Endometrial Pipelle biopsy computer-aided diagnosis (ENDO-AID): a feasibility study

Sanne Vermorgen, Thijs Gelton, Peter Bult, Heidi V N Kusters-Vandevelde, Jitka Hausnerová, Koen Van de Vijver, Ben Davidson, Ingunn Marie Stefansson, Loes F S Kooreman, Adelina Qerimi, Jutta Huvila, Blake Gilks, Maryam Shahi, Saskia Zomer, Carla Bartosch, Johanna Ma Pijnenborg, Johan Bulten, Francesco Ciompi, Michiel Simons*

*Corresponding author for this work

Research output: Contribution to journalArticleAcademicpeer-review

Abstract

Endometrial biopsies are important in the diagnostic work-up of women who present with abnormal uterine bleeding or women with hereditary risk of endometrial cancer. In general, about 10% of all endometrial biopsies demonstrate endometrial (pre)malignancy that requires specific treatment. As the diagnostic evaluation of mostly benign cases results in a substantial workload for pathologists, artificial intelligence (AI) assisted pre-selection of biopsies could optimize the workflow. This study aimed to assess the feasibility of AI-assisted diagnosis for endometrial biopsies (ENDO-AID), trained on daily-practice whole slide images instead of highly selected images. Endometrial biopsies were classified into six clinically relevant categories defined as: non-representative, normal, non-neoplastic, hyperplasia without atypia, hyperplasia with atypia and malignant. The agreement among 15 pathologists, within these classifications, was evaluated in 91 endometrial biopsies. Next, an algorithm (trained on a total of 2,819 endometrial biopsies) rated the same 91 cases and we compared its performance using the pathologist's classification as reference standard. The interrater reliability among pathologists was moderate with a mean Cohen's kappa of 0.51, whereas for a binary classification into benign versus (pre)malignant, the agreement was substantial with a mean Cohen's kappa of 0.66. The AI algorithm performed slightly worse for the six categories with a moderate Cohen's kappa of 0.43, but was comparable for the binary classification with a substantial Cohen's kappa of 0.65. AI-assisted diagnosis of endometrial biopsies was demonstrated to be feasible in discriminating between benign and (pre)malignant endometrial tissue, even when trained on unselected cases. Endometrial premalignancies remain challenging for both pathologists and AI algorithms. Future steps to improve reliability of the diagnosis are needed to achieve a more refined AI-assisted diagnostic solution for endometrial biopsies that covers both premalignant and malignant diagnoses.
Original languageEnglish
Article number100417
Number of pages9
JournalModern Pathology
Volume37
Issue number2
DOIs
Publication statusPublished - Feb 2024

Keywords

  • classification
  • digital pathology
  • endometrial cancer
  • inter-observer variability

Fingerprint

Dive into the research topics of 'Endometrial Pipelle biopsy computer-aided diagnosis (ENDO-AID): a feasibility study'. Together they form a unique fingerprint.

Cite this