Artifact Restoration in Histology Images with Diffusion Probabilistic Models

TL;DR

This paper introduces ArtiFusion, a novel diffusion probabilistic model for restoring artifacts in histology images, overcoming GAN limitations and preserving tissue details through a denoising process and transformer architecture.

Contribution

First application of diffusion probabilistic models to histological artifact restoration, with a new Swin-Transformer denoising architecture and training on artifact-free images.

Findings

Effective artifact removal preserving tissue structure

Outperforms GAN-based methods in realism and stability

Enhances histology analysis accuracy

Abstract

Histological whole slide images (WSIs) can be usually compromised by artifacts, such as tissue folding and bubbles, which will increase the examination difficulty for both pathologists and Computer-Aided Diagnosis (CAD) systems. Existing approaches to restoring artifact images are confined to Generative Adversarial Networks (GANs), where the restoration process is formulated as an image-to-image transfer. Those methods are prone to suffer from mode collapse and unexpected mistransfer in the stain style, leading to unsatisfied and unrealistic restored images. Innovatively, we make the first attempt at a denoising diffusion probabilistic model for histological artifact restoration, namely ArtiFusion.Specifically, ArtiFusion formulates the artifact region restoration as a gradual denoising process, and its training relies solely on artifact-free images to simplify the training complexity.Furthermore, to capture local-global correlations in the regional artifact restoration, a novel Swin-Transformer denoising architecture is designed, along with a time token scheme. Our extensive evaluations demonstrate the effectiveness of ArtiFusion as a pre-processing method for histology analysis, which can successfully preserve the tissue structures and stain style in artifact-free regions during the restoration. Code is available at https://github.com/zhenqi-he/ArtiFusion.