Jove
Visualize
Contact Us
JoVE
x logofacebook logolinkedin logoyoutube logo
ABOUT JoVE
OverviewLeadershipBlogJoVE Help Center
AUTHORS
Publishing ProcessEditorial BoardScope & PoliciesPeer ReviewFAQSubmit
LIBRARIANS
TestimonialsSubscriptionsAccessResourcesLibrary Advisory BoardFAQ
RESEARCH
JoVE JournalMethods CollectionsJoVE Encyclopedia of ExperimentsArchive
EDUCATION
JoVE CoreJoVE BusinessJoVE Science EducationJoVE Lab ManualFaculty Resource CenterFaculty Site
Terms & Conditions of Use
Privacy Policy
Policies

Related Concept Videos

You might also read

Related Articles

Articles linked to this work by shared authors, journal, and citation graph.

Sort by
Same author

Fusion of Clinical and Deep Learning Features for Predicting Pembrolizumab Monotherapy Response in Advanced Non-Small Cell Lung Cancer.

Journal of clinical medicine·2026
Same author

Spectral Unmixing to Reduce Refraction Effects in Feulgen-Stained Slides.

Sensors (Basel, Switzerland)·2026
Same author

Machine Learning and Computed Tomography Radiomics to Predict Disease Progression to Upfront Pembrolizumab Monotherapy in Advanced Non-Small-Cell Lung Cancer: A Pilot Study.

Cancers·2025
Same author

Multimodal Optical Imaging of Ex Vivo Fallopian Tubes to Distinguish Early and Occult Tubo-Ovarian Cancers.

Cancers·2024
Same author

Imaging Biomarkers of Oral Dysplasia and Carcinoma Measured with In Vivo Endoscopic Optical Coherence Tomography.

Cancers·2024
Same author

Three-Dimension Epithelial Segmentation in Optical Coherence Tomography of the Oral Cavity Using Deep Learning.

Cancers·2024
Same journal

Multiple subcutaneous nodules as the primary presentation of angioimmunoblastic T-cell lymphoma: a case report and literature review.

Pathology oncology research : POR·2026
Same journal

<i>Connexin 43</i> enhances liver metastatic ability of GIST cells <i>in vivo</i>.

Pathology oncology research : POR·2026
Same journal

Proof-of-principle 4-marker spatial profiling reveals distinct, location-independent immune clusters in biliary tract cancers.

Pathology oncology research : POR·2026
Same journal

Genotyping of suspected partial hydatidiform moles - our experiences and future directions.

Pathology oncology research : POR·2026
Same journal

Prognostic impact of p53 and HER2 immunohistochemistry profiles in colorectal carcinoma.

Pathology oncology research : POR·2026
Same journal

Delayed diagnostic imaging but stable treatment initiation for kidney cancer during the COVID-19 pandemic: a Hungarian cohort study.

Pathology oncology research : POR·2026
See all related articles

Related Experiment Video

Updated: Oct 29, 2025

Semi-automatic PD-L1 Characterization and Enumeration of Circulating Tumor Cells from Non-small Cell Lung Cancer Patients by Immunofluorescence
10:29

Semi-automatic PD-L1 Characterization and Enumeration of Circulating Tumor Cells from Non-small Cell Lung Cancer Patients by Immunofluorescence

Published on: August 14, 2019

10.8K

Automated PD-L1 Scoring for Non-Small Cell Lung Carcinoma Using Open-Source Software.

Julia R Naso1, Tetiana Povshedna2, Gang Wang2

  • 1Department of Pathology and Laboratory Medicine, University of British Columbia, Vancouver, BC, Canada.

Pathology Oncology Research : POR
|July 14, 2021
PubMed
Summary
This summary is machine-generated.

Automated scoring of PD-L1 expression in non-small cell lung cancer (NSCLC) using QuPath software shows high concordance with manual pathologist scoring. This free, open-source tool offers a consistent alternative for predicting immunotherapy response.

Keywords:
PD-L1biomarkerdigital pathologynon-small cell lung cancerpathology

More Related Videos

Using 22C3 Anti-PD-L1 Antibody Concentrate on Biopsy and Cytology Samples from Non-small Cell Lung Cancer Patients
07:43

Using 22C3 Anti-PD-L1 Antibody Concentrate on Biopsy and Cytology Samples from Non-small Cell Lung Cancer Patients

Published on: September 25, 2018

10.7K
Digital Analysis of Immunostaining of ZW10 Interacting Protein in Human Lung Tissues
07:40

Digital Analysis of Immunostaining of ZW10 Interacting Protein in Human Lung Tissues

Published on: May 1, 2019

5.5K

Related Experiment Videos

Last Updated: Oct 29, 2025

Semi-automatic PD-L1 Characterization and Enumeration of Circulating Tumor Cells from Non-small Cell Lung Cancer Patients by Immunofluorescence
10:29

Semi-automatic PD-L1 Characterization and Enumeration of Circulating Tumor Cells from Non-small Cell Lung Cancer Patients by Immunofluorescence

Published on: August 14, 2019

10.8K
Using 22C3 Anti-PD-L1 Antibody Concentrate on Biopsy and Cytology Samples from Non-small Cell Lung Cancer Patients
07:43

Using 22C3 Anti-PD-L1 Antibody Concentrate on Biopsy and Cytology Samples from Non-small Cell Lung Cancer Patients

Published on: September 25, 2018

10.7K
Digital Analysis of Immunostaining of ZW10 Interacting Protein in Human Lung Tissues
07:40

Digital Analysis of Immunostaining of ZW10 Interacting Protein in Human Lung Tissues

Published on: May 1, 2019

5.5K

Area of Science:

  • Oncology
  • Computational Pathology
  • Immunotherapy

Background:

  • Programmed death-ligand 1 (PD-L1) expression in non-small cell lung cancer (NSCLC) predicts immunotherapy response.
  • Manual scoring of PD-L1 immunohistochemistry (IHC) exhibits significant interobserver variability.
  • Automated scoring methods offer potential for enhanced consistency and efficiency in PD-L1 assessment.

Purpose of the Study:

  • To evaluate the technical concordance between automated PD-L1 scoring using QuPath software and manual scoring by pathologists in NSCLC.
  • To compare the accuracy of automated PD-L1 scoring against a gold standard of averaged manual pathologist scores.
  • To assess the sensitivity and specificity of automated PD-L1 scoring at different expression thresholds.

Main Methods:

  • A PD-L1 scoring classifier was developed using 30 NSCLC image patches.
  • A test set of 207 image patches from 69 NSCLC cases was used for comparison.
  • Automated scores were compared against the average manual scores of three pathologists.

Main Results:

  • Excellent correlation was observed between automated and average manual PD-L1 scores (concordance correlation coefficient = 0.925).
  • Automated scoring resulted in a higher proportion of 1-49% scores compared to manual scoring (p=0.012).
  • Concordance with the gold standard at 1% and 50% thresholds was comparable to individual pathologists, with high sensitivity (95%) and lower specificity (84%) at 1%, and excellent specificity (100%) and lower sensitivity (71%) at 50%.

Conclusions:

  • The automated PD-L1 scoring system using QuPath demonstrates accuracy comparable to individual pathologists in NSCLC.
  • The provided protocol and discussion of limitations can aid clinical integration of automated scoring.
  • This open-source approach may improve consistency and efficiency in PD-L1 assessment for immunotherapy selection.