3D UNet with GAN discriminator for robust localisation of the fetal brain and trunk in MRI with partial coverage of the fetal body
Uus, A.; Grigorescu, I.; van Poppel, M.; Hughes, E.; Steinweg, J.; Roberts, T.; Lloyd, D.; Pushparajah, K.; Deprez, M.
Show abstract
In fetal MRI, automated localisation of the fetal brain or trunk is a prerequisite for motion correction methods. However, the existing CNN-based solutions are prone to errors and may require manual editing. In this work, we propose to combine a multi-label 3D UNet with a GAN discriminator for localisation of both fetal brain and trunk in fetal MRI stacks. The proposed method is robust for datasets with both full and partial coverage of the fetal body.
Matching journals
The top 4 journals account for 50% of the predicted probability mass.
Similar papers in this journal
Similar papers in this journal
- QSMxT: Robust Masking and Artefact Reduction for Quantitative Susceptibility Mapping 95%
- Prospective Motion Correction and Automatic Segmentation of Penetrating Arteries in Phase Contrast MRI at 7 T 95%
- Offline Reconstruction of Diffusion MRI Acquisitions for Comparison Between Complex PCA-based and AI-based Denoising 95%
Similar papers in this journal
- Cross-modality image translation of 3 Tesla Magnetic Resonance Imaging to 7 Tesla using Generative Adversarial Networks 95%
- Deep Bayesian networks for uncertainty estimation and adversarial resistance of white matter hyperintensity segmentation 95%
- CEREBRUM-7T: Fast and Fully-volumetric Brain Segmentation of 7 Tesla MR Volumes 94%
Similar papers in this journal
- Automated 3D reconstruction of the fetal thorax in the standard atlas space from motion-corrupted MRI stacks for 21-36 weeks GA range 98%
- MISPEL: A supervised deep learning harmonizationmethod for multi-scanner neuroimaging data 95%
- STAMP: Simultaneous Training and Model Pruning for Low Data Regimes in Medical Image Segmentation 94%
"Similar papers" are the closest papers from that journal in the model's embedding space. They show what the match is built on, but the ranking comes mostly from a classifier over the whole training set, not from these examples alone.