UNSUPERVISED HARMONIZATION OF BRAIN MRI USING 3D CYCLE GANS AND ITS EFFECT ON BRAIN AGE PREDICTION Article Swipe
YOU?
·
· 2022
· Open Access
·
· DOI: https://doi.org/10.1101/2022.11.15.516349
Deep learning methods trained on brain MRI data from one scanner or imaging protocol can fail catastrophically when tested on data from other sites or protocols - a problem known as domain shift . To address this, here we propose a domain adaptation method that trains a 3D CycleGAN (cycle-consistent generative adversarial network) to harmonize brain MRI data from 5 diverse sources (ADNI, WHIMS, OASIS, AIBL, and UK Biobank; total N=4,941 MRIs, age range: 46-96 years). The approach uses 2 generators and 2 discriminators to generate an image harmonized to a specific target dataset given an image from the source domain distribution and vice versa . We train the CycleGAN to jointly optimize an adversarial loss and cyclic consistency. We use a patch-based discriminator and impose identity loss to further regularize model training. To test the benefit of the harmonization, we show that brain age estimation - a common benchmarking task - is more accurate in GAN-harmonized versus raw data. t -SNE maps show the improved distributional overlap of the harmonized data in the latent space.
Related Topics To Compare & Contrast
- Type
- preprint
- Language
- en
- Landing Page
- https://doi.org/10.1101/2022.11.15.516349
- https://www.biorxiv.org/content/biorxiv/early/2022/11/15/2022.11.15.516349.full.pdf
- OA Status
- green
- Cited By
- 1
- References
- 20
- Related Works
- 10
- OpenAlex ID
- https://openalex.org/W4309258633