DISC: Latent Diffusion Models with Self-Distillation from Separated Conditions for Prostate Cancer Grading

arXiv:2404.13097v1 Announce Type: cross
Abstract: Latent Diffusion Models (LDMs) can generate high-fidelity images from noise, offering a promising approach for augmenting histopathology images for training cancer grading models. While previous works successfully generated high-fidelity histopathology images using LDMs, the generation of image tiles to improve prostate cancer grading has not yet been explored. Additionally, LDMs face challenges in accurately generating admixtures of multiple cancer grades in a tile when conditioned by a tile mask. In this study, we train specific …

abstract arxiv cancer cs.cv cs.lg diffusion diffusion models distillation eess.iv fidelity generate generated image images latent diffusion models noise q-bio.qm tiles training type