EUVIMEDEUVIMED entdecken
VergleichsstudieOpen Access · CC BY 4.0

Comparative performance of PD ‐ L1 scoring by pathologists and AI algorithms

Markus Plass iD, Gheorghe-Emilian Olteanu iD, Sanja Dacic iD, Izidor Kern iD, Martin Zacharias iD, Helmut Popper iD, Junya Fukuoka iD, Sosuke Ishijima iD, Michaela Kargl iD, Christoph Murauer, Lipika Kalson iD, Luka Brcic iD

Histopathology · 2025-07 · 87 (1) · 90-100

DOI: 10.1111/his.15432 ↗

Kurz gefasst

Vergleichsstudie in der Zeitschrift Histopathology, online erschienen am 17.02.2025. Verfasst von Markus Plass und 11 weiteren Autor:innen. Beteiligte Einrichtung: Diagnostic and Research Institute of Pathology, Medical University of Graz, Graz, Austria. Hauptthemen laut MEDLINE: Carcinoma, Non-Small-Cell Lung, Lung Neoplasms, Algorithms, B7-H1 Antigen. Die Arbeit wurde bisher 19-mal zitiert (Crossref) und nennt 35 Literaturangaben. Der Volltext ist frei zugänglich (Open Access, CC BY 4.0). Gefördert von: Austrian Science Fund, European Commission.

AbstractSchlagwörterBibliografische AngabenZitierenVerwandte Studien

Abstract (Originalsprache)

Aim This study evaluates the comparative effectiveness of pathologists versus artificial intelligence (AI) algorithms in scoring PD‐L1 expression in non‐small cell lung carcinoma (NSCLC). Immune‐checkpoint inhibitors have revolutionized NSCLC treatment, with PD‐L1 expression, measured as the tumour proportion score (TPS), serving as a critical predictive biomarker for therapeutic response. Methods and Results In our analysis, 51 SP263‐stained NSCLC cases were scored by six pathologists using light microscopy and whole‐slide images (WSI), alongside evaluations by two commercially available software tools: uPath software (Roche) and the PD‐L1 Lung Cancer TME application (Visiopharm). The study examined intra‐ and interobserver agreement among pathologists at TPS cutoffs of 1% and 50%, revealing moderate interobserver agreement (Fleiss' kappa 0.558) for TPS

Schlagwörter

MeSH-Schlagwörter (MEDLINE)

Carcinoma, Non-Small-Cell LungLung NeoplasmsAlgorithmsB7-H1 AntigenBiomarkers, TumorArtificial IntelligenceHumansPathologistsObserver VariationImmunohistochemistry

Stichwörter der Autor:innen

AI algorithmsNSCLCPD‐L1 expressionpathologiststumour proportion score (TPS)

Substanzen

B7-H1 AntigenCD274 protein, humanBiomarkers, Tumor

Autor:innen und Institutionen

  • Diagnostic and Research Institute of Pathology, Medical University of Graz, Graz, Austria.
  • Department of Pathology, British Columbia Cancer Agency, Vancouver, BC, Canada.
  • Department of Pathology and Laboratory Medicine, University of British Columbia, Vancouver, BC, Canada.
  • University of Pittsburgh Medical Center, Pittsburgh, PA, USA.
  • Cytology and Pathology Laboratory, University Clinic of Respiratory and Allergic Diseases, Golnik, Slovenia.
  • Department of Pathology Informatics, Nagasaki University Graduate School of Biomedical Sciences, Nagasaki, Japan.

ORCID-Profile: Markus Plass, Gheorghe-Emilian Olteanu, Sanja Dacic, Izidor Kern, Martin Zacharias, Helmut Popper, Junya Fukuoka, Sosuke Ishijima, Michaela Kargl, Lipika Kalson, Luka Brcic

Förderung

  • Austrian Science Fund
  • European Commission

Zitieren

APA

Plass, M., Olteanu, G. E., Dacic, S., Kern, I., Zacharias, M., Popper, H., Fukuoka, J., Ishijima, S., Kargl, M., Murauer, C., Kalson, L., & Brcic, L. (2025). Comparative performance of PD ‐ L1 scoring by pathologists and AI algorithms. Histopathology, 87(1), 90-100. https://doi.org/10.1111/his.15432

Vancouver

Plass M, Olteanu GE, Dacic S, Kern I, Zacharias M, Popper H, et al. Comparative performance of PD ‐ L1 scoring by pathologists and AI algorithms. Histopathology. 2025;87(1):90-100. doi:10.1111/his.15432

BibTeX
@article{Plass2025,
  author = {Plass, Markus and Olteanu, Gheorghe-Emilian and Dacic, Sanja and Kern, Izidor and Zacharias, Martin and Popper, Helmut and Fukuoka, Junya and Ishijima, Sosuke and Kargl, Michaela and Murauer, Christoph and Kalson, Lipika and Brcic, Luka},
  title = {Comparative performance of PD ‐ L1 scoring by pathologists and AI algorithms},
  journal = {Histopathology},
  year = {2025},
  volume = {87},
  number = {1},
  pages = {90--100},
  doi = {10.1111/his.15432}
}
Kostenlos starten →