Deep Learning–Enabled Diagnosis of Liver Adenocarcinoma

Publikation: Beitrag in FachzeitschriftForschungsartikelBeigetragenBegutachtung


  • Thomas Albrecht - , Universität Heidelberg, Liver Cancer Center Heidelberg (LCCH) (Autor:in)
  • Annik Rossberg - , Universität Heidelberg (Autor:in)
  • Jana Dorothea Albrecht - , Universität Heidelberg (Autor:in)
  • Jan Peter Nicolay - , Universität Heidelberg (Autor:in)
  • Beate Katharina Straub - , Johannes Gutenberg-Universität Mainz (Autor:in)
  • Tiemo Sven Gerber - , Johannes Gutenberg-Universität Mainz (Autor:in)
  • Michael Albrecht - , Universitätsklinikum Heidelberg (Autor:in)
  • Fritz Brinkmann - , Universität Heidelberg (Autor:in)
  • Alphonse Charbel - , Universität Heidelberg (Autor:in)
  • Constantin Schwab - , Universität Heidelberg (Autor:in)
  • Johannes Schreck - , Universität Heidelberg (Autor:in)
  • Alexander Brobeil - , Universität Heidelberg (Autor:in)
  • Christa Flechtenmacher - , Universität Heidelberg (Autor:in)
  • Moritz von Winterfeld - , Universität Heidelberg (Autor:in)
  • Bruno Christian Köhler - , Liver Cancer Center Heidelberg (LCCH), Universität Heidelberg (Autor:in)
  • Christoph Springfeld - , Liver Cancer Center Heidelberg (LCCH), Universität Heidelberg (Autor:in)
  • Arianeb Mehrabi - , Liver Cancer Center Heidelberg (LCCH), Universität Heidelberg (Autor:in)
  • Stephan Singer - , Eberhard Karls Universität Tübingen (Autor:in)
  • Monika Nadja Vogel - , Universität Heidelberg (Autor:in)
  • Olaf Neumann - , Universität Heidelberg (Autor:in)
  • Albrecht Stenzinger - , Universität Heidelberg (Autor:in)
  • Peter Schirmacher - , Universität Heidelberg, Liver Cancer Center Heidelberg (LCCH) (Autor:in)
  • Cleo Aron Weis - , Universität Heidelberg (Autor:in)
  • Stephanie Roessler - , Universität Heidelberg, Liver Cancer Center Heidelberg (LCCH) (Autor:in)
  • Jakob Nikolas Kather - , Else Kröner Fresenius Zentrum für Digitale Gesundheit, Nationales Zentrum für Tumorerkrankungen (NCT) Heidelberg (Autor:in)
  • Benjamin Goeppert - , Universität Heidelberg, RKH Hospital Ludwigsburg, Universität Bern (Autor:in)


Background & Aims: Diagnosis of adenocarcinoma in the liver is a frequent scenario in routine pathology and has a critical impact on clinical decision making. However, rendering a correct diagnosis can be challenging, and often requires the integration of clinical, radiologic, and immunohistochemical information. We present a deep learning model (HEPNET) to distinguish intrahepatic cholangiocarcinoma from colorectal liver metastasis, as the most frequent primary and secondary forms of liver adenocarcinoma, with clinical grade accuracy using H&E-stained whole-slide images. Methods: HEPNET was trained on 714,589 image tiles from 456 patients who were randomly selected in a stratified manner from a pool of 571 patients who underwent surgical resection or biopsy at Heidelberg University Hospital. Model performance was evaluated on a hold-out internal test set comprising 115 patients and externally validated on 159 patients recruited at Mainz University Hospital. Results: On the hold-out internal test set, HEPNET achieved an area under the receiver operating characteristic curve of 0.994 (95% CI, 0.989–1.000) and an accuracy of 96.522% (95% CI, 94.521%–98.694%) at the patient level. Validation on the external test set yielded an area under the receiver operating characteristic curve of 0.997 (95% CI, 0.995–1.000), corresponding to an accuracy of 98.113% (95% CI, 96.907%–100.000%). HEPNET surpassed the performance of 6 pathology experts with different levels of experience in a reader study of 50 patients (P = .0005), boosted the performance of resident pathologists to the level of senior pathologists, and reduced potential downstream analyses. Conclusions: We provided a ready-to-use tool with clinical grade performance that may facilitate routine pathology by rendering a definitive diagnosis and guiding ancillary testing. The incorporation of HEPNET into pathology laboratories may optimize the diagnostic workflow, complemented by test-related labor and cost savings.


Seiten (von - bis)1262-1275
PublikationsstatusVeröffentlicht - Nov. 2023

Externe IDs

PubMed 37562657


Ziele für nachhaltige Entwicklung

ASJC Scopus Sachgebiete


  • Artificial Intelligence, Biliary Tract Cancer, Digital Pathology, Intestinal Cancer