Cargando…
Equitable modelling of brain imaging by counterfactual augmentation with morphologically constrained 3D deep generative models
We describe CounterSynth, a conditional generative model of diffeomorphic deformations that induce label-driven, biologically plausible changes in volumetric brain images. The model is intended to synthesise counterfactual training data augmentations for downstream discriminative modelling tasks whe...
Autores principales: | Pombo, Guilherme, Gray, Robert, Cardoso, M. Jorge, Ourselin, Sebastien, Rees, Geraint, Ashburner, John, Nachev, Parashkev |
---|---|
Formato: | Online Artículo Texto |
Lenguaje: | English |
Publicado: |
Elsevier
2023
|
Materias: | |
Acceso en línea: | https://www.ncbi.nlm.nih.gov/pmc/articles/PMC10591114/ https://www.ncbi.nlm.nih.gov/pubmed/36542907 http://dx.doi.org/10.1016/j.media.2022.102723 |
Ejemplares similares
-
Predicting mortality in acutely hospitalised older patients: the impact of model dimensionality
por: Tsui, Alex, et al.
Publicado: (2023) -
Unsupervised brain imaging 3D anomaly detection and segmentation with transformers
por: Pinaya, Walter H.L., et al.
Publicado: (2022) -
Reclassifying stroke lesion anatomy
por: Bonkhoff, Anna K., et al.
Publicado: (2021) -
Lost in translation
por: Nachev, Parashkev, et al.
Publicado: (2019) -
Deep forecasting of translational impact in medical research
por: Nelson, Amy P.K., et al.
Publicado: (2022)