cs.CVNov 15, 2026

HEmIF-Bench: Benchmarking H&E-to-mIF Models BeyondVirtual-StainFidelity

Authors: Fuxian Zhao, Hyokeun Park

Organizations: Department of Physics, The Hong Kong University of Science and Technology, Hong Kong SAR, China · Division of Life Science, The Hong Kong University of Science and Technology, Hong Kong SAR, China

Abstract

Hematoxylin and eosin (H&E)-to-multiplex immunofluorescence (mIF) generators predict spatial protein expression from routine histology, yet pixel-level marker reconstruction does not establish downstream utility. We present HEmIF-Bench, evaluating five frozen generators across eight datasets spanning molecular, cellular, tissue, and patient scales. HEmIF-Bench decouples internal encoder features from generated outputs, benchmarking both against the pathology foundation reference UNI2. Mirroring the clinical workflow where pathologists rely on mIF to define cell phenotypes, delineate tertiary lymphoid structures (TLSs) and germinal centers (GCs), and stratify patient risk, we evaluate external CD3 recovery, single-cell classification, dense nuclear segmentation, TLS/GC segmentation, and patient survival prediction. Across the benchmark, foundation-model-based MIPHEI-ViT leads among the generators, while non-foundation models show task-specific strengths. Comparing the two routes reveals that internal encoder features generally outperform generated outputs, and larger output marker panels do not guarantee stronger downstream utility across datasets. Moreover, neither internal encoder features nor generated outputs consistently surpass frozen UNI2. These findings show that pixel-level stain fidelity does not equate to downstream utility, and that generators trained at current paired-data scales have yet to surpass large-scale pure-H&E foundation models. With the expansion of paired translation cohorts and the advancement of foundation-based generative architectures, HEmIF-Bench establishes a definitive benchmark for tracking when H&E-to-mIF generation crosses the threshold to deliver genuine value beyond routine histology for tumor microenvironment analysis and precision oncology.

Figures & tables

Explore similar work

Mar 13, 2026

UNIStainNet: Foundation-Model-Guided Virtual Staining of H&E to IHC

Virtual immunohistochemistry (IHC) staining from hematoxylin and eosin (H&E) images can accelerate diagnostics by providing preliminary molecular insight directly from routine sections, reducing the need for repeat sectioning when tissue is limited. Existing methods improve realism through contrastive objectives, prototype matching, or domain alignment, yet the generator itself receives no direct guidance from pathology foundation models. We present UNIStainNet, a SPADE-UNet conditioned on dense spatial tokens from a frozen pathology foundation model (UNI), providing tissue-level semantic guidance for stain translation. A misalignment-aware loss suite preserves stain quantification accuracy, and learned stain embeddings enable a single model to serve multiple IHC markers simultaneously. On MIST, UNIStainNet achieves state-of-the-art distributional metrics on all four stains (HER2, Ki67, ER, PR) from a single unified model, where prior methods typically train separate per-stain models. On BCI, it also achieves the best distributional metrics. A tissue-type stratified failure analysis reveals that remaining errors are systematic, concentrating in non-tumor tissue. Code is available at https://github.com/facevoid/UNIStainNet.
Nov 10, 2026

Predicting Single-Cell Spatial Gene Expression from H&E using Pathology Foundation Models

Predicting gene expression directly from hematoxylin and eosin (H&E) images offers a scalable and cost-effective approach to deriving spatial molecular insights from routine histology. Pathology foundation models, typically pretrained using tile-level objectives, may not adequately capture the fine-grained cellular features required for single-cell molecular prediction. In this work, we systematically evaluate and establish domain-informed and task-specific strategies for adapting pathology foundation models to single-cell spatial gene expression prediction. Using paired H&E and Xenium 5K data, our approach improves mean gene-wise Pearson correlation by 2.67x over the standard zero-shot baseline and achieves state-of-the-art performance on this task. We demonstrate strong gene-detection performance across the full gene panel (AUROC = 0.800) and importantly identify that predictive performance varies substantially across biological contexts, with our model achieving its highest Pearson correlation for spatially variable genes (r = 0.643). Our findings demonstrate that, despite the challenges of sparse single-cell measurements, H&E-derived representations can recover biologically meaningful spatial expression patterns, highlighting both the opportunities and limitations of morphology-based molecular inference at cellular resolution.
Mar 17, 2026

Segmentation-before-Staining Improves Structural Fidelity in Virtual IHC-to-Multiplex IF Translation

Multiplex immunofluorescence (mIF) enables simultaneous single-cell quantification of multiple biomarkers within intact tissue architecture, yet its high reagent cost, multi-round staining protocols, and need for specialized imaging platforms limit routine clinical adoption. Virtual staining can synthesize mIF channels from widely available brightfield immunohistochemistry (IHC), but current translators optimize pixel-level fidelity without explicitly constraining nuclear morphology. In pathology, this gap is clinically consequential: subtle distortions in nuclei count, shape, or spatial arrangement propagate directly to quantification endpoints such as the Ki67 proliferation index, where errors of a few percent can shift treatment-relevant risk categories. This work introduces a supervision-free, architecture-agnostic conditioning strategy that injects a continuous cell probability map from a pretrained nuclei segmentation foundation model as an explicit input prior, together with a variance-preserving regularization term that matches local intensity statistics to maintain cell-level heterogeneity in synthesized fluorescence channels. The soft prior retains gradient-level boundary information lost by binary thresholding, providing a richer conditioning signal without task-specific tuning. Controlled experiments across Pix2Pix with U-Net and ResNet generators, deterministic regression U-Net, and conditional diffusion on two independent datasets demonstrate consistent improvements in nuclei count fidelity and perceptual quality, as the sole modifications. Code will be made publicly available upon acceptance.