Fourier Transform Infrared microspectroscopy-based super-resolution virtual staining of unlabeled tissues by pixel Diffusion Transformer
Fuente:
arXiv
Salvato in:
| Autori principali: | , , , , |
|---|---|
| Natura: | Preprint |
| Pubblicazione: |
2026
|
| Soggetti: | |
| Accesso online: | |
| Tags: |
Aggiungi Tag
Nessun Tag, puoi essere il primo ad aggiungerne!!
|
| _version_ | 1866912954934362112 |
|---|---|
| author | Tian, Yudong Zhao, Xiangyu Liu, Yuqing Yang, Bofei Wu, Chongzhao |
| author_facet | Tian, Yudong Zhao, Xiangyu Liu, Yuqing Yang, Bofei Wu, Chongzhao |
| contents | 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. |
| format | Preprint |
| id |
arxiv_https___arxiv_org_abs_2603_08143 |
| institution | arXiv |
| publishDate | 2026 |
| record_format | arxiv |
| spellingShingle | Fourier Transform Infrared microspectroscopy-based super-resolution virtual staining of unlabeled tissues by pixel Diffusion Transformer Tian, Yudong Zhao, Xiangyu Liu, Yuqing Yang, Bofei Wu, Chongzhao Optics 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. |
| title | Fourier Transform Infrared microspectroscopy-based super-resolution virtual staining of unlabeled tissues by pixel Diffusion Transformer |
| topic | Optics |
| url | https://arxiv.org/abs/2603.08143 |