Accuracy of segment anything model for classification of vascular stenosis in digital subtraction angiography.

Journal: CVIR endovascular
Published Date: May 19, 2025

Abstract

BACKGROUND: This retrospective study evaluates the diagnostic performance of an optimized comprehensive multi-stage framework based on the Segment Anything Model (SAM), which we named Dr-SAM, for detecting and grading vascular stenosis in the abdominal aorta and iliac arteries using digital subtraction angiography (DSA).

Authors

  • Vagner Navasardyan
    Department of Radiology, Neuroradiology and Nuclear Medicine, Johannes Wesling University Hospital, Hans-Nolte-Straße 1, 32429, Minden, Germany. Vagner.Navasardyan@edu.ruhr-uni-bochum.de.
  • Maria Katz
    Department of Radiology, Neuroradiology and Nuclear Medicine, Johannes Wesling University Hospital, Hans-Nolte-Straße 1, 32429, Minden, Germany.
  • Lukas Goertz
    Institute for Diagnostic and Interventional Radiology, Faculty of Medicine and University Hospital Cologne, University of Cologne, Cologne, Germany.
  • Vazgen Zohranyan
    ServiceTitan, Inc, 11/1 Antarain St, 0009, Yerevan, Armenia.
  • Hayk Navasardyan
    Synopsys Armenia CJSC, 41 Arshakunyats Ave, Yerevan, Armenia.
  • Iram Shahzadi
    Department of Radiology, Neuroradiology and Nuclear Medicine, Johannes Wesling University Hospital, Ruhr University Bochum, Bochum, Germany; Siemens Healthineers GmbH, Erlangen, Germany.
  • Jan Robert Kröger
    , Hans-Nolte-Str. 1, 32429, Minden, Deutschland.
  • Jan Borggrefe
    Institute for Diagnostic and Interventional Radiology, University Hospital Cologne, Cologne, Germany. jan.borggrefe@uk-koeln.de.

Keywords

No keywords available for this article.

External Resources

Popular Topics
Recent Journals