PixCell: A generative foundation model for digital histopathology images

TL;DR

PixCell is a novel generative foundation model for histopathology images that uses diffusion techniques to synthesize realistic images, aiding in data augmentation, privacy preservation, and virtual staining without requiring annotated data.

Contribution

The paper introduces PixCell, the first large-scale, self-supervised diffusion model for histopathology images, enabling diverse image synthesis and downstream applications like virtual staining and privacy-preserving data sharing.

Findings

PixCell effectively generates high-fidelity synthetic histopathology images.

Synthetic data improves classification performance on small datasets.

PixCell enables virtual IHC staining from H&E images.

Abstract

The digitization of histology slides has revolutionized pathology, providing massive datasets for cancer diagnosis and research. Self-supervised and vision-language models have been shown to effectively mine large pathology datasets to learn discriminative representations. On the other hand, there are unique problems in pathology, such as annotated data scarcity, privacy regulations in data sharing, and inherently generative tasks like virtual staining. Generative models, capable of synthesizing realistic and diverse images, present a compelling solution to address these problems through image synthesis. We introduce PixCell, the first generative foundation model for histopathology images. PixCell is a diffusion model trained on PanCan-30M, a large, diverse dataset derived from 69,184 H&E-stained whole slide images of various cancer types. We employ a progressive training strategy and a self-supervision-based conditioning that allows us to scale up training without any human-annotated data. By conditioning on real slides, the synthetic images capture the properties of the real data and can be used as data augmentation for small-scale datasets to boost classification performance. We prove the foundational versatility of PixCell by applying it to two generative downstream tasks: privacy-preserving synthetic data generation and virtual IHC staining. PixCell's high-fidelity conditional generation enables institutions to use their private data to synthesize highly realistic, site-specific surrogate images that can be shared in place of raw patient data. Furthermore, using datasets of roughly paired H&E-IHC tiles, we learn to translate PixCell's conditioning from H&E to multiple IHC stains, allowing the generation of IHC images from H&E inputs. Our trained models are publicly released to accelerate research in computational pathology.