Multimodal convolutional neural network-based algorithm for real-time detection and differentiation of malignant and inflammatory biliary strictures in cholangioscopy: a proof-of-concept study (with video).

Journal: Gastrointestinal endoscopy
PMID:

Abstract

BACKGROUND AND AIMS: Deep learning algorithms gained attention for detection (computer-aided detection [CADe]) of biliary tract cancer in digital single-operator cholangioscopy (dSOC). We developed a multimodal convolutional neural network (CNN) for detection (CADe), characterization and discriminating (computer-aided diagnosis [CADx]) between malignant, inflammatory, and normal biliary tissue in raw dSOC videos. In addition, clinical metadata were included in the CNN algorithm to overcome limitations of image-only models.

Authors

  • Joceline Ziegler
    Digital Engineering Faculty, University of Potsdam, 14482 Potsdam, Germany.
  • Philipp Dobsch
    Department of Internal Medicine I, Gastroenterology, Hepatology, Endocrinology, Rheumatology and Infectious Diseases, University Hospital Regensburg, Regensburg, Germany.
  • Marten Rozema
    Unetiq GmbH, München, Germany.
  • Ina Zuber-Jerger
    Department of Internal Medicine I, Gastroenterology, Hepatology, Endocrinology, Rheumatology and Infectious Diseases, University Hospital Regensburg, Regensburg, Germany.
  • Kilian Weigand
    Department of Internal Medicine I, Gastroenterology, Hepatology, Endocrinology, Rheumatology and Infectious Diseases, University Hospital Regensburg, Regensburg, Germany; Department of Internal Medicine, Gastroenterology, Gastrointestinal Oncology and Diabetology, Gemeinschaftsklinikum Mittelrhein, Koblenz, Germany.
  • Stefan Reuther
    Unetiq GmbH, München, Germany.
  • Martina Müller
    Department of Internal Medicine I, Gastroenterology, Hepatology, Endocrinology, Rheumatology and Infectious Diseases, University Hospital Regensburg, Regensburg, Germany.
  • Arne Kandulski
    Department of Internal Medicine I, Gastroenterology, Hepatology, Endocrinology, Rheumatology and Infectious Diseases, University Hospital Regensburg, Regensburg, Germany. Electronic address: Arne.Kandulski@ukr.de.