English (United Kingdom)

https://curated-unify.zendy.io/wp-json/zendy-region/v1/featured_content/oa?rat=en

https://curated-unify.zendy.io/wp-json/zendy-region/v1/highlighted_journal/

Global: Zendy Tools annual

Presents the keyphrase highlighting as premium feature

Keyphrase Highlighting

Presents the summarisation as premium feature

Summarisation

Insights

Presents the pdf analysis as premium feature

PDF Analysis

Presents the zaia usage as premium feature

ZAIA

Global: Zendy Tools monthly

Global: Zendy Plus monthly

Presents the access of premium content as premium feature

Premium Content

Global: Zendy Plus annual

Global: Zendy Free Plan

Image-to-image translation is an ill-posed problem as unique one-to-onemapping may not exist between the source and target images. Learning-basedmethods proposed in this context often evaluate the performance on test datathat is similar to the training data, which may be impractical. This demandsrobust methods that can quantify uncertainty in the prediction for makinginformed decisions, especially for critical areas such as medical imaging.Recent works that employ conditional generative adversarial networks (GANs)have shown improved performance in learning photo-realistic image-to-imagemappings between the source and the target images. However, these methods donot focus on (i)~robustness of the models to out-of-distribution (OOD)-noisydata and (ii)~uncertainty quantification. This paper proposes a GAN-basedframework that (i)~models an adaptive loss function for robustness to OOD-noisydata that automatically tunes the spatially varying norm for penalizing theresiduals and (ii)~estimates the per-voxel uncertainty in the predictions. Wedemonstrate our method on two key applications in medical imaging:(i)~undersampled magnetic resonance imaging (MRI) reconstruction (ii)~MRImodality propagation. Our experiments with two different real-world datasetsshow that the proposed method (i)~is robust to OOD-noisy test data and providesimproved accuracy and (ii)~quantifies voxel-level uncertainty in thepredictions.

Uncertainty-aware GAN with Adaptive Loss for Robust MRI Image Enhancement