Generating Realistic Counterfactuals for Retinal Fundus and OCT Images using Diffusion Models
This addresses the problem of providing visual explanations for medical decisions in ophthalmology, though it is incremental as it builds on existing diffusion models and classifiers.
The paper tackled generating realistic counterfactual images for retinal fundus and OCT images to aid clinical decision-making, achieving results where experts found the generated images significantly more realistic than previous methods and indistinguishable from real ones.
Counterfactual reasoning is often used in clinical settings to explain decisions or weigh alternatives. Therefore, for imaging based specialties such as ophthalmology, it would be beneficial to be able to create counterfactual images, illustrating answers to questions like "If the subject had had diabetic retinopathy, how would the fundus image have looked?". Here, we demonstrate that using a diffusion model in combination with an adversarially robust classifier trained on retinal disease classification tasks enables the generation of highly realistic counterfactuals of retinal fundus images and optical coherence tomography (OCT) B-scans. The key to the realism of counterfactuals is that these classifiers encode salient features indicative for each disease class and can steer the diffusion model to depict disease signs or remove disease-related lesions in a realistic way. In a user study, domain experts also found the counterfactuals generated using our method significantly more realistic than counterfactuals generated from a previous method, and even indistinguishable from real images.