Prediction of heart transplant rejection from routine pathology slides with self-supervised deep learning

  • Tobias Paul Seraphin (Shared first author)
  • Mark Luedde (Shared first author)
  • Christoph Roderburg (Shared first author)
  • Marko van Treeck
  • Pascal Scheider
  • Roman D Buelow
  • Peter Boor
  • Sven H Loosen
  • Zdenek Provaznik
  • Daniel Mendelsohn
  • Filip Berisha
  • Christina Magnussen
  • Dirk Westermann
  • Tom Luedde
  • Christoph Brochhausen (Shared last author)
  • Samuel Sossalla (Shared last author)
  • Jakob Nikolas Kather (Shared last author)

Related Research units

Abstract

AIMS: One of the most important complications of heart transplantation is organ rejection, which is diagnosed on endomyocardial biopsies by pathologists. Computer-based systems could assist in the diagnostic process and potentially improve reproducibility. Here, we evaluated the feasibility of using deep learning in predicting the degree of cellular rejection from pathology slides as defined by the International Society for Heart and Lung Transplantation (ISHLT) grading system.

METHODS AND RESULTS: We collected 1079 histopathology slides from 325 patients from three transplant centres in Germany. We trained an attention-based deep neural network to predict rejection in the primary cohort and evaluated its performance using cross-validation and by deploying it to three cohorts. For binary prediction (rejection yes/no), the mean area under the receiver operating curve (AUROC) was 0.849 in the cross-validated experiment and 0.734, 0.729, and 0.716 in external validation cohorts. For a prediction of the ISHLT grade (0R, 1R, 2/3R), AUROCs were 0.835, 0.633, and 0.905 in the cross-validated experiment and 0.764, 0.597, and 0.913; 0.631, 0.633, and 0.682; and 0.722, 0.601, and 0.805 in the validation cohorts, respectively. The predictions of the artificial intelligence model were interpretable by human experts and highlighted plausible morphological patterns.

CONCLUSION: We conclude that artificial intelligence can detect patterns of cellular transplant rejection in routine pathology, even when trained on small cohorts.

Bibliographical data

Original languageEnglish
ISSN2634-3916
DOIs
Publication statusPublished - 05.2023

Comment Deanary

© The Author(s) 2023. Published by Oxford University Press on behalf of the European Society of Cardiology.

PubMed 37265858