LatentArtiFusion: An Effective and Efficient Histological Artifacts Restoration Framework

TL;DR

LatentArtiFusion is a novel framework that uses latent diffusion models to efficiently restore histological artifacts, outperforming existing GAN and pixel-level diffusion methods in speed and accuracy, with practical benefits for tissue analysis.

Contribution

The paper introduces LatentArtiFusion, a new artifact restoration framework leveraging latent diffusion models and a regional reconstruction algorithm for improved efficiency and accuracy.

Findings

Over 30X faster than pixel-level diffusion frameworks.

At least 5% better accuracy than GAN-based methods.

Effective in downstream tissue classification tasks.

Abstract

Histological artifacts pose challenges for both pathologists and Computer-Aided Diagnosis (CAD) systems, leading to errors in analysis. Current approaches for histological artifact restoration, based on Generative Adversarial Networks (GANs) and pixel-level Diffusion Models, suffer from performance limitations and computational inefficiencies. In this paper, we propose a novel framework, LatentArtiFusion, which leverages the latent diffusion model (LDM) to reconstruct histological artifacts with high performance and computational efficiency. Unlike traditional pixel-level diffusion frameworks, LatentArtiFusion executes the restoration process in a lower-dimensional latent space, significantly improving computational efficiency. Moreover, we introduce a novel regional artifact reconstruction algorithm in latent space to prevent mistransfer in non-artifact regions, distinguishing our approach from GAN-based methods. Through extensive experiments on real-world histology datasets, LatentArtiFusion demonstrates remarkable speed, outperforming state-of-the-art pixel-level diffusion frameworks by more than 30X. It also consistently surpasses GAN-based methods by at least 5% across multiple evaluation metrics. Furthermore, we evaluate the effectiveness of our proposed framework in downstream tissue classification tasks, showcasing its practical utility. Code is available at https://github.com/bugs-creator/LatentArtiFusion.