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

• URL: http://arxiv.org/abs/2604.08305v1
• Date: Thu, 09 Apr 2026 14:39:37 GMT
• Title: HistDiT: A Structure-Aware Latent Conditional Diffusion Model for High-Fidelity Virtual Staining in Histopathology
• Abstract summary: HistDiT architecture establishes a new benchmark for visual fidelity in virtual histological staining.<n>Our model outperforms existing baselines as demonstrated through rigorous quantitative and qualitative evaluations.
• Score: 3.5196641463125
• License: http://arxiv.org/licenses/nonexclusive-distrib/1.0/
• Abstract: 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.

Related papers

• Towards Reliable Stain Transfer: An Iterative Data-Model Co-Optimization Framework Based on Multimodal Expert-Guided Assessment [55.16957949238588]
  We propose DMCoStain, a novel Data-Model Co-optimization framework for Stain transfer.<n>It iteratively co-refines training data and model capability, improving staining accuracy and interpretability in both pathological and structural consistency.<n>To support MEGFS, we construct ImmunoInstruction, the first large-scale IPE instruction-following dataset with 150K VQA samples.
  arXiv  Detail & Related papers  (2026-07-28T07:54:43Z)
• PathAR: Structure-First Autoregressive Synthesis of Multimodal Pathology Images [51.428093790826814]
  We propose pathology Autorgressive modeling (PathAR) to factorize structure and appearance for modality-label-conditioned pathology generation.<n>PathAR stabilizes morphology under heterogeneous modality-specific appearances and enables spatially aligned image-mask pair generation.
  arXiv  Detail & Related papers  (2026-06-01T01:43:48Z)
• Multi-View Synergistic Learning with Vision-Language Adaption for Low-Resource Biomedical Image Classification [59.24009931000134]
  Multi-View Synergistic Learning (MVSL) is a unified framework that addresses adaptation paradigms, representation granularity, and disease semantic relationships.<n>MVSL decouples the adaptation of visual and textual encoders to respect their distinct representational characteristics.<n>It further introduces multi-granularity contrastive learning to explicitly model both global image semantics and localized lesion-level evidence.<n>MVSL consistently outperforms state-of-the-art methods in few-shot and zero-shot classification settings.
  arXiv  Detail & Related papers  (2026-04-27T02:41:27Z)
• PHASOR: Anatomy- and Phase-Consistent Volumetric Diffusion for CT Virtual Contrast Enhancement [60.81732730684265]
  This paper introduces PHASOR, a volumetric diffusion framework for high-fidelity virtual contrast enhancement (VCE)<n>By treating CT volumes as coherent sequences, we leverage a video diffusion model to enhance structural coherence and volumetric accuracy.<n>To ensure anatomy-phase consistent synthesis, we introduce two complementary modules. First, anatomy-routed mixture-of-experts (AR-MoE) anchors distinct enhancement patterns to anatomical semantics, with organ-specific memory to capture salient details.<n>Second, intensity-phase aware representation alignment (IP-REPA) highlights intricate contrast signals while mitigating the impact of imperfect spatial alignment.
  arXiv  Detail & Related papers  (2026-04-01T15:57:18Z)
• Layout-Guided Controllable Pathology Image Generation with In-Context Diffusion Transformers [57.54843029965778]
  Controllable pathology image synthesis requires reliable regulation of spatial layout, tissue morphology, and semantic detail.<n>We propose In-Context Diffusion Transformer (IC-DiT), a layout-aware generative model that incorporates spatial layouts, textual descriptions, and visual embeddings into a unified diffusion transformer.<n>IC-DiT achieves higher fidelity, stronger spatial controllability, and better diagnostic consistency than existing methods.
  arXiv  Detail & Related papers  (2026-03-11T06:14:11Z)
• Structure-constrained Language-informed Diffusion Model for Unpaired Low-dose Computed Tomography Angiography Reconstruction [72.80209358480424]
  overdose of iodinated contrast media (ICM) can cause kidney damage and life-threatening allergic reactions.<n>Deep learning methods can generate CT images of normal-dose ICM from low-dose ICM, reducing the required dose.<n>We propose a Structure-constrained Language-informed Diffusion Model (SLDM) that integrates structural synergy and spatial intelligence.
  arXiv  Detail & Related papers  (2026-01-28T06:54:06Z)
• PAINT: Pathology-Aware Integrated Next-Scale Transformation for Virtual Immunohistochemistry [17.230315436967356]
  Virtualchemistry aims to computationally synthesize molecular staining patterns from routine Hematoxylin and Eosin (H&E) images.<n>We propose Pathology-Aware Integrated Next-Scale Transformation (PAINT), a visual autoregressive framework that reformulates the synthesis process as a structure-first conditional generation task.
  arXiv  Detail & Related papers  (2026-01-22T14:49:30Z)
• A Semantically Enhanced Generative Foundation Model Improves Pathological Image Synthesis [82.01597026329158]
  We introduce a Correlation-Regulated Alignment Framework for Tissue Synthesis (CRAFTS) for pathology-specific text-to-image synthesis.<n>CRAFTS incorporates a novel alignment mechanism that suppresses semantic drift to ensure biological accuracy.<n>This model generates diverse pathological images spanning 30 cancer types, with quality rigorously validated by objective metrics and pathologist evaluations.
  arXiv  Detail & Related papers  (2025-12-15T10:22:43Z)
• Progressive Translation of H&E to IHC with Enhanced Structural Fidelity [8.881744407746845]
  Compared to hematoxylin-eosin (H&E) staining, gradientchemistry (IHC) provides high-resolution protein localization.<n>Despite its diagnostic value, IHC remains a costly and labor-intensive technique.<n>We propose a novel network architecture that follows a progressive structure, incorporating color and cell border generation logic.
  arXiv  Detail & Related papers  (2025-11-03T16:06:46Z)
• From Pixels to Pathology: Restoration Diffusion for Diagnostic-Consistent Virtual IHC [37.284994932355865]
  We introduce Star-Diff, a structure-aware staining restoration diffusion model that reformulates virtual staining as an image restoration task.<n>By combining residual and noise-based generation pathways, Star-Diff maintains tissue structure while modeling realistic biomarker variability.<n> Experiments on the BCI dataset demonstrate that Star-Diff achieves state-of-the-art (SOTA) performance in both visual fidelity and diagnostic relevance.
  arXiv  Detail & Related papers  (2025-08-04T15:36:58Z)
• Score-based Diffusion Model for Unpaired Virtual Histology Staining [7.648204151998162]
  Hematoxylin and eosin (H&E) staining visualizes histology but lacks specificity for diagnostic markers.<n>Hematoxylin and eosin (H&E) staining provides protein-targeted staining but is restricted by tissue availability and antibody specificity.<n>Virtual staining, i.e., translating the H&E image to its IHC counterpart while preserving tissue structure, is promising for efficient IHC generation.<n>This study proposes a mutual-information (MI)-guided score-based diffusion model for unpaired virtual staining.
  arXiv  Detail & Related papers  (2025-06-29T11:02:45Z)
• HistDiST: Histopathological Diffusion-based Stain Transfer [4.936165689668498]
  HistDiST is a Latent Diffusion Model (LDM) based framework for high-fidelity H&E-to-IHC translation.<n>HistDiST significantly outperforms existing methods, achieving a 28% improvement in MRA on evaluations H&E-to-Ki6767.
  arXiv  Detail & Related papers  (2025-05-11T00:19:22Z)
• StealthDiffusion: Towards Evading Diffusion Forensic Detection through Diffusion Model [62.25424831998405]
  StealthDiffusion is a framework that modifies AI-generated images into high-quality, imperceptible adversarial examples. It is effective in both white-box and black-box settings, transforming AI-generated images into high-quality adversarial forgeries.
  arXiv  Detail & Related papers  (2024-08-11T01:22:29Z)

This list is automatically generated from the titles and abstracts of the papers in this site.

This site does not guarantee the quality of this site (including all information) and is not responsible for any consequences.