Delta Marches: Generative AI based image synthesis to decode disease-driving morphologic transformations.

Delta-Marches uses generative AI to decode disease-related tissue morphological changes at subcellular resolution, revealing key features in renal carcinoma and colorectal tissues.

• Why it matters: Understanding how tissue morphology relates to disease progression is crucial for advancing diagnostics and treatments, but current methods lack interpretability and subcellular detail.
• What they did: The approach couples latent-space transformations with generative AI to simulate morphological shifts between disease states, comparing images to their class-shifted counterparts to identify affected features.
• The result: Delta-Marches accurately captures known and novel tissue changes, such as tumor nuclear phenotypes and vascular reduction, enabling detailed hypothesis generation across tissue types.