Pathological changes or technical artefacts? The problem of the heterogenous databases in COVID-19 CXR image analysis.

Journal: Computer methods and programs in biomedicine
PMID: 37356354

Abstract

BACKGROUND: When the COVID-19 pandemic commenced in 2020, scientists assisted medical specialists with diagnostic algorithm development. One scientific research area related to COVID-19 diagnosis was medical imaging and its potential to support molecular tests. Unfortunately, several systems reported high accuracy in development but did not fare well in clinical application. The reason was poor generalization, a long-standing issue in AI development. Researchers found many causes of this issue and decided to refer to them as confounders, meaning a set of artefacts and methodological errors associated with the method. We aim to contribute to this steed by highlighting an undiscussed confounder related to image resolution.

Authors

  • Marek Socha
    Department of Data Science and Engineering, Silesian University of Technology, Gliwice, Poland.
  • Wojciech Prazuch
    Department of Data Science and Engineering, Silesian University of Technology, 44-100 Gliwice, Poland.
  • Aleksandra Suwalska
    Laboratory of Neuropsychobiology, Department of Psychiatry, University of Medical Sciences, Poznan, Poland.
  • Paweł Foszner
    Department of Computer Graphics, Vision and Digital Systems, Faculty of Automatic Control, Electronics and Computer Science, Silesian University of Technology, Akademicka 2A, 44-100 Gliwice, Poland.
  • Joanna Tobiasz
    Department of Data Science and Engineering, Silesian University of Technology, Gliwice, Poland; Department of Computer Graphics, Vision and Digital Systems, Silesian University of Technology, Gliwice, Poland.
  • Jerzy Jaroszewicz
    Department of Infectious Diseases and Hepatology, Medical University of Silesia, Katowice, Poland.
  • Katarzyna Gruszczynska
    Department of Radiology and Nuclear Medicine, Medical University of Silesia, Katowice, Poland.
  • Magdalena Sliwinska
    Department of Diagnostic Imaging, Voivodship Specialist Hospital, Wroclaw, Poland.
  • Mateusz Nowak
    Department of Radiology, Silesian Hospital, Cieszyn, Poland.
  • Barbara Gizycka
    Department of Imaging Diagnostics, MEGREZ Hospital, Tychy, Poland.
  • Gabriela Zapolska
    Department of Radiology, Czerniakowski Hospital, Warsaw, Poland.
  • Tadeusz Popiela
    Chair of Radiology, Jagiellonian University Medical College, 31-501 Kraków, Poland.
  • Grzegorz Przybylski
    Department of Lung Diseases, Cancer and Tuberculosis, Kujawsko-Pomorskie Pulmonology Center, Bydgoszcz, Poland.
  • Piotr Fiedor
    Department of General and Transplantation Surgery, Medical University of Warsaw, Warsaw, Poland.
  • Małgorzata Pawłowska
    Katedra i Klinika Chorób Zakaźnych i Hepatologii, Collegium Medicum Uniwersytetu Mikołaja Kopernika w Toruniu. kikchzak@cm.umk.pl
  • Robert Flisiak
    c Department of Infectious Diseases and Hepatology , Medical University of Bialystok , Bialystok , Poland.
  • Krzysztof Simon
    Department of Infectious Diseases and Hepatology, Wroclaw Medical University, Wroclaw, Poland.
  • Jerzy Walecki
    Department of Radiology, Centre of Postgraduate Medical Education, Central Clinical Hospital of the Ministry of Interior in Warsaw, Poland.
  • Andrzej Cieszanowski
    Department of Radiology I, The Maria Sklodowska-Curie National Research Institute of Oncology, Warsaw, Poland.
  • Edyta Szurowska
    2nd Department of Radiology, Medical University of Gdansk, 80-210 Gdansk, Poland.
  • Michal Marczyk
    Department of Data Science and Engineering, Silesian University of Technology, 44-100 Gliwice, Poland.
  • Joanna Polanska
    Department of Data Science and Engineering, Silesian University of Technology, 44-100 Gliwice, Poland.

Keywords

External Resources

Popular Topics
Recent Journals