| Title: | Equitable modelling of brain imaging by counterfactual augmentation with morphologically constrained 3D deep generative models |
| Journal: | Medical Image Analysis |
| Published: | 5 Dec 2022 |
| Pubmed: | https://pubmed.ncbi.nlm.nih.gov/36542907/ |
| DOI: | https://doi.org/10.1016/j.media.2022.102723 |
Publication 10782
WARNING: the interactive features of this website use CSS3, which your browser does not support. To use the full features of this website, please update your browser.
Abstract
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 where fidelity is limited by data imbalance, distributional instability, confounding, or underspecification, and exhibits inequitable performance across distinct subpopulations. Focusing on demographic attributes, we evaluate the quality of synthesised counterfactuals with voxel-based morphometry, classification and regression of the conditioning attributes, and the Fréchet inception distance. Examining downstream discriminative performance in the context of engineered demographic imbalance and confounding, we use UK Biobank and OASIS magnetic resonance imaging data to benchmark CounterSynth augmentation against current solutions to these problems. We achieve state-of-the-art improvements, both in overall fidelity and equity. The source code for CounterSynth is available at https://github.com/guilherme-pombo/CounterSynth.</p>
7 Authors
- Guilherme Pombo
- Robert Gray
- M. Jorge Cardoso
- Sebastien Ourselin
- Geraint Rees
- John Ashburner
- Parashkev Nachev
1 Application
| Application ID | Title |
|---|---|
| 16273 | Lifestyle-predictive brain-body interactions |
Enabling scientific discoveries that improve human health