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.

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.

How are pathologists involved?

Pathologists are involved in: Dataset development, Blinded evaluation studies, Image quality assessment, and 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: Capture of unstained tissue using autofluorescence or brightfield imaging, AI-based registration and mapping using paired training data, and 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.

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.

Where does the system run?

Pictor Virtual Staining supports two deployment models: On-Premises where processing occurs within the customer's internal infrastructure, and Cloud where processing occurs in a managed cloud environment. Deployment configuration determines where data is processed and stored.

What hardware and software is required?

Hardware requirements depend on deployment model. On-Prem requires GPU-enabled server, Internal IT management, and Network integration with scanners and storage systems. Cloud requires Secure internet connection, Image upload or API integration, and No local GPU required.

Data & Evidence | Pictor Labs

Real-World Applications of Virtual Staining

Pictor Labs works with leading biopharma companies, CROs, and academic medical centers to integrate virtual staining into real-world workflows. These deployments focus on solving practical constraints, tissue limitations, workflow delays, and variability, without changing how experts work.

Biopharma - Calibration + Tissue

Maximizing the value of every tissue sample across drug development programs

Across drug development programs, tissue is a limited and valuable resource. Every additional stain, whether H&E, a special stain, or an IHC marker, typically requires another section cut from a finite tissue block. At the same time, stain appearance can vary across sites, batches, and studies, making consistent interpretation more challenging.

Pictor Labs' virtual staining, calibrated to a laboratory's own staining standards, enables generating additional stains from a single scanned slide. This approach enables teams to preserve scarce tissue for downstream molecular and spatial assays while maintaining a consistent stain appearance across programs, sites, and study timelines.

Impact

Preserves tissue for downstream molecular and spatial assays
Reduces the need for additional sectioning, re-staining, and chemical processing
Supports a consistent visual staining standard across studies, sites, and programs

CRO - Workflow + Speed

Reducing turnaround time across multi-site studies without changing existing workflows

A global CRO faced stain turnaround delays, slide logistics challenges, and workflow bottlenecks that were impacting project timelines, particularly across multi-site clinical trials.

By integrating virtual staining into the existing workflow, the organization removed dependency on chemical processing steps and reduced the need to ship slides between sites for staining or review. Digitally generated stains could be accessed immediately and reanalyzed or re-stained on demand, while maintaining established lab operations.

Impact

Accelerates access to stain outputs across sites
Reduces workflow bottlenecks and shipping dependencies
Enables on-demand reanalysis and virtual re-staining
Maintains existing processes and lab workflows

Veterinary Pathology Labs - Insight Expansion

Expanding analytical insight from limited tissue samples

A veterinary pathology laboratory sought to maximize the information available from limited biopsy material while preserving tissue for future molecular testing and research applications.

In traditional workflows, each additional stain consumes another tissue section, reducing the tissue available for downstream analysis. Pictor Labs' virtual staining can generate multiple stain views from a single scanned slide, enabling broader pathological evaluation while helping preserve tissue for future testing needs.

Impact

Enables broader pathological evaluation from a single scanned slide
Supports more consistent stain appearance across global laboratory networks by reducing variability between sites, protocols, and batches
Expands access to stain types that may not be readily available in all regions

Scientific Publications

Realtime, multiplexed rendering of lymphoma diagnostic panels from unstained tissue sections using virtual staining

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

Label-Free Virtual HER2 Immunohistochemical Staining of Breast Tissue using Deep Learning

Real-World Applications of Virtual Staining

Maximizing the value of every tissue sample across drug development programs

Reducing turnaround time across multi-site studies without changing existing workflows

Expanding analytical insight from limited tissue samples

Virtual Staining 101

What Is Virtual Staining?

Virtual Vs. Chemical Staining

How Safe AI Works in Pathology

Frequently Asked Questions