Figure - available via license: Creative Commons Attribution 4.0 International
Content may be subject to copyright.
Source publication
We introduce unORANIC, an unsupervised approach that uses an adapted loss function to drive the orthogonalization of anatomy and image-characteristic features. The method is versatile for diverse modalities and tasks, as it does not require domain knowledge, paired data samples, or labels. During test time unORANIC is applied to potentially corrupt...
Context in source publication
Context 1
... vanilla AE shares the same architecture and latent dimension as the anatomy branch of our model. The average peak signal-to-noise ratio (PSNR) values for the reconstructions of both methods on the selected datasets are presented in Table 2. Both models demonstrate precise reconstruction of the input images, with our model achieving a slight improvement across all datasets. ...