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:10.1038/s41467-023-43749-3

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. GrahamFrédéric 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

Research output: Contribution to journal › Article › peer-review

1 Scopus citations

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.

Original language	English (US)
Article number	8290
Journal	Nature communications
Volume	14
Issue number	1
DOIs	https://doi.org/10.1038/s41467-023-43749-3
State	Published - Dec 2023

ASJC Scopus subject areas

General Chemistry
General Biochemistry, Genetics and Molecular Biology
General Physics and Astronomy

Access to Document

10.1038/s41467-023-43749-3

Cite this

Calderaro, J., Ghaffari Laleh, N., Zeng, Q., Maille, P., Favre, L., Pujals, A., Klein, C., Bazille, C., Heij, L. R., Uguen, A., Luedde, T., Di Tommaso, L., Beaufrère, A., Chatain, A., Gastineau, D., Nguyen, C. T., Nguyen-Canh, H., Thi, K. N., Gnemmi, V., ... Kather, J. N. (2023). Deep learning-based phenotyping reclassifies combined hepatocellular-cholangiocarcinoma. Nature communications, 14(1), Article 8290. https://doi.org/10.1038/s41467-023-43749-3

Calderaro, J, Ghaffari Laleh, N, Zeng, Q, Maille, P, Favre, L, Pujals, A, Klein, C, Bazille, C, Heij, LR, Uguen, A, Luedde, T, Di Tommaso, L, Beaufrère, A, Chatain, A, Gastineau, D, Nguyen, CT, Nguyen-Canh, H, Thi, KN, Gnemmi, V, Graham, RP, Charlotte, F, Wendum, D, Vij, M, Allende, DS, Aucejo, F, Diaz, A, Rivière, B, Herrero, A, Evert, K, Calvisi, DF, Augustin, J, Leow, WQ, Leung, HHW, Boleslawski, E, Rela, M, François, A, Cha, AWH, Forner, A, Reig, M, Allaire, M, Scatton, O, Chatelain, D, Boulagnon-Rombi, C, Sturm, N, Menahem, B, Frouin, E, Tougeron, D, Tournigand, C, Kempf, E, Kim, H, Ningarhari, M, Michalak-Provost, S, Gopal, P, Brustia, R, Vibert, E, Schulze, K, Rüther, DF, Weidemann, SA, Rhaiem, R, Pawlotsky, JM, Zhang, X, Luciani, A, Mulé, S, Laurent, A, Amaddeo, G, Regnault, H, De Martin, E, Sempoux, C, Navale, P, Westerhoff, M, Lo, RCL, Bednarsch, J, Gouw, A, Guettier, C, Lequoy, M, Harada, K, Sripongpun, P, Wetwittayaklang, P, Loménie, N, Tantipisit, J, Kaewdech, A, Shen, J, Paradis, V, Caruso, S & Kather, JN 2023, 'Deep learning-based phenotyping reclassifies combined hepatocellular-cholangiocarcinoma', Nature communications, vol. 14, no. 1, 8290. https://doi.org/10.1038/s41467-023-43749-3

@article{f996f3c51a91458892ad90f8b8ebe6d7,

title = "Deep learning-based phenotyping reclassifies combined hepatocellular-cholangiocarcinoma",

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.",

author = "Julien Calderaro and {Ghaffari Laleh}, Narmin and Qinghe Zeng and Pascale Maille and Loetitia Favre and Ana{\"i}s Pujals and Christophe Klein and C{\'e}line Bazille and Heij, {Lara R.} and Arnaud Uguen and Tom Luedde and {Di Tommaso}, Luca and Aur{\'e}lie Beaufr{\`e}re and Augustin Chatain and Delphine Gastineau and Nguyen, {Cong Trung} and Hiep Nguyen-Canh and Thi, {Khuyen Nguyen} and Viviane Gnemmi and Graham, {Rondell P.} and Fr{\'e}d{\'e}ric Charlotte and Dominique Wendum and Mukul Vij and Allende, {Daniela S.} and Federico Aucejo and Alba Diaz and Benjamin Rivi{\`e}re and Astrid Herrero and Katja Evert and Calvisi, {Diego Francesco} and J{\'e}r{\'e}my Augustin and Leow, {Wei Qiang} and Leung, {Howard Ho Wai} and Emmanuel Boleslawski and Mohamed Rela and Arnaud Fran{\c c}ois and Cha, {Anthony Wing Hung} and Alejandro Forner and Maria Reig and Manon Allaire and Olivier Scatton and Denis Chatelain and Camille Boulagnon-Rombi and Nathalie Sturm and Benjamin Menahem and Eric Frouin and David Tougeron and Christophe Tournigand and Emmanuelle Kempf and Haeryoung Kim and Massih Ningarhari and Sophie Michalak-Provost and Purva Gopal and Raffaele Brustia and Eric Vibert and Kornelius Schulze and R{\"u}ther, {Darius F.} and Weidemann, {S{\"o}ren A.} and Rami Rhaiem and Pawlotsky, {Jean Michel} and Xuchen Zhang and Alain Luciani and S{\'e}bastien Mul{\'e} and Alexis Laurent and Giuliana Amaddeo and H{\'e}l{\`e}ne Regnault and {De Martin}, Eleonora and Christine Sempoux and Pooja Navale and Maria Westerhoff and Lo, {Regina Cheuk Lam} and Jan Bednarsch and Annette Gouw and Catherine Guettier and Marie Lequoy and Kenichi Harada and Pimsiri Sripongpun and Poowadon Wetwittayaklang and Nicolas Lom{\'e}nie and Jarukit Tantipisit and Apichat Kaewdech and Jeanne Shen and Val{\'e}rie Paradis and Stefano Caruso and Kather, {Jakob Nikolas}",

note = "Publisher Copyright: {\textcopyright} 2023, The Author(s).",

year = "2023",

month = dec,

doi = "10.1038/s41467-023-43749-3",

language = "English (US)",

volume = "14",

journal = "Nature communications",

issn = "2041-1723",

publisher = "Nature Publishing Group",

number = "1",

}

TY - JOUR

T1 - Deep learning-based phenotyping reclassifies combined hepatocellular-cholangiocarcinoma

AU - Calderaro, Julien

AU - Ghaffari Laleh, Narmin

AU - Zeng, Qinghe

AU - Maille, Pascale

AU - Favre, Loetitia

AU - Pujals, Anaïs

AU - Klein, Christophe

AU - Bazille, Céline

AU - Heij, Lara R.

AU - Uguen, Arnaud

AU - Luedde, Tom

AU - Di Tommaso, Luca

AU - Beaufrère, Aurélie

AU - Chatain, Augustin

AU - Gastineau, Delphine

AU - Nguyen, Cong Trung

AU - Nguyen-Canh, Hiep

AU - Thi, Khuyen Nguyen

AU - Gnemmi, Viviane

AU - Graham, Rondell P.

AU - Charlotte, Frédéric

AU - Wendum, Dominique

AU - Vij, Mukul

AU - Allende, Daniela S.

AU - Aucejo, Federico

AU - Diaz, Alba

AU - Rivière, Benjamin

AU - Herrero, Astrid

AU - Evert, Katja

AU - Calvisi, Diego Francesco

AU - Augustin, Jérémy

AU - Leow, Wei Qiang

AU - Leung, Howard Ho Wai

AU - Boleslawski, Emmanuel

AU - Rela, Mohamed

AU - François, Arnaud

AU - Cha, Anthony Wing Hung

AU - Forner, Alejandro

AU - Reig, Maria

AU - Allaire, Manon

AU - Scatton, Olivier

AU - Chatelain, Denis

AU - Boulagnon-Rombi, Camille

AU - Sturm, Nathalie

AU - Menahem, Benjamin

AU - Frouin, Eric

AU - Tougeron, David

AU - Tournigand, Christophe

AU - Kempf, Emmanuelle

AU - Kim, Haeryoung

AU - Ningarhari, Massih

AU - Michalak-Provost, Sophie

AU - Gopal, Purva

AU - Brustia, Raffaele

AU - Vibert, Eric

AU - Schulze, Kornelius

AU - Rüther, Darius F.

AU - Weidemann, Sören A.

AU - Rhaiem, Rami

AU - Pawlotsky, Jean Michel

AU - Zhang, Xuchen

AU - Luciani, Alain

AU - Mulé, Sébastien

AU - Laurent, Alexis

AU - Amaddeo, Giuliana

AU - Regnault, Hélène

AU - De Martin, Eleonora

AU - Sempoux, Christine

AU - Navale, Pooja

AU - Westerhoff, Maria

AU - Lo, Regina Cheuk Lam

AU - Bednarsch, Jan

AU - Gouw, Annette

AU - Guettier, Catherine

AU - Lequoy, Marie

AU - Harada, Kenichi

AU - Sripongpun, Pimsiri

AU - Wetwittayaklang, Poowadon

AU - Loménie, Nicolas

AU - Tantipisit, Jarukit

AU - Kaewdech, Apichat

AU - Shen, Jeanne

AU - Paradis, Valérie

AU - Caruso, Stefano

AU - Kather, Jakob Nikolas

PY - 2023/12

Y1 - 2023/12

N2 - 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.

AB - 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.

UR - http://www.scopus.com/inward/record.url?scp=85179647318&partnerID=8YFLogxK

UR - http://www.scopus.com/inward/citedby.url?scp=85179647318&partnerID=8YFLogxK

U2 - 10.1038/s41467-023-43749-3

DO - 10.1038/s41467-023-43749-3

M3 - Article

C2 - 38092727

AN - SCOPUS:85179647318

SN - 2041-1723

VL - 14

JO - Nature communications

JF - Nature communications

IS - 1

M1 - 8290

ER -

Deep learning-based phenotyping reclassifies combined hepatocellular-cholangiocarcinoma

Abstract

ASJC Scopus subject areas

Access to Document

Other files and links

Fingerprint

Cite this