Validation of SynthSeg segmentation performance on CT using paired MRI from radiotherapy patients.

Journal: NeuroImage
Published Date: Nov 16, 2024

Abstract

INTRODUCTION: Manual segmentation of medical images is labor intensive and especially challenging for images with poor contrast or resolution. The presence of disease exacerbates this further, increasing the need for an automated solution. To this extent, SynthSeg is a robust deep learning model designed for automatic brain segmentation across various contrasts and resolutions. This study validates the SynthSeg robust brain segmentation model on computed tomography (CT), using a multi-center dataset.

Authors

  • Selena Huisman
    Department of Radiation Oncology, Amsterdam UMC, De Boelelaan 1117, 1081 HV Amsterdam, The Netherlands; Department of Radiation Oncology, UMC Utrecht, Heidelberglaan 100, 3508 GA Utrecht, The Netherlands. Electronic address: s.i.huisman@amsterdamumc.nl.
  • Matteo Maspero
    Department of Radiation Oncology, Imaging and Cancer Division, University Medical Center Utrecht, Utrecht, The Netherlands; Computational Imaging Group for MR Diagnostics & Therapy, Center for Image Sciences, University Medical Center Utrecht, Utrecht, The Netherlands.
  • Marielle Philippens
    Department of Radiation Oncology, UMC Utrecht, Heidelberglaan 100, 3508 GA Utrecht, The Netherlands.
  • Joost Verhoeff
    Department of Radiation Oncology, Amsterdam UMC, De Boelelaan 1117, 1081 HV Amsterdam, The Netherlands; Department of Radiation Oncology, UMC Utrecht, Heidelberglaan 100, 3508 GA Utrecht, The Netherlands.
  • Szabolcs David
    Department of Radiation Oncology, UMC Utrecht, 3584 CX Utrecht, The Netherlands. Electronic address: s.david@umcutrecht.nl.

Keywords

External Resources

Popular Topics
Recent Journals