Oops, you're using an old version of your browser so some of the features on this page may not be displaying properly.

MINIMAL Requirements: Google Chrome 24+Mozilla Firefox 20+Internet Explorer 11Opera 15–18Apple Safari 7SeaMonkey 2.15-2.23

Proffered Paper session: Sarcoma

1484O - Deep learning predicts patients’ outcome and mutations from H&E slides in gastrointestinal stromal tumor (GIST)


10 Sep 2022


Proffered Paper session: Sarcoma


Pathology/Molecular Biology;  Cancer Intelligence (eHealth, Telehealth Technology, BIG Data)

Tumour Site



raul perret


Annals of Oncology (2022) 33 (suppl_7): S681-S700. 10.1016/annonc/annonc1073


A. Italiano1, Y. FU2, M. karanian3, R. perret4, A. camara2, F. Le Loarer4, M. Jean-Denis3, I. hostein4, A. michot4, F. Ducimetiere3, A. Giraud5, J. courreges6, K. Courtet7, Y. laizet7, J.O. du terrail8, B. Schmauch9, C. Maussion8, J. Blay10, J.M. coindre4

Author affiliations

  • 1 Early Phase Trials Unit, Institute Bergonié, 33000 - Bordeaux/FR
  • 2 Paris, OWKIN France, 75010 - Paris/FR
  • 3 Cancer Research Center Of Lyon, Centre Léon Bérard, 69008 - Lyon/FR
  • 4 Department Of Biopathology, Institute Bergonié - Centre Régional de Lutte Contre le Cancer (CLCC), 33000 - Bordeaux/FR
  • 5 Clinical Research And Clinical Epidemiology Unit, Institut Bergonié, Bordeaux/FR
  • 6 Clinical Research And Clinical Epidemiology Unit, Institute Bergonié - Centre Régional de Lutte Contre le Cancer (CLCC), 33000 - Bordeaux/FR
  • 7 Clinical Research And Clinical Epidemiology Unit, Institut Bergonie, Bordeaux/FR
  • 8 Rd, OWKIN France, 75010 - Paris/FR
  • 9 Data And Clinical Solutions, OWKIN France, 75010 - Paris/FR
  • 10 Medicine Department, Centre Léon Bérard, 69008 - Lyon/FR


Login to access the resources on OncologyPRO.

Abstract 1484O


Risk assessment according to the AFIP/Miettinen classification and mutational profiling are major tools for patient management. However, the AFIP/Miettinen classification depends heavily on mitotic counts, which is laborious and sometimes inconsistent between pathologists. It has also been shown to be imperfect in stratifying patients. Molecular testing is costly and time consuming, therefore not systematically performed in all countries. New methods to improve risk and molecular predictions are hence crucial to improve the tailoring of adjuvant therapy.


We have built deep learning (DL) models on digitized H&E-stained whole slide images (WSI) to predict patients’ outcome and mutations. Models were trained with a cohort of 1233 GIST and validated on an independent cohort of 286 GIST.


DL models outperformed the Miettinen classification for relapse-free-survival prediction in localized GIST without adjuvant Imatinib (C-index=0.83 in testing and 0.72 for independent validation). DL splitted Miettinen intermediate risk GIST into high/low risk groups(p value=2.1e-03). DL models achieved an area under the receiver operating characteristic curve (AUC) of 0.81, 0.91 and 0.71 for predicting mutations in KIT, PDGFRA and wild type respectively in testing and 0.84, 0.93 and 0.56 in independent validation. Notably, PDGFRA exon18 D842V mutation which is resistant to Imatinib, was predicted with an AUC of 0.87 and 0.90 in testing and independent validation, respectively. Additionally, novel histological criteria predictive of patients’ outcome and mutations were identified by reviewing the tiles selected by the models.


Our results strongly suggest that implementing DL with digitized WSI may represent a reproducible way to improve tailoring therapy and precision medicine for patients with GIST.

Clinical trial identification

Editorial acknowledgement

Legal entity responsible for the study

Institut Bergonié. Bordeaux, France.


Has not received any funding.


All authors have declared no conflicts of interest.

This site uses cookies. Some of these cookies are essential, while others help us improve your experience by providing insights into how the site is being used.

For more detailed information on the cookies we use, please check our Privacy Policy.

Customise settings
  • Necessary cookies enable core functionality. The website cannot function properly without these cookies, and you can only disable them by changing your browser preferences.