Automated fetal brain segmentation from 2D MRI slices for motion correction
- Submitting institution
-
King's College London
- Unit of assessment
- 12 - Engineering
- Output identifier
- 98363799
- Type
- D - Journal article
- DOI
-
10.1016/j.neuroimage.2014.07.023
- Title of journal
- NeuroImage
- Article number
- -
- First page
- 633
- Volume
- 101
- Issue
- 0
- ISSN
- 1053-8119
- Open access status
- Out of scope for open access requirements
- Month of publication
- July
- Year of publication
- 2014
- URL
-
-
- Supplementary information
-
-
- Request cross-referral to
- -
- Output has been delayed by COVID-19
- No
- COVID-19 affected output statement
- -
- Forensic science
- No
- Criminology
- No
- Interdisciplinary
- No
- Number of additional authors
-
7
- Research group(s)
-
-
- Proposed double-weighted
- No
- Reserve for an output with double weighting
- No
- Additional information
- Motion correction of 3D fetal MRI is hampered by need for lengthy manual segmentation of the fetal organs. This pioneering paper introduced a novel paradigm that machine learning can perform automatic localisation and segmentation of fetal brain in motion-corrupted MRI. Successful application to a hundred cases proved that machine learning can support fully automatic reconstruction of 3D fetal MRI. It inspired current state-of-the-art deep learning solutions (10.1109/TMI.2017.2721362; 10.1016/j.neuroimage.2019.116324). This new paradigm is the key technological foundation for a development of a fully automatic widely translatable 3D fetal MRI reconstruction tool, funded by a new research grant (Rosetrees Trust A2725).
- Author contribution statement
- -
- Non-English
- No
- English abstract
- -