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 Plus annual

Presents the access of premium content as premium feature

Premium Content

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 Plus monthly

Global: Zendy Tools annual

Global: Zendy Tools monthly

Global: Zendy Free Plan

Deep neural networks are commonly used for medical purposes such as imagegeneration, segmentation, or classification. Besides this, they are oftencriticized as black boxes as their decision process is often not humaninterpretable. Encouraging the latent representation of a generative model tobe disentangled offers new perspectives of control and interpretability.Understanding the data generation process could help to create artificialmedical data sets without violating patient privacy, synthesizing differentdata modalities, or discovering data generating characteristics. Thesecharacteristics might unravel novel relationships that can be related togenetic traits or patient outcomes. In this paper, we give a comprehensiveoverview of popular generative models, like Generative Adversarial Networks(GANs), Variational Autoencoders (VAEs), and Flow-based Models. Furthermore, wesummarize the different notions of disentanglement, review approaches todisentangle latent space representations and metrics to evaluate the degree ofdisentanglement. After introducing the theoretical frameworks, we give anoverview of recent medical applications and discuss the impact and importanceof disentanglement approaches for medical applications.

Review of Disentanglement Approaches for Medical Applications -- Towards Solving the Gordian Knot of Generative Models in Healthcare