Training and validation of a deep learning U-net architecture general model for automated segmentation of inner ear from CT.

Journal: European radiology experimental
PMID: 39266784

Abstract

BACKGROUND: The intricate three-dimensional anatomy of the inner ear presents significant challenges in diagnostic procedures and critical surgical interventions. Recent advancements in deep learning (DL), particularly convolutional neural networks (CNN), have shown promise for segmenting specific structures in medical imaging. This study aimed to train and externally validate an open-source U-net DL general model for automated segmentation of the inner ear from computed tomography (CT) scans, using quantitative and qualitative assessments.

Authors

  • Jonathan Lim
    Department of Endocrinology and Diabetes, University Hospital Aintree, Longmoor Lane, Liverpool, UK.
  • Aurore Abily
    Department of Neuroradiology-Brest University Hospital, Boulevard Tanguy Prigent, 29200, Brest, France.
  • Douraied Ben Salem
    Neuroradiology, University Hospital of Brest, boulevard Tanguy-Prigent, 29609 Brest cedex, France; Laboratory of medical information processing - LaTIM, Inserm UMR 1101, CS 93837, Université de Bretagne Occidentale, 22, avenue Camille-Desmoulins, 29238 Brest cedex 3, France. Electronic address: douraied.bensalem@chu-brest.fr.
  • Loic Gaillandre
    Centre Libéral d'Imagerie Médicale de l'Agglomération Lilloise, 59000 Lille, France.
  • Arnaud Attyé
    CNRS LPNC UMR 5105, CS 40700, University of Grenoble Alpes, 38058 Grenoble cedex 9, France.
  • Julien Ognard
    Neuroradiology, University Hospital of Brest, boulevard Tanguy-Prigent, 29609 Brest cedex, France; Laboratory of medical information processing - LaTIM, Inserm UMR 1101, CS 93837, Université de Bretagne Occidentale, 22, avenue Camille-Desmoulins, 29238 Brest cedex 3, France.

Keywords

External Resources

Popular Topics
Recent Journals