Saved in:
Bibliographic Details
Main Authors: Ma, Rongze, Lu, Mengkang, Xiang, Zhenyu, Pan, Yongsheng, Wu, Yicheng, Zeng, Qingjie, Xia, Yong
Format: Preprint
Published: 2026
Subjects:
Online Access:https://arxiv.org/abs/2601.16024
Tags: Add Tag
No Tags, Be the first to tag this record!
_version_ 1866911392269860864
author Ma, Rongze
Lu, Mengkang
Xiang, Zhenyu
Pan, Yongsheng
Wu, Yicheng
Zeng, Qingjie
Xia, Yong
author_facet Ma, Rongze
Lu, Mengkang
Xiang, Zhenyu
Pan, Yongsheng
Wu, Yicheng
Zeng, Qingjie
Xia, Yong
contents Virtual immunohistochemistry (IHC) aims to computationally synthesize molecular staining patterns from routine Hematoxylin and Eosin (H\&E) images, offering a cost-effective and tissue-efficient alternative to traditional physical staining. However, this task is particularly challenging: H\&E morphology provides ambiguous cues about protein expression, and similar tissue structures may correspond to distinct molecular states. Most existing methods focus on direct appearance synthesis to implicitly achieve cross-modal generation, often resulting in semantic inconsistencies due to insufficient structural priors. In this paper, 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. Unlike direct image translation, PAINT enforces a causal order by resolving molecular details conditioned on a global structural layout. Central to this approach is the introduction of a Spatial Structural Start Map (3S-Map), which grounds the autoregressive initialization in observed morphology, ensuring deterministic, spatially aligned synthesis. Experiments on the IHC4BC and MIST datasets demonstrate that PAINT outperforms state-of-the-art methods in structural fidelity and clinical downstream tasks, validating the potential of structure-guided autoregressive modeling.
format Preprint
id arxiv_https___arxiv_org_abs_2601_16024
institution arXiv
publishDate 2026
record_format arxiv
spellingShingle PAINT: Pathology-Aware Integrated Next-Scale Transformation for Virtual Immunohistochemistry
Ma, Rongze
Lu, Mengkang
Xiang, Zhenyu
Pan, Yongsheng
Wu, Yicheng
Zeng, Qingjie
Xia, Yong
Computer Vision and Pattern Recognition
Virtual immunohistochemistry (IHC) aims to computationally synthesize molecular staining patterns from routine Hematoxylin and Eosin (H\&E) images, offering a cost-effective and tissue-efficient alternative to traditional physical staining. However, this task is particularly challenging: H\&E morphology provides ambiguous cues about protein expression, and similar tissue structures may correspond to distinct molecular states. Most existing methods focus on direct appearance synthesis to implicitly achieve cross-modal generation, often resulting in semantic inconsistencies due to insufficient structural priors. In this paper, 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. Unlike direct image translation, PAINT enforces a causal order by resolving molecular details conditioned on a global structural layout. Central to this approach is the introduction of a Spatial Structural Start Map (3S-Map), which grounds the autoregressive initialization in observed morphology, ensuring deterministic, spatially aligned synthesis. Experiments on the IHC4BC and MIST datasets demonstrate that PAINT outperforms state-of-the-art methods in structural fidelity and clinical downstream tasks, validating the potential of structure-guided autoregressive modeling.
title PAINT: Pathology-Aware Integrated Next-Scale Transformation for Virtual Immunohistochemistry
topic Computer Vision and Pattern Recognition
url https://arxiv.org/abs/2601.16024