Fourier Transform Infrared microspectroscopy-based super-resolution virtual staining of unlabeled tissues by pixel Diffusion Transformer

TL;DR

This paper introduces a diffusion transformer-based method for super-resolution virtual staining of unlabeled tissues, transforming low-resolution FTIR images into high-resolution H&E-stained images with improved speed and accuracy.

Contribution

The authors develop a novel pixel diffusion transformer that models the transformation as a stochastic process, enabling rapid, high-quality virtual staining from infrared spectroscopic images.

Findings

Achieves 4x pixel-level super-resolution of FTIR images.

Speeds up inference fourfold compared to U-Net diffusion models.

Generates clinically usable high-resolution stained images.

Abstract

Here, we present a diffusion transformer (DiT)-based pixel super-resolution virtual staining approach to transform low-resolution FTIR microspectroscopic images of the unstained tissues into corresponding high-resolution H&E-stained images. Unlike conventional conditional DiT architectures, this method models the transformation from FTIR images to H&E-stained images as a stochastic Brownian bridge process and directly learns the cross-domain translation in pixel space by means of a large-patch Transformer. When applied to FTIR images of unlabeled human lung tissue samples, the proposed method successfully transforms them into high-resolution H&E-stained images, achieving a 4 times pixel-level super-resolution. Additionally, by partitioning images into large patches, our method achieves a fourfold improvement in inference speed compared with traditional U-Net-based diffusion models, without compromising the quality of generated images. This super-resolution virtual staining method provides a rapid and effective solution for generating high-resolution, clinically usable H&E-stained images from infrared spectroscopic images, which can significantly facilitate the incorporation of FTIR microspectroscopy into clinical histological scenarios.