Article Text

Download PDFPDF

2022-RA-648-ESGO Interpretable deep learning provides clues for prognostic refinement of the molecular endometrial cancer classification
  1. Sarah Fremond1,
  2. Sonali Andani2,
  3. Jurriaan Barkey Wolf1,
  4. Jouke Dijkstra3,
  5. Jan Jobsen4,
  6. Ina Jürgenliemk-Schulz5,
  7. Ludy Lutgens6,
  8. Remi Nout7,
  9. Elzbieta van der Steen-Banasik8,
  10. Stephanie de Boer9,
  11. Melanie Powell10,
  12. Naveena Singh11,
  13. Linda Mileshkin12,
  14. Helen Mackay13,
  15. Alexandra Leary14,
  16. Hans Nijman15,
  17. Carien Creutzberg9,
  18. Nanda Horeweg16,
  19. Viktor Hendrik Koelzer17 and
  20. Tjalling Bosse1
  1. 1Pathology, Leiden University medical center, Leiden, Netherlands
  2. 2Pathology and Molecular Pathology and Computer Science, University Hospital Zurich and ETH Zurich, Zurich, Switzerland
  3. 3Department of Vascular and Molecular Imaging, Leiden University Medical Center, Leiden, Netherlands
  4. 4Department of Radiation Oncology, Medisch Spectrum Twente, Enschede, Netherlands
  5. 5Department of Radiation Oncology, University Medical Center Utrecht, Utrecht, Netherlands
  6. 6Department of Radiation Oncology, Maastricht UMC+, Maastricht, Netherlands
  7. 7Department of Radiation Oncology, Erasmus University Medical Center, Rotterdam, Netherlands
  8. 8Department of Radiation Oncology, Radiotherapiegroep, Arnhem, Netherlands
  9. 9Department of Radiation Oncology, Leiden University Medical Center, Leiden, Netherlands
  10. 10Department of Clinical Oncology, Barts Health NHS Trust, London, UK
  11. 11Department of Pathology, Barts Health NHS Trust, London, UK
  12. 12Department of Medical Oncology, Peter MacCallum Cancer Center, Melbourne, Australia
  13. 13Department of Medical Oncology and Hematology, Odette Cancer Center Sunnybrook Health Sciences Center, Toronto, ON, Canada
  14. 14Department Medical Oncology, Gustave Roussy Institute, Villejuif, France
  15. 15Department of Obstetrics and Gynecology, University Medical Center Groningen, Groningen, Netherlands
  16. 16Radiotherapy, Leiden University medical center, Leiden, Netherlands
  17. 17Pathology and Molecular Pathology, University Hospital Zurich, Zurich, Switzerland


Introduction/Background Endometrial Cancer (EC) are molecularly classified into polymerase-ε mutated (POLEmut), mismatch repair deficient (MMRd), p53 abnormal (p53abn) and no specific molecular profile (NSMP). With the incorporation of the molecular classification in risk-assessment of EC patients, clinical relevance of histopathological features became unclear. Deep Learning (DL) can identify morphology associated with molecular class from whole tumor slide images (WSIs). We developed an interpretable DL model for image-based prediction of the molecular EC classification (im4MEC) to identify morpho-molecular correlates which may refine EC prognostication.

Methodology Digital H&E-WSIs from 2028 molecularly classified EC of the transPORTEC repository were included. im4MEC used state-of-the-art DL models combining self-supervised learning and attention mechanism. Performance was calculated on the independent test set PORTEC-3 (N=393) using area under receiver-operating-characteristic curve (AUROC). Slide sub-regions with highest attention scores given by im4MEC were reviewed to identify morpho-molecular correlates. Human-interpretable morphological features were extracted using predictions from a nuclear classification DL model. Prognostic refinement was explored though morphological and survival analyses using Kaplan-Meier’s methodology.

Results im4MEC achieved a macro-average AUROC of 0.876 on PORTEC-3, with highest of 0.928 among p53abn class. Top-attended sub-regions indicated significant association between dense lymphocyte infiltrates and POLEmut and MMRd EC; low tumor-stroma ratio and NSMP EC; high nuclear atypia and p53abn EC. Image-based molecular classification had a strong prognostic value in PORTEC-3 (p=1.e-04; figure 1A). MMRd cases predicted as POLEmut had excellent prognosis; p53abn cases predicted as MMRd showed MMRd-like inflammatory morphology and slightly better prognosis; few NSMP cases predicted as p53abn showed p53abn-like strong nuclear atypia and worse prognosis (figure 1B,C,D).

Abstract 2022-RA-648-ESGO Figure 1

Conclusion im4MEC shows promising performance for H&E-based molecular classification of high-risk EC patients, correlating with distinct clinical outcome. im4MEC robustly identifies known and novel morpho-molecular correlates which enable prognostic refinement. This work provides novel indicators for an improved risk stratification system integrating molecular and morphological data.

Statistics from

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.