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

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

    Mar 13, 2026Jillur Rahman Saurav, Thuong Le Hoai Pham, Pritam Mukherjee +3Virtual StainingComputational Pathology

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

    Nov 10, 2026Ashley P. Tsang, Evan Liu, Conrad Foo +10Spatial Gene Expression PredictionGene Expression Prediction from Histopathology Images

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

    Mar 17, 2026Junhyeok Lee, Han Jang, Heeseong Eum +2Virtual StainingMedical Image Synthesis