Article Dans Une Revue European Journal of Nuclear Medicine and Molecular Imaging Année : 2021

An [18F]FDG-PET/CT deep learning method for fully automated detection of pathological mediastinal lymph nodes in lung cancer patients

David Wallis
  • Fonction : Auteur
  • PersonId : 1139151
Michaël Soussan
  • Fonction : Auteur
Maxime Lacroix
  • Fonction : Auteur
Pia Akl
  • Fonction : Auteur
Clément Duboucher
  • Fonction : Auteur

Résumé

The identification of pathological mediastinal lymph nodes is an important step in the staging of lung cancer, with the presence of metastases significantly affecting survival rates. Nodes are currently identified by a physician, but this process is time-consuming and prone to errors. In this paper we investigate the use of artificial intelligence-based methods to increase the accuracy and consistency of this process. Methods: Whole-body [18F]FDG-PET/CT scans (Philips Gemini TF) from 134 patients were retrospectively analysed. The thorax was automatically located, then slices were fed into a U-Net to identify candidate regions. These regions were split into overlapping 3D cubes, which were individually predicted as positive or negative using a 3D CNN. From these

Fichier principal
Vignette du fichier
EJNMMI_Submission_accepted_IB.pdf (401.9 Ko) Télécharger le fichier
Origine Fichiers produits par l'(les) auteur(s)
Licence

Dates et versions

hal-03441716 , version 1 (22-11-2021)

Licence

Identifiants

Citer

David Wallis, Michaël Soussan, Maxime Lacroix, Pia Akl, Clément Duboucher, et al.. An [18F]FDG-PET/CT deep learning method for fully automated detection of pathological mediastinal lymph nodes in lung cancer patients. European Journal of Nuclear Medicine and Molecular Imaging, 2021, 49 (3), pp.881-888. ⟨10.1007/s00259-021-05513-x⟩. ⟨hal-03441716⟩
97 Consultations
222 Téléchargements

Altmetric

Partager

  • More