Automated cervix biometry, volumetry and normative models for 3D motion-corrected T2-weighted 0.55-3T fetal MRI during 2nd and 3rd trimesters
Fetal MRI provides superior tissue contrast and true 3D spatial information however there is only a limited number of MRI studies investigating cervix during pregnancy<sup>1-3</sup>. Furthermore, there are no clearly formalised protocols or automated methods for MRI cervical measurements. This work introduces the first deep learning pipeline for automated multi-layer segmentation and biometry for 3D T2w reconstructed images of the pregnant cervix. Evaluation on 20 datasets from 0.55T and 3T acquisitions showed good performance in comparison to manual measurements. This solution could potentially minimise the need for manual editing, significantly reduce analysis time and address inter- and intra-observer bias. Next, we used the pipeline to process 270 normal term cases from 16 to 40 weeks gestational age (GA) range. The inlet diameter and length showed the strongest correlation with GA which is in agreement with the gradual remodeling and softening of the cervix prior to birth. We also generated 3D population-averaged MRI atlases of the cervix that are publicly available online.
Authors
- Agnieszka Glazewska‐Hallin (ORCID: https://orcid.org/0000-0002-7054-4121)
- Alena Uus (ORCID: https://orcid.org/0000-0001-5796-2145)
- Jana Hutter (ORCID: https://orcid.org/0000-0003-3476-3500)
- Jordina Aviles Verdera (ORCID: https://orcid.org/0009-0007-7575-4244)
- Mary Rutherford (ORCID: https://orcid.org/0000-0003-3361-1337)
- Lisa Story (ORCID: https://orcid.org/0000-0001-9328-9592)
- Megan P. Hall
- Simi Bansal
- Chris Bradshaw (ORCID: https://orcid.org/0009-0001-0691-0297)
Institutions
- King's College London (GB)
- Guy's and St Thomas' NHS Foundation Trust (GB)
- Universitätsklinikum Erlangen (DE)
- King's College School (GB)
Publication Details
- Journal
- Scientific Reports
- Published
- 2025-12-01
- DOI
- https://doi.org/10.1038/s41598-025-29744-2
- Primary Topic
- Fetal and Pediatric Neurological Disorders
- Type
- article
- Field-Weighted Citation Impact
- 0.00
Funders
- Wellcome Trust
- UK Research and Innovation
- NIHR Biomedical Research Centre, Royal Marsden NHS Foundation Trust/Institute of Cancer Research
- National Institute for Health and Care Research
- King's College London
- Deutsche Forschungsgemeinschaft
- National Institutes of Health
- Medical Research Council
- Engineering and Physical Sciences Research Council
- Menzies Centre for Australian Studies, King's College London, University of London
- Centre For Medical Engineering, King’s College London