AI model synthesizes medical images with controllable disease progression

Researchers have developed a new diffusion model called Disentangled Anatomy-Disease Diffusion (DADD) to synthesize longitudinal medical images. This model can generate images of ulcerative colitis progression at specific disease stages while preserving patient-specific anatomy. DADD uses a novel Feature Purifier to separate anatomical features from disease indicators and a Delta Steering mechanism for precise control over disease transitions during image generation. AI

IMPACT Introduces a new method for generating controlled medical image sequences, potentially improving downstream diagnostic tasks.

RANK_REASON Academic paper detailing a novel diffusion model for medical image synthesis. [lever_c_demoted from research: ic=1 ai=1.0]

Read on arXiv cs.CV →

• arXiv
• DADD
• LIMUC dataset
• Mayo Endoscopic Score
• ulcerative colitis

• paper
• other

AI-generated summary · Google Gemini · from 1 sources. How we write summaries →