Structure-Guided Histopathology Synthesis via Dual-LoRA Diffusion

TL;DR

This paper introduces Dual-LoRA Diffusion, a unified model that jointly performs local tissue structure completion and global tissue synthesis in histopathology images, improving realism and structural fidelity.

Contribution

It proposes a novel centroid-guided diffusion framework with task-specific LoRA adapters, enabling joint local and global tissue synthesis without separate models.

Findings

Improved LPIPS score for local completion from 0.1797 to 0.1524.

Reduced FID score for global synthesis from 225.15 to 76.04.

Demonstrated superior performance over state-of-the-art methods in tissue synthesis tasks.

Abstract

Histopathology image synthesis plays an important role in tissue restoration, data augmentation, and modeling of tumor microenvironments. However, existing generative methods typically address restoration and generation as separate tasks, although both share the same objective of structure-consistent tissue synthesis under varying degrees of missingness, and often rely on weak or inconsistent structural priors that limit realistic cellular organization. We propose Dual-LoRA Controllable Diffusion, a unified centroid-guided diffusion framework that jointly supports Local Structure Completion and Global Structure Synthesis within a single model. Multi-class nuclei centroids serve as lightweight and annotation-efficient spatial priors, providing biologically meaningful guidance under both partial and complete image absence. Two task-specific LoRA adapters specialize the shared backbone for local and global objectives without retraining separate diffusion models. Extensive experiments demonstrate consistent improvements over state-of-the-art GAN and diffusion baselines across restoration and synthesis tasks. For local completion, LPIPS computed within the masked region improves from 0.1797 (HARP) to 0.1524, and for global synthesis, FID improves from 225.15 (CoSys) to 76.04, indicating improved structural fidelity and realism. Our approach achieves more faithful structural recovery in masked regions and substantially improved realism and morphology consistency in full synthesis, supporting scalable pan-cancer histopathology modeling.