Poster
in
Workshop: Generative AI for Education (GAIED): Advances, Opportunities, and Challenges
Paper 16: Diffusion Models in Dermatological Education: Flexible High Quality Image Generation for VR-based Clinical Simulations
Leon Pielage · Paul Schmidle · Bernhard Marschall · Benjamin Risse
Keywords: [ Deep Learning ] [ Guidance Strategies ] [ Simulation Training ] [ Generative AI ] [ diffusion models ] [ virtual reality ] [ upsampling ] [ Image Generation ] [ Medical Education ]
Training medical students to accurately recognize malignant melanoma is a crucial competence and part of almost all medical curricular. We here present a pipeline to generate realistic high-resolution imagery of nevus and melanoma skin lesions by using diffusion models. To ensure the required quality and flexibility we introduce three novel guidance strategies and an adapted upsampling approach which enable the generation of user-specified shapes and to integrate the lesions onto pre-defined skin textures. We evaluate our lesions qualitatively and quantitatively and integrate our results into a virtual reality (VR) simulation for clinical education. Moreover, we discuss several advantages of synthetic over real images such as the ability to facilitate adjustable learning scenarios and the preservation of patient privacy underlining the huge potential of generative image generation for medical education.