kingdom, ⁶Smart Imaging Lab, Radiologisches Institut, Universitätsklinikum Erlangen, Erlangen, Germany

Synopsis

Keywords: Data Processing, Fetal, low-field, motion tracking, segmentation

Motivation: Quantifying fetal movement allows first fascinating views into early human development. Fetal MRI is well suited, but isolated individually analyzed contrasts do not allow continuous assessment.

Goal(s): Providing quantification of fetal motion for the whole duration of fetal MRI scans and analyzing patterns to obtain insights into time-scale, sequence, gestational age and time point of birth.

Approach: A contrast, field-strength and age agnostic network was trained on nearly 3000 fetal MRI scans, providing continuous information, analyzed with a range of automatic measurements.

Results: Isolated bursts of activities are replaced by continuous phases of activity across gestation.

Impact: First emerging signatures of human neurological development can be systematically and automatically assessed retro- and prospectively on fetal MRI. Signatures of fetal activity and their correlation to fetal health can offer new opportunities for research and future clinical application.

How to access this content:

For one year after publication, abstracts and videos are only open to registrants of this annual meeting. Registrants should use their existing login information. Non-registrant access can be purchased via the ISMRM E-Library.

After one year, current ISMRM & ISMRT members get free access to both the abstracts and videos. Non-members and non-registrants must purchase access via the ISMRM E-Library.

After two years, the meeting proceedings (abstracts) are opened to the public and require no login information. Videos remain behind password for access by members, registrants and E-Library customers.

Click here for more information on becoming a member.