Data & Evidence

Pictor Labs’ virtual staining technology generates additional histologic views (including H&E, IHC-like, and other stain representations) from existing specimens. Our models are trained on expertly curated, co-registered image pairs to provide visually comparable, consistent virtual stains that support diverse research and downstream workflows.

The Science Behind Virtual Staining

Pictor Labs’ virtual staining technologies are evaluated through peer-reviewed research, validating performance against established histologic and diagnostic standards. Our publications span virtual H&E generation, IHC-like marker translation, and cross-modality stain transformation, with results reviewed by the scientific and pathology community.

Conference SITC 2024 2024
Multi-modal spatial analysis of classic Hodgkin lymphoma microenvironment utilizing multiplex immunofluorescence and virtual staining

At SITC 2024, Pictor Labs—alongside Leica Biosystems and the University of Maryland—demonstrates how virtual H&E (vHE) staining enables regulatory T-cell subtyping and tumor microenvironment analysis in cancer research.

Spatial Analysis View
Conference AACR 2024 2024
Combination analysis of tumor-associated collagen frameworks and tumor immune phenotype of lung carcinomas using virtual staining

At AACR 2024, Pictor Labs presents virtual multiplex special stains and IHC to support immune phenotyping and classification of lung carcinoma for pathologists.

Immune Phenotyping View
Conference USCAP 2024 2024
Assessment of AI Computational H&E Staining Versus Chemical H&E Staining For Primary Diagnosis in Lymphomas

At USCAP 2024, Pictor Labs, with Johns Hopkins, UCLA, and University of Maryland, presents a study comparing AI computational H&E staining to chemical staining for lymphoma diagnosis.

Diagnostic Concordance View
Journal Journal of Hematopathology 2024
AI-based computational H&E staining in lymphomas

Published in Journal of Hematopathology 2024, Pictor Labs’ AI-driven virtual staining technology rapidly generates high-quality digital pathology images and multiplex immunostains from unstained FFPE tissue slides—enhancing diagnostic accuracy, preserving valuable biopsy samples, and accelerating hematopathology research and clinical workflows.

Multiplex IHC View
Journal Int. Journal of Surgical Pathology 2024
AI-Based Computational H&E Staining Enables Spatial Transcriptomic Analysis in Classic Hodgkin Lymphoma

Published in International Journal of Surgical Pathology 2024, Pictor Labs demonstrates AI-based computational H&E staining that enables advanced spatial transcriptomic analysis in classic Hodgkin lymphoma, enhancing lymphoma research with cutting-edge machine learning and neural network technology.

Spatial Transcriptomics View
Conference AACR 2023 2023
Virtual staining enabled combined morphological and spatial transcriptomic analysis of individual malignant B cells and local tumor microenvironments

At AACR 2023—in collaboration with NanoString and the University of Maryland School of Medicine—Pictor Labs presents virtual staining–enabled morphological and spatial transcriptomic analysis of malignant B cells and the tumor microenvironment.

Spatial Transcriptomics View
Conference ASCO Breakthrough 2023 2023
Realtime, multiplexed rendering of lymphoma diagnostic panels from unstained tissue sections using virtual staining

At ASCO Breakthrough 2023, Pictor Labs—in collaboration with the University of Maryland—leverages AI-driven virtual staining technology to rapidly generate multiplex virtual IHC markers (CD3, CD20, and PAX5) from a single unstained tissue, accelerating immune cell phenotyping and tumor analysis.

Virtual IHC View
Conference SITC 2023 2023
Spatial Overlay: A novel approach for evaluating tumor microenvironment (TME) specific expression of PD-L1 in whole slide images of lung cancer

At SITC 2023, Pictor Labs showcases AI-driven virtual staining generating multiplex virtual stains (PanCK, CD45 LCA, H&E) from a single unstained tissue, enhancing PD-L1 scoring and patient selection in non-small cell lung cancer (NSCLC) immunotherapy.

PD-L1 / NSCLC View
Journal BMEF (Science Partner Journal) 2022
Label-Free Virtual HER2 Immunohistochemical Staining of Breast Tissue using Deep Learning

Published in BMEF: A Science Partner Journal 2022, Pictor Labs presents an AI-based method that replicates HER2 immunohistochemistry from autofluorescence breast tissue images, offering a faster, cost-effective alternative for cancer diagnostics.

Virtual HER2 IHC View
Conference Charles River (collaboration) Year TBD
Deep Learning-Enabled Virtual H&E and FluoroJade B Tissue Staining for Neuronal Degeneration

In collaboration with Charles River, Pictor Labs’ AI-driven virtual staining generates H&E and Fluoro-Jade B images from unstained brain sections, streamlining neuronal degeneration assessment in nonclinical neurotoxicity studies (kainic acid rat model).

Neurotoxicity View
Journal Nature Communications 2021
Deep learning-based transformation of H&E stained tissues into special stains

Published in Nature Communications 2021, Pictor Labs demonstrates AI-based transformation of H&E-stained kidney biopsies into virtual special stains (Masson’s Trichrome, PAS, Jones), enabling improved research workflows and supporting histological assessment of non-neoplastic kidney disease.

Special Stains View
Journal Light: Science & Applications 2020
Digital synthesis of histological stains using micro-structured and multiplexed virtual staining of label-free tissue

Published in Light: Science & Applications 2020, Pictor Labs’ deep learning framework enables virtual multiplex staining of label-free tissue by digitally applying different histological stains—such as H&E, Jones, and Trichrome—to distinct tissue microstructures within the same section, supporting advanced spatial tissue analysis.

Multiplex Staining View
Journal Nature Biomedical Engineering 2019
Virtual histological staining of unlabelled tissue-autofluorescence images via deep learning

Published in Nature Biomedical Engineering 2019, Pictor Labs’ deep learning-based virtual staining transforms autofluorescence images into brightfield-equivalent stains, eliminating chemical staining and accelerating tissue analysis. Validated across organs and stain types by board-certified pathologists.

Foundational View

No publications match this filter.

Frequently Asked Questions

What is Virtual Staining?

Virtual staining is a computational method that generates stain-equivalent images from digitized tissue scans.

Instead of applying chemical dyes, tissue is scanned using autofluorescence or brightfield imaging, and a trained AI model produces a virtual representation of stains such as H&E or IHC.

The original tissue is not chemically altered, allowing multiple stain representations from a single section.

Learn more: What Is Virtual Staining

Does Virtual Staining replace pathologists?

No.

Virtual staining is adjunctive in nature and generates images that are visually comparable to chemical stains. It does not interpret findings, assign diagnoses, or make clinical decisions.

Pathologists remain responsible for reviewing images and determining diagnostic conclusions. The system is designed to support visualization and workflow flexibility, not to replace medical expertise.

Is Virtual Staining approved for diagnostic use?

Pictor Virtual Staining is currently offered for research-use only (RUO). It is not cleared or approved for clinical diagnostic use.

It should not be used as a standalone basis for medical diagnosis.

Regulatory status may evolve pending appropriate validation and regulatory review.

How is the AI system governed?

Governance includes structured performance evaluation, expert review, and defined deployment controls.

Model performance is evaluated using quantitative image metrics and blinded pathologist review. Diagnostic concordance studies are conducted for evaluation purposes only.

Data processing and storage depend on the selected deployment model (On-Prem or Cloud) and are governed by service agreements.

Learn more: How Safe AI Works in Pathology

How are pathologists involved?

Pathologists are involved in:

  • Dataset development
  • Blinded evaluation studies
  • Image quality assessment
  • Concordance review

Human interpretation serves as the reference standard during validation. AI outputs are reviewed by qualified pathologists and are not accepted autonomously.

How does Virtual Staining work?

The process involves three stages:

  1. Capture of unstained tissue using autofluorescence or brightfield imaging
  2. AI-based registration and mapping using paired training data
  3. Generation of stain-equivalent images through learned transformations

The system relies on supervised deep learning trained on co-registered images from the same tissue section.

Learn more: What Is Virtual Staining

Can multiple stains be generated from one tissue sample?

Yes.

Because the tissue is not chemically altered during virtual staining, multiple computational stain representations can be generated from a single section.

This may be beneficial when tissue samples are limited or when multiple analytical approaches are required.

How is Virtual Staining evaluated?

Performance evaluation combines quantitative technical assessment with expert clinical review.

During development, the model is evaluated using objective image-based measures such as PSNR, SSIM, and feature-level quantitative analyses. These metrics facilitate assessment of image quality, structural integrity, and color accuracy compared to reference stains.

Additionally, pathologists review to verify that the virtually stained images meet standards for visual quality and diagnostic interpretability.

Additional details are available on the Safe AI page.

Where does the system run?

Pictor Virtual Staining supports two deployment models:

  • On-Premises: Processing occurs within the customer’s internal infrastructure.
  • Cloud: Processing occurs in a managed cloud environment.

Deployment configuration determines where data is processed and stored.

See: Deployment Options

What hardware and software is required?

Hardware requirements depend on deployment model:

On-Prem

  • GPU-enabled server
  • Internal IT management
  • Network integration with scanners and storage systems

On Cloud

  • Secure internet connection
  • Image upload or API integration
  • No local GPU required

Technical specifications are provided during onboarding.