Style-Extracting Diffusion Models for Semi-Supervised Histopathology Segmentation

TL;DR

This paper introduces Style-Extracting Diffusion Models that generate diverse, unseen-style images for semi-supervised histopathology segmentation, improving model robustness and performance.

Contribution

The work presents a novel diffusion model with style and content conditioning, enabling zero-shot style transfer and synthetic data generation for histopathology segmentation.

Findings

Generated diverse images with unseen styles using the proposed method.

Improved segmentation accuracy with synthetic data in semi-supervised training.

Reduced variability in segmentation performance across patients.

Abstract

Deep learning-based image generation has seen significant advancements with diffusion models, notably improving the quality of generated images. Despite these developments, generating images with unseen characteristics beneficial for downstream tasks has received limited attention. To bridge this gap, we propose Style-Extracting Diffusion Models, featuring two conditioning mechanisms. Specifically, we utilize 1) a style conditioning mechanism which allows to inject style information of previously unseen images during image generation and 2) a content conditioning which can be targeted to a downstream task, e.g., layout for segmentation. We introduce a trainable style encoder to extract style information from images, and an aggregation block that merges style information from multiple style inputs. This architecture enables the generation of images with unseen styles in a zero-shot manner, by leveraging styles from unseen images, resulting in more diverse generations. In this work, we use the image layout as target condition and first show the capability of our method on a natural image dataset as a proof-of-concept. We further demonstrate its versatility in histopathology, where we combine prior knowledge about tissue composition and unannotated data to create diverse synthetic images with known layouts. This allows us to generate additional synthetic data to train a segmentation network in a semi-supervised fashion. We verify the added value of the generated images by showing improved segmentation results and lower performance variability between patients when synthetic images are included during segmentation training. Our code will be made publicly available at [LINK].