# HistDiT: A Structure-Aware Latent Conditional Diffusion Model for High-Fidelity Virtual Staining in Histopathology

arXiv: https://arxiv.org/abs/2604.08305 · HTML: https://mlsanity.com/paper/2604.08305/

## Key facts

- Cited by 1 papers in the map (data through 14 Oct 2026).
- Placed in Medical imaging and segmentation, one of 14 directions in Diffusion models.
- Builds on 21 of its 37 references that are in the map.
- First posted on arXiv 9 Apr 2026.

## Placed in

- Diffusion models / [Medical imaging and segmentation](https://mlsanity.com/diffusion/medical-imaging-and-segmentation/)

## Builds on (most cited first, 21 of 21)

- [An Image is Worth 16x16 Words: Transformers for Image Recognition at Scale](https://mlsanity.com/paper/2010.11929/) (2020)
- [Denoising Diffusion Probabilistic Models](https://mlsanity.com/paper/2006.11239/) (2020)
- [High-Resolution Image Synthesis with Latent Diffusion Models](https://mlsanity.com/paper/2112.10752/) (2021)
- [GPT-4 Technical Report](https://mlsanity.com/paper/2303.08774/) (2023)
- [The Unreasonable Effectiveness of Deep Features as a Perceptual Metric](https://mlsanity.com/paper/1801.03924/) (2018)
- [Diffusion Models Beat GANs on Image Synthesis](https://mlsanity.com/paper/2105.05233/) (2021)
- [Scalable Diffusion Models with Transformers](https://mlsanity.com/paper/2212.09748/) (2022)
- [Image-to-Image Translation with Conditional Adversarial Networks](https://mlsanity.com/paper/1611.07004/) (2016)
- [Improved Denoising Diffusion Probabilistic Models](https://mlsanity.com/paper/2102.09672/) (2021)
- [Diffusion Models for Medical Image Analysis: A Comprehensive Survey](https://mlsanity.com/paper/2211.07804/) (2022)
- [Unsupervised Medical Image Translation with Adversarial Diffusion Models](https://mlsanity.com/paper/2207.08208/) (2022)
- [PTQ4DiT: Post-training Quantization for Diffusion Transformers](https://mlsanity.com/paper/2405.16005/) (2024)
- [A Morphology Focused Diffusion Probabilistic Model for Synthesis of Histopathology Images](https://mlsanity.com/paper/2209.13167/) (2022)
- [BCI: Breast Cancer Immunohistochemical Image Generation through Pyramid Pix2pix](https://mlsanity.com/paper/2204.11425/) (2022)
- [Improved Noise Schedule for Diffusion Training](https://mlsanity.com/paper/2407.03297/) (2024)
- [Adaptive Supervised PatchNCE Loss for Learning H&E-to-IHC Stain Translation with Inconsistent Groundtruth Image Pairs](https://mlsanity.com/paper/2303.06193/) (2023)
- [DEsignBench: Exploring and Benchmarking DALL-E 3 for Imagining Visual Design](https://mlsanity.com/paper/2310.15144/) (2023)
- [A Hitchhiker's Guide to Structural Similarity](https://mlsanity.com/paper/2101.06354/) (2021)
- [PixCell: A generative foundation model for digital histopathology images](https://mlsanity.com/paper/2506.05127/) (2025)
- [HistDiST: Histopathological Diffusion-based Stain Transfer](https://mlsanity.com/paper/2505.06793/) (2025)
- [From Pixels to Pathology: Restoration Diffusion for Diagnostic-Consistent Virtual IHC](https://mlsanity.com/paper/2508.02528/) (2025)

## Built on by (most cited first, 1 of 1)

- [SheafStain: Sheaf-Theoretic Schr"odinger Bridge for Spatially and Biologically Coherent Virtual Staining](https://mlsanity.com/paper/2606.11846/) (2026)

## Abstract (arXiv)

Immunohistochemistry (IHC) is essential for assessing specific immune biomarkers like Human Epidermal growth-factor Receptor 2 (HER2) in breast cancer. However, the traditional protocols of obtaining IHC stains are resource-intensive, time-consuming, and prone to structural damages. Virtual staining has emerged as a scalable alternative, but it faces significant challenges in preserving fine-grained cellular structures while accurately translating biochemical expressions. Current state-of-the-art methods still rely on Generative Adversarial Networks (GANs) or standard convolutional U-Net diffusion models that often struggle with "structure and staining trade-offs". The generated samples are either structurally relevant but blurry, or texturally realistic but have artifacts that compromise their diagnostic use. In this paper, we introduce HistDiT, a novel latent conditional Diffusion Transformer (DiT) architecture that establishes a new benchmark for visual fidelity in virtual histological staining. The novelty introduced in this work is, a) the Dual-Stream Conditioning strategy that explicitly maintains a balance between spatial constraints via VAE-encoded latents and semantic phenotype guidance via UNI embeddings; b) the multi-objective loss function that contributes to sharper images with clear morphological structure; and c) the use of the Structural Correlation Metric (SCM) to focus on the core morphological structure for precise assessment of sample quality. Consequently, our model outperforms existing baselines, as demonstrated through rigorous quantitative and qualitative evaluations.