You are here

  • Home
  • Online First
  • Assessment of AI-based computational H&E staining versus chemical H&E staining for primary diagnosis in lymphomas: a brief interim report

Article Text

Article menu
Download PDFPDF
Short report
Assessment of AI-based computational H&E staining versus chemical H&E staining for primary diagnosis in lymphomas: a brief interim report
  1. Rima Koka1,
  2. Laura M Wake2,
  3. Nam K Ku3,
  4. Kathryn Rice1,
  5. Autumn LaRocque1,
  6. Elba G Vidal4,
  7. Serge Alexanian5,
  8. Raymond Kozikowski5,
  9. Yair Rivenson5,
  10. Michael Edward Kallen1
  1. 1Department of Pathology, University of Maryland School of Medicine, Baltimore, Maryland, USA
  2. 2Johns Hopkins Hospital, Baltimore, Maryland, USA
  3. 3Department of Pathology and Laboratory Medicine, University of California Los Angeles, Los Angeles, California, USA
  4. 4University of Maryland Medical Center, Baltimore, Maryland, USA
  5. 5PictorLabs Inc, Los Angeles, California, USA
  1. Correspondence to Dr Michael Edward Kallen; mkallen{at}som.umaryland.edu

Abstract

Microscopic review of tissue sections is of foundational importance in pathology, yet the traditional chemistry-based histology laboratory methods are labour intensive, tissue destructive, poorly scalable to the evolving needs of precision medicine and cause delays in patient diagnosis and treatment. Recent AI-based techniques offer promise in upending histology workflow; one such method developed by PictorLabs can generate near-instantaneous diagnostic images via a machine learning algorithm. Here, we demonstrate the utility of virtual staining in a blinded, wash-out controlled study of 16 cases of lymph node excisional biopsies, including a spectrum of diagnoses from reactive to lymphoma and compare the diagnostic performance of virtual and chemical H&Es across a range of stain quality, image quality, morphometric assessment and diagnostic interpretation parameters as well as proposed follow-up immunostains. Our results show non-inferior performance of virtual H&E stains across all parameters, including an improved stain quality pass rate (92% vs 79% for virtual vs chemical stains, respectively) and an equivalent rate of binary diagnostic concordance (90% vs 92%). More detailed adjudicated reviews of differential diagnoses and proposed IHC panels showed no major discordances. Virtual H&Es appear fit for purpose and non-inferior to chemical H&Es in diagnostic assessment of clinical lymph node samples, in a limited pilot study.

  • Artificial Intelligence
  • Machine Learning
  • LYMPHOMA

https://doi.org/10.1136/jcp-2024-209643

Statistics from Altmetric.com

    Request Permissions

    If you wish to reuse any or all of this article please use the link below which will take you to the Copyright Clearance Center’s RightsLink service. You will be able to get a quick price and instant permission to reuse the content in many different ways.

    View Full Text

    Footnotes

    • Handling editor Vikram Deshpande.

    • Contributors RK, LMW and NKK participated in study performance and slide review and edited the paper. KR and AL assisted in material preparation. EGV created study material and coordinated material preparation with PictorLabs. SA coordinated study design, served as a study adjudicator and edited the manuscript. RK supplied information technology support, performed data interpretation and performed statistical analysis. YR supervised virtual slide creation. MEK was an adjudicator, wrote the manuscript and is the principal investigator.

    • Funding The authors have not declared a specific grant for this research from any funding agency in the public, commercial or not-for-profit sectors.

    • Competing interests SA, RK and YR are employees of PictorLabs. The authors have no other conflicts of interest or disclosures to report.

    • Provenance and peer review Not commissioned; internally peer reviewed.