Augmented reality microscopy to bridge trust between AI and pathologists.

Journal: NPJ precision oncology
Published Date:

Abstract

Diagnostic certainty is the cornerstone of modern medicine and critical for maximal treatment benefit. When evaluating biomarker expression by immunohistochemistry (IHC), however, pathologists are hindered by complex scoring methodologies, unique positivity cut-offs and subjective staining interpretation. Artificial intelligence (AI) can potentially eliminate diagnostic uncertainty, especially when AI "trustworthiness" is proven by expert pathologists in the context of real-world clinical practice. Building on an IHC foundation model, we employed pathologists-in-the-loop finetuning to produce a programmed cell death ligand 1 (PD-L1) CPS AI Model. We devised a multi-head augmented reality microscope (ARM) system overlayed with the PD-L1 CPS AI Model to assess interobserver variability and gauge the pathologists' trust in AI model outputs. Using difficult to interpret regions on gastroesophageal biopsies, we show that AI-assistance improved case agreement between any 2 pathologists by 14% (agreement on 77% vs 91%) and among 11 pathologists by 26% (agreement on 43% vs 69%). At a clinical cutoff of PD-L1 CPS ≥ 5, the number of cases diagnosed as positive by all 11 pathologists increased by 31%. Our findings underscore the benefits of fully engaging pathologists as active participants in the development and deployment of IHC AI models and frame the roadmap for trustworthy AI as a bridge to increased adoption in routine pathology practice.

Authors

  • Sunil Badve
    Emory University School of Medicine, Atlanta, GA, USA. sbadve@emory.edu.
  • George L Kumar
    Bristol Myers Squibb, Princeton, NJ, USA. george.kumar@astrazeneca.com.
  • Tobias Lang
    Mindpeak, Hamburg, Germany. tobias.lang@mindpeak.ai.
  • Eli Peigin
    Augmentiqs, D.N, Misgav, Israel.
  • James Pratt
    Bristol Myers Squibb, Princeton, NJ, USA.
  • Robert Anders
    Johns Hopkins University Baltimore, Baltimore, MD, USA.
  • Deyali Chatterjee
    MD Anderson Cancer Center, Houston, TX, USA.
  • Raul S Gonzalez
    Emory University School of Medicine, Atlanta, GA, USA.
  • Rondell P Graham
    Mayo Clinic, Rochester, MN, USA.
  • Alyssa M Krasinskas
    Emory University School of Medicine, Atlanta, GA, USA.
  • Xiuli Liu
    Washington University School of Medicine, St Louis, MO, USA.
  • Alexander Quaas
    Institute of Pathology, University Hospital Cologne, Cologne, Germany.
  • Romil Saxena
    Emory University School of Medicine, Atlanta, GA, USA.
  • Namrata Setia
    University of Chicago, Chicago, IL, USA.
  • Laura Tang
    Memorial Sloan Kettering Cancer Center, New York, NY, USA.
  • Hanlin L Wang
    UCLA David Geffen School of Medicine, Los Angeles, CA, USA.
  • Josef Rüschoff
    Discovery Life Sciences Biomarker Services GmbH, Kassel, Germany.
  • Hans-Ulrich Schildhaus
    Discovery Life Sciences Biomarker Services GmbH, Kassel, Germany.
  • Khalid Daifalla
    Mindpeak, Hamburg, Germany.
  • Marc Päpper
    Mindpeak, Hamburg, Germany.
  • Patrick Frey
    Mindpeak, Hamburg, Germany.
  • Felix Faber
    Mindpeak, Hamburg, Germany.
  • Maria Karasarides
    Bristol Myers Squibb, Princeton, NJ, USA. maria@delphina.io.

Keywords

No keywords available for this article.