One model to use them all: training a segmentation model with complementary datasets.

Journal: International journal of computer assisted radiology and surgery
Published Date: Apr 27, 2024

Abstract

PURPOSE: Understanding surgical scenes is crucial for computer-assisted surgery systems to provide intelligent assistance functionality. One way of achieving this is via scene segmentation using machine learning (ML). However, such ML models require large amounts of annotated training data, containing examples of all relevant object classes, which are rarely available. In this work, we propose a method to combine multiple partially annotated datasets, providing complementary annotations, into one model, enabling better scene segmentation and the use of multiple readily available datasets.

Authors

  • Alexander C Jenke
    Department of Translational Surgical Oncology, National Center for Tumor Diseases (NCT/UCC), Dresden, Germany.
  • Sebastian Bodenstedt
    Division of Translational Surgical Oncology, National Center for Tumor Diseases (NCT), Partner Site Dresden, Dresden, Germany.
  • Fiona R Kolbinger
    Department of Visceral, Thoracic and Vascular Surgery, Faculty of Medicine and University Hospital Carl Gustav Carus, TUD Dresden University of Technology, Dresden, Germany; Weldon School of Biomedical Engineering, Purdue University, West Lafayette, Indiana.
  • Marius Distler
    Department of Visceral, Thoracic and Vascular Surgery, University Hospital and Faculty of Medicine Carl Gustav Carus, Technische Universität Dresden, Dresden, Germany.
  • Jürgen Weitz
    Department of Visceral, Thoracic and Vascular Surgery, University Hospital and Faculty of Medicine Carl Gustav Carus, Technische Universität Dresden, Dresden, Germany.
  • Stefanie Speidel
    Division of Translational Surgical Oncology, National Center for Tumor Diseases (NCT), Partner Site Dresden, Dresden, Germany.

Keywords

External Resources

Popular Topics
Recent Journals