Deep learning helps discriminate between autoimmune hepatitis and primary biliary cholangitis

Publikation: Beitrag in FachzeitschriftForschungsartikelBeigetragenBegutachtung

Beitragende

  • Alessio Gerussi - , Fondazione IRCCS San Gerardo dei Tintori, Università degli Studi di Milano Bicocca (Autor:in)
  • Oliver Lester Saldanha - , Else Kröner Fresenius Zentrum für Digitale Gesundheit, Universitätsklinikum Aachen (Autor:in)
  • Giorgio Cazzaniga - , Università degli Studi di Milano Bicocca (Autor:in)
  • Damiano Verda - , Rulex Inc. (Autor:in)
  • Zunamys I. Carrero - , Else Kröner Fresenius Zentrum für Digitale Gesundheit (Autor:in)
  • Bastian Engel - , Medizinische Hochschule Hannover (MHH), European Reference Network on Rare Hepatological Diseases (Autor:in)
  • Richard Taubert - , Medizinische Hochschule Hannover (MHH), European Reference Network on Rare Hepatological Diseases (Autor:in)
  • Francesca Bolis - , Fondazione IRCCS San Gerardo dei Tintori, Università degli Studi di Milano Bicocca (Autor:in)
  • Laura Cristoferi - , Fondazione IRCCS San Gerardo dei Tintori, Università degli Studi di Milano Bicocca (Autor:in)
  • Federica Malinverno - , Fondazione IRCCS San Gerardo dei Tintori, Università degli Studi di Milano Bicocca (Autor:in)
  • Francesca Colapietro - , Humanitas University , IRCCS Istituto Clinico Humanitas - Rozzano (Milano) (Autor:in)
  • Reha Akpinar - , Humanitas University , IRCCS Istituto Clinico Humanitas - Rozzano (Milano) (Autor:in)
  • Luca Di Tommaso - , Humanitas University , IRCCS Istituto Clinico Humanitas - Rozzano (Milano) (Autor:in)
  • Luigi Terracciano - , Humanitas University , IRCCS Istituto Clinico Humanitas - Rozzano (Milano) (Autor:in)
  • Ana Lleo - , Humanitas University , IRCCS Istituto Clinico Humanitas - Rozzano (Milano) (Autor:in)
  • Mauro Viganó - , Papa Giovanni XXIII Hospital (Autor:in)
  • Cristina Rigamonti - , University of Eastern Piedmont (Autor:in)
  • Daniela Cabibi - , Università degli Studi di Palermo (Autor:in)
  • Vincenza Calvaruso - , Università degli Studi di Palermo (Autor:in)
  • Fabio Gibilisco - , Ospedale Gravina e Santo Pietro, University of Catania (Autor:in)
  • Nicoló Caldonazzi - , University of Verona (Autor:in)
  • Alessandro Valentino - , Ospedale Niguarda Ca'Granda (Autor:in)
  • Stefano Ceola - , Università degli Studi di Milano Bicocca (Autor:in)
  • Valentina Canini - , Università degli Studi di Milano Bicocca (Autor:in)
  • Eugenia Nofit - , Fondazione IRCCS San Gerardo dei Tintori, Università degli Studi di Milano Bicocca (Autor:in)
  • Marco Muselli - , Rulex Inc. (Autor:in)
  • Julien Calderaro - , Université Paris-Est Créteil, Hôpital Henri Mondor, INSERM - Institut national de la santé et de la recherche médicale (Autor:in)
  • Dina Tiniakos - , Aretaieion University Hospital, Newcastle University (Autor:in)
  • Vincenzo L'Imperio - , Università degli Studi di Milano Bicocca (Autor:in)
  • Fabio Pagni - , Università degli Studi di Milano Bicocca (Autor:in)
  • Nicola Zucchini - , Università degli Studi di Milano Bicocca (Autor:in)
  • Pietro Invernizzi - , Fondazione IRCCS San Gerardo dei Tintori, Università degli Studi di Milano Bicocca (Autor:in)
  • Marco Carbone - , Università degli Studi di Milano Bicocca, Ospedale Niguarda Ca'Granda (Autor:in)
  • Jakob Nikolas Kather - , Medizinische Klinik und Poliklinik I, Else Kröner Fresenius Zentrum für Digitale Gesundheit, Nationales Zentrum für Tumorerkrankungen (NCT) Heidelberg (Autor:in)

Abstract

Background & Aims: Biliary abnormalities in autoimmune hepatitis (AIH) and interface hepatitis in primary biliary cholangitis (PBC) occur frequently, and misinterpretation may lead to therapeutic mistakes with a negative impact on patients. This study investigates the use of a deep learning (DL)-based pipeline for the diagnosis of AIH and PBC to aid differential diagnosis. 

Methods: We conducted a multicenter study across six European referral centers, and built a library of digitized liver biopsy slides dating from 1997 to 2023. A training set of 354 cases (266 AIH and 102 PBC) and an external validation set of 92 cases (62 AIH and 30 PBC) were available for analysis. A novel DL model, the autoimmune liver neural estimator (ALNE), was trained on whole-slide images (WSIs) with H&E staining, without human annotations. The ALNE model was evaluated against clinico-pathological diagnoses and tested for interobserver variability among general pathologists. 

Results: The ALNE model demonstrated high accuracy in differentiating AIH from PBC, achieving an area under the receiver operating characteristic curve of 0.81 in external validation. Attention heatmaps showed that ALNE tends to focus more on areas with increased inflammation, associating such patterns predominantly with AIH. A multivariate explainable ML model revealed that PBC cases misclassified as AIH more often had ALP values between 1 × upper limit of normal (ULN) and 2 × ULN, coupled with AST values above 1 × ULN. Inconsistency among general pathologists was noticed when evaluating a random sample of the same cases (Fleiss's kappa value 0.09). 

Conclusions: The ALNE model is the first system generating a quantitative and accurate differential diagnosis between cases with AIH or PBC. 

Impact and implications: This study demonstrates the significant potential of the autoimmune liver neural estimator model, a transformer-based deep learning system, in accurately distinguishing between autoimmune hepatitis and primary biliary cholangitis using digitized liver biopsy slides without human annotation. The scientific justification for this work lies in addressing the challenge of differentiating these conditions, which often present with overlapping features and can lead to therapeutic mistakes. In addition, there is need for quantitative assessment of information embedded in liver biopsies, which are currently evaluated on qualitative or semi-quantitative methods. The results of this study are crucial for pathologists, researchers, and clinicians, providing a reliable diagnostic tool that reduces interobserver variability and improves diagnostic accuracy of these conditions. Potential methodological limitations, such as the diversity in scanning techniques and slide colorations, were considered, ensuring the robustness and generalizability of the findings.

Details

OriginalspracheEnglisch
Aufsatznummer101198
FachzeitschriftJHEP Reports
Jahrgang7
Ausgabenummer2
PublikationsstatusVeröffentlicht - Feb. 2025
Peer-Review-StatusJa

Externe IDs

ORCID /0000-0001-8501-1566/work/175220823

Schlagworte

Ziele für nachhaltige Entwicklung

Schlagwörter

  • Artificial intelligence, Autoimmunity, Computational pathology, Digital pathology, Liver, Rare liver diseases