Seamless Whole Slide Label-Free Virtual Staining
Abstract
Label-free virtual staining offers a compelling, non-destructive alternative to standard histopathology; however, its clinical adoption is hindered by the computational bottlenecks inherent to processing gigapixel Whole Slide Images (WSIs). Current deep learning approaches require patch-based inference to avoid memory constraints, which disrupts global tissue continuity and introduces tiling artifacts--displaying visible seams and color shifts. To address this, we introduce the Consistency Memory Bank (COMB), a novel label-free virtual staining framework that enforces spatial and channel consistency across tiles without memory bottlenecks. COMB decouples context storage from computation, utilizing a dynamic retrieval mechanism to fetch feature representations from adjacent tiles. This enables a retrieval-based context integration strategy that adopts local padding to resolve spatial discontinuities and neighbor-aware channel attention to stabilize statistical drift. Further optimized with a sliding window schedule to ensure minimal memory overhead, our method demonstrates superior performance over state-of-the-art baselines, achieving significant improvements in both perceptual fidelity and tiling consistency, while suggesting its downstream utility in tumor segmentation. Code is available at https://github.com/dou0000/COMB.
Related
- Supervised 3D Virtual Fluorescence and Pseudo-H&E Staining of Fresh Bulk Tissues via Multimodal qOBM and Fluorescence Microscopy
- StainAI-Web: An Interactive Platform for Whole-Slide Microglial Morphology Analysis
- Prompting Beyond Pairs: Decoupled Semantic Supervision for Knowledge-Guided Multiplex Virtual Staining
- Generalizable virtual staining from histopathology to spatial proteomics across biological scales
- Development of a SCGP-CGAN framework for bidirectional H&E–Masson’s Trichrome Virtual Staining
BibTeX
@misc{kwark2026seamless,
title = {{Seamless Whole Slide Label-Free Virtual Staining}},
author = {Dou Hoon Kwark and Kianoush Falahkheirkhah and Ji-hun Oh and Shirui Luo and Volodymyr Kindratenko and Rohit Bhargava},
howpublished = {arXiv},
year = {2026},
month = sep,
doi = {10.48550/arxiv.2609.10914},
eprint = {2609.10914},
archivePrefix = {arXiv},
url = {https://arxiv.org/abs/2609.10914},
}
RIS
TY - UNPB
TI - Seamless Whole Slide Label-Free Virtual Staining
AU - Dou Hoon Kwark
AU - Kianoush Falahkheirkhah
AU - Ji-hun Oh
AU - Shirui Luo
AU - Volodymyr Kindratenko
AU - Rohit Bhargava
PY - 2026
DA - 2026/09/09
PB - arXiv
DO - 10.48550/arxiv.2609.10914
UR - https://arxiv.org/abs/2609.10914
AB - Label-free virtual staining offers a compelling, non-destructive alternative to standard histopathology; however, its clinical adoption is hindered by the computational bottlenecks inherent to processing gigapixel Whole Slide Images (WSIs). Current deep learning approaches require patch-based inference to avoid memory constraints, which disrupts global tissue continuity and introduces tiling artifacts--displaying visible seams and color shifts. To address this, we introduce the Consistency Memory Bank (COMB), a novel label-free virtual staining framework that enforces spatial and channel consistency across tiles without memory bottlenecks. COMB decouples context storage from computation, utilizing a dynamic retrieval mechanism to fetch feature representations from adjacent tiles. This enables a retrieval-based context integration strategy that adopts local padding to resolve spatial discontinuities and neighbor-aware channel attention to stabilize statistical drift. Further optimized with a sliding window schedule to ensure minimal memory overhead, our method demonstrates superior performance over state-of-the-art baselines, achieving significant improvements in both perceptual fidelity and tiling consistency, while suggesting its downstream utility in tumor segmentation. Code is available at https://github.com/dou0000/COMB.
ER -