Resources
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.
Scientific publications
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.
Abstract A106: Virtual Stromal Staining of Routine Histology as an Exploratory, Stroma-Aware Prognostic Readout in Pancreatic Cancer
At the AACR Conference on Pancreatic Cancer 2026, Pictor Labs shows that a virtual stromal stain generated from routine H&E adds prognostic information beyond clinical staging in pancreatic ductal adenocarcinoma.
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.
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.
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.
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.
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.
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.
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.
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.
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.
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).
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.
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.
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.
No publications match this filter.
FAQ
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
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.
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.
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
Pathologists are involved in:
Human interpretation serves as the reference standard during validation. AI outputs are reviewed by qualified pathologists and are not accepted autonomously.
The process involves three stages:
The system relies on supervised deep learning trained on co-registered images from the same tissue section.
Learn more: What Is Virtual Staining
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.
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.
Pictor Virtual Staining supports two deployment models:
Deployment configuration determines where data is processed and stored.
See: Deployment Options
Hardware requirements depend on deployment model:
On-Prem
On Cloud
Technical specifications are provided during onboarding.
For Research Use Only. Not for use in diagnostic procedures.