Enhancing deep learning methods for brain metastasis detection through cross-technique annotations on SPACE MRI.

Journal: European radiology experimental
PMID: 39913077

Abstract

BACKGROUND: Gadolinium-enhanced "sampling perfection with application-optimized contrasts using different flip angle evolution" (SPACE) sequence allows better visualization of brain metastases (BMs) compared to "magnetization-prepared rapid acquisition gradient echo" (MPRAGE). We hypothesize that this better conspicuity leads to high-quality annotation (HAQ), enhancing deep learning (DL) algorithm detection of BMs on MPRAGE images.

Authors

  • Tassilo Wald
    Division of Medical Image Computing, German Cancer Research Center (DKFZ), Im Neuenheimer Feld 280, 69120, Heidelberg, Germany.
  • Benjamin Hamm
    German Cancer Research Center (DKFZ) Heidelberg, Division of Medical Image Computing, Heidelberg, Germany.
  • Julius C Holzschuh
    Department of Radiation Oncology, Medical Center - University of Freiburg, Freiburg, Germany; German Cancer Consortium (DKTK), Partner Site Freiburg, Freiburg, Germany; Faculty of Computer Science, Karlsruhe Institute of Technology, Karlsruhe, Germany. Electronic address: julius.holzschuh@uniklinik-freiburg.de.
  • Rami El Shafie
    Department of Radiation Oncology, Heidelberg University Hospital, Heidelberg, Germany.
  • Andreas Kudak
    Department of Radiation Oncology, Heidelberg University Hospital, Heidelberg, Germany.
  • Balint Kovacs
    German Cancer Research Center (DKFZ) Heidelberg, Division of Medical Image Computing, Heidelberg, Germany.
  • Irada Pflüger
    Department of Neuroradiology, Heidelberg University Hospital, Heidelberg, Germany.
  • Bastian von Nettelbladt
    Department of Radiation Oncology, Heidelberg University Hospital, Heidelberg, Germany.
  • Constantin Ulrich
    German Cancer Research Center (DKFZ) Heidelberg, Division of Medical Image Computing, Heidelberg, Germany.
  • Michael Anton Baumgartner
    German Cancer Research Center (DKFZ) Heidelberg, Division of Medical Image Computing, Heidelberg, Germany.
  • Philipp Vollmuth
    Department of Neuroradiology, Heidelberg University Hospital, Heidelberg, Germany. Electronic address: philipp.vollmuth@med.uni-heidelberg.de.
  • Jürgen Debus
    Department of Radiation Oncology, Heidelberg University Hospital, Heidelberg, Germany; Heidelberg Institute of Radiation Oncology, Heidelberg, Germany; Heidelberg Ion-Beam Therapy Center, Heidelberg, Germany.
  • Klaus H Maier-Hein
    Medical Image Computing (MIC), German Cancer Research Center (DKFZ), Heidelberg, Germany. Electronic address: k.maier-hein@dkfz.de.
  • Thomas Welzel
    Department of Radiation Oncology, Heidelberg University Hospital, Heidelberg, Germany.

Keywords

External Resources

Popular Topics
Recent Journals