Performance and limitations of a supervised deep learning approach for the histopathological Oxford Classification of glomeruli with IgA nephropathy.

Journal: Computer methods and programs in biomedicine
PMID: 37722311

Abstract

BACKGROUND AND OBJECTIVE: The Oxford Classification for IgA nephropathy is the most successful example of an evidence-based nephropathology classification system. The aim of our study was to replicate the glomerular components of Oxford scoring with an end-to-end deep learning pipeline that involves automatic glomerular segmentation followed by classification for mesangial hypercellularity (M), endocapillary hypercellularity (E), segmental sclerosis (S) and active crescents (C).

Authors

  • Nicola Altini
    Department of Electrical and Information Engineering (DEI), Polytechnic University of Bari, Via Edoardo Orabona n.4, Bari 70126, Italy.
  • Michele Rossini
    Department of Emergency and Organ Transplantation, Nephrology Unit University of Bari Aldo Moro, Bari, Italy.
  • Sándor Turkevi-Nagy
    Department of Pathology, Albert Szent-Györgyi Health Center, University of Szeged, Szeged, Hungary.
  • Francesco Pesce
    D.E.T.O. University of Bari Medical School, Piazza Giulio Cesare, 11, Bari, 70124, Italy.
  • Paola Pontrelli
    Nephrology Dialysis and Transplantation Unit, Department of Emergency and Organ Transplantation, University of Bari, Bari, Italy.
  • Berardino Prencipe
    Department of Electrical and Information Engineering (DEI), Polytechnic University of Bari, Via Edoardo Orabona n.4, Bari 70126, Italy.
  • Francesco Berloco
  • Surya Seshan
    Department of Pathology, Weill-Cornell Medical Center/New York Presbyterian Hospital, New York, NY, USA.
  • Jean-Baptiste Gibier
    Department of Pathology, Pathology Institute, Lille University Hospital (CHU), Lille, France.
  • Aníbal Pedraza Dorado
    VISILAB Research Group, University of Castilla-La Mancha, Ciudad Real, Spain.
  • Gloria Bueno
    VISILAB Group, ETSI Industriales, University of Castilla-La Mancha, Ciudad Real, Spain.
  • Licia Peruzzi
    AOU Città della Salute e della Scienza di Torino, Regina Margherita Children's Hospital, Turin, Italy.
  • Mattia Rossi
    Division of Nephrology, Department of Medicine, University of Verona, Piazzale Aristide Stefani, 1, 37126, Verona, Italy.
  • Albino Eccher
    Department of Pathology and Diagnostics, University and Hospital Trust of Verona, P.le Stefani n. 1, 37126, Verona, Italy. albino.eccher@aovr.veneto.it.
  • Feifei Li
    School of Chinese Pharmacy, Beijing University of Chinese Medicine, Beijing 102488, China.
  • Adamantios Koumpis
    Institut Digital Enabling, Berner Fachhochschule, CH-3012 Bern, Switzerland.
  • Oya Beyan
    Institute for Biomedical Informatics, Faculty of Medicine and University Hospital Cologne, University of Cologne, Cologne, Germany.
  • Jonathan Barratt
    The Mayer IgA Nephropathy Laboratories, Department of Cardiovascular, University of Leicester, Leicester, UK.
  • Huy Quoc Vo
    Department of Biomedical Engineering, University of Houston, Houston, USA.
  • Chandra Mohan
    Biomedical Engineering & Medicine, University of Houston, Houston, TX, United States.
  • Hien Van Nguyen
    Department of Biomedical Engineering, University of Houston, Houston, USA.
  • Pietro Antonio Cicalese
    Department of Biomedical Engineering, University of Houston, Houston, USA.
  • Angela Ernst
    Faculty of Medicine, Institute of Medical Statistics and Computational Biology, University of Cologne, Cologne, Germany.
  • Loreto Gesualdo
    Department of Diagnostic Pathology, Bioimages and Public Health, Policlinic University Hospital, Bari, Italy.
  • Vitoantonio Bevilacqua
  • Jan Ulrich Becker
    Institute of Pathology, University Hospital of Cologne, Cologne, Germany.

Keywords

External Resources

Popular Topics
Recent Journals