
Lung PD-L1 AI
Automated PD-L1 IHC scoring for NSCLC whole slide images, standardizing Tumor Proportion Score assessment across SP263 and 22C3 clones.
Overview
Lung PD-L1 AI, developed by Indica Labs, is an automated, AI-based decision-support tool designed to standardize the scoring of PD-L1 immunohistochemistry (IHC) in non-small cell lung cancer (NSCLC). Operating on whole slide images (WSI), the algorithm produces results in accordance with established clinical scoring guidelines, helping pathologists and researchers achieve consistent, reproducible PD-L1 evaluation. Lung PD-L1 AI is intended for research use only and is not cleared for clinical diagnostic use.
The tool is seamlessly integrated into the HALO AP® diagnostic digital pathology platform from Indica Labs, enabling a fully connected anatomic pathology workflow. It accepts inputs from lung resections and core biopsies, and supports two widely used companion diagnostic clones — SP263 and 22C3 — validated on 3D Histech P1000 and Leica GT450 scanners respectively.
Key Outputs and Scoring Capabilities
- Generates a Tumor Proportion Score (TPS) as the primary output for PD-L1 IHC evaluation in NSCLC
- Reports a comprehensive set of results including total cell count, number of tumor cells, and number of PD-L1 positive and negative tumor cells
- Provides built-in, validated AI-based exclusion of artifact and benign epithelial regions to ensure accurate and consistent analysis
- Includes pathologist-verifiable markups highlighting excluded regions for transparency and quality assurance
Workflow and Efficiency Benefits
- The algorithm can be run on slides before they are released for pathologist review, enabling faster and more informed decision-making
- Assists pathologists and researchers in conducting more efficient PD-L1 expression evaluations
- Standardizes PD-L1 evaluation to facilitate comparison across individuals, laboratories, and institutions, enhancing data reliability and supporting collaborative research
- Complements pathologist expertise with an easy-to-read visual mask that highlights tumor areas and positive and negative cells using colorimetric feedback
- Delivers cell-level information to inform the overall PD-L1 IHC evaluation process
Supported File Formats
- Non-proprietary formats: JPG, TIF, OME.TIFF, DICOM (DCM)
- Leica: SVS, AFI, SCN, LIF
- Hamamatsu: NDPI, NDPIS
- Philips: iSyntax, i2Syntax
- 3DHistech: MRXS
- Nikon: ND2
- Akoya: QPTIFF, component TIFF
- Olympus / Evident: VSI
- Zeiss: CZI
- Ventana: BIF
- KFBIO: KFB, KFBF
Supported Clones and Validation
- SP263 clone validation performed using a 3D Histech P1000 scanner
- 22C3 clone validation performed using a Leica GT450 scanner
Lung PD-L1 AI is deployed and fully integrated into HALO AP®, which is CE-IVDR marked for in-vitro diagnostic use in Europe, the UK, and Switzerland. HALO AP® also provides built-in compliance with FDA 21 CFR Part 11, HIPAA, and GDPR. In the USA, both Lung PD-L1 AI and HALO AP® are for research use only and are not FDA cleared for clinical diagnostic use.
