Nature Communications (Dec 2023)

Deep learning-based phenotyping reclassifies combined hepatocellular-cholangiocarcinoma

  • Julien Calderaro,
  • Narmin Ghaffari Laleh,
  • Qinghe Zeng,
  • Pascale Maille,
  • Loetitia Favre,
  • Anaïs Pujals,
  • Christophe Klein,
  • Céline Bazille,
  • Lara R. Heij,
  • Arnaud Uguen,
  • Tom Luedde,
  • Luca Di Tommaso,
  • Aurélie Beaufrère,
  • Augustin Chatain,
  • Delphine Gastineau,
  • Cong Trung Nguyen,
  • Hiep Nguyen-Canh,
  • Khuyen Nguyen Thi,
  • Viviane Gnemmi,
  • Rondell P. Graham,
  • Frédéric Charlotte,
  • Dominique Wendum,
  • Mukul Vij,
  • Daniela S. Allende,
  • Federico Aucejo,
  • Alba Diaz,
  • Benjamin Rivière,
  • Astrid Herrero,
  • Katja Evert,
  • Diego Francesco Calvisi,
  • Jérémy Augustin,
  • Wei Qiang Leow,
  • Howard Ho Wai Leung,
  • Emmanuel Boleslawski,
  • Mohamed Rela,
  • Arnaud François,
  • Anthony Wing-Hung Cha,
  • Alejandro Forner,
  • Maria Reig,
  • Manon Allaire,
  • Olivier Scatton,
  • Denis Chatelain,
  • Camille Boulagnon-Rombi,
  • Nathalie Sturm,
  • Benjamin Menahem,
  • Eric Frouin,
  • David Tougeron,
  • Christophe Tournigand,
  • Emmanuelle Kempf,
  • Haeryoung Kim,
  • Massih Ningarhari,
  • Sophie Michalak-Provost,
  • Purva Gopal,
  • Raffaele Brustia,
  • Eric Vibert,
  • Kornelius Schulze,
  • Darius F. Rüther,
  • Sören A. Weidemann,
  • Rami Rhaiem,
  • Jean-Michel Pawlotsky,
  • Xuchen Zhang,
  • Alain Luciani,
  • Sébastien Mulé,
  • Alexis Laurent,
  • Giuliana Amaddeo,
  • Hélène Regnault,
  • Eleonora De Martin,
  • Christine Sempoux,
  • Pooja Navale,
  • Maria Westerhoff,
  • Regina Cheuk-Lam Lo,
  • Jan Bednarsch,
  • Annette Gouw,
  • Catherine Guettier,
  • Marie Lequoy,
  • Kenichi Harada,
  • Pimsiri Sripongpun,
  • Poowadon Wetwittayaklang,
  • Nicolas Loménie,
  • Jarukit Tantipisit,
  • Apichat Kaewdech,
  • Jeanne Shen,
  • Valérie Paradis,
  • Stefano Caruso,
  • Jakob Nikolas Kather

DOI
https://doi.org/10.1038/s41467-023-43749-3
Journal volume & issue
Vol. 14, no. 1
pp. 1 – 10

Abstract

Read online

Abstract Primary liver cancer arises either from hepatocytic or biliary lineage cells, giving rise to hepatocellular carcinoma (HCC) or intrahepatic cholangiocarcinoma (ICCA). Combined hepatocellular- cholangiocarcinomas (cHCC-CCA) exhibit equivocal or mixed features of both, causing diagnostic uncertainty and difficulty in determining proper management. Here, we perform a comprehensive deep learning-based phenotyping of multiple cohorts of patients. We show that deep learning can reproduce the diagnosis of HCC vs. CCA with a high performance. We analyze a series of 405 cHCC-CCA patients and demonstrate that the model can reclassify the tumors as HCC or ICCA, and that the predictions are consistent with clinical outcomes, genetic alterations and in situ spatial gene expression profiling. This type of approach could improve treatment decisions and ultimately clinical outcome for patients with rare and biphenotypic cancers such as cHCC-CCA.