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

Counterfactual reasoning is often used in clinical settings to explaindecisions or weigh alternatives. Therefore, for imaging based specialties suchas ophthalmology, it would be beneficial to be able to create counterfactualimages, illustrating answers to questions like "If the subject had had diabeticretinopathy, how would the fundus image have looked?". Here, we demonstratethat using a diffusion model in combination with an adversarially robustclassifier trained on retinal disease classification tasks enables thegeneration of highly realistic counterfactuals of retinal fundus images andoptical coherence tomography (OCT) B-scans. The key to the realism ofcounterfactuals is that these classifiers encode salient features indicativefor each disease class and can steer the diffusion model to depict diseasesigns or remove disease-related lesions in a realistic way. In a user study,domain experts also found the counterfactuals generated using our methodsignificantly more realistic than counterfactuals generated from a previousmethod, and even indistinguishable from real images.

Generating Realistic Counterfactuals for Retinal Fundus and OCT Images using Diffusion Models