DRUNET : a dilated-residual U-Net deep learning network to segment optic nerve head tissues in optical coherence tomography images - Archive ouverte HAL Accéder directement au contenu
Article Dans Une Revue Biomedical optics express Année : 2018

DRUNET : a dilated-residual U-Net deep learning network to segment optic nerve head tissues in optical coherence tomography images

Sripad Krishna Devalla
  • Fonction : Auteur
Prajwal P. Renukanand
  • Fonction : Auteur
Bharathwaj K. Sreedhar
  • Fonction : Auteur
Giridhar Subramanian
  • Fonction : Auteur
Liang Zhang
  • Fonction : Auteur
  • PersonId : 1012730
Shamira Perera
  • Fonction : Auteur
Jean-Martial Mari
Khai Sing Chin
  • Fonction : Auteur
Tin A. Tun
  • Fonction : Auteur
Nicholas G. Strouthidis
  • Fonction : Auteur
Alexandre H. Thiéry
  • Fonction : Auteur
Michaël J. A. Girard
  • Fonction : Auteur

Résumé

Given that the neural and connective tissues of the optic nerve head (ONH) exhibit complex morphological changes with the development and progression of glaucoma, their simultaneous isolation from optical coherence tomography (OCT) images may be of great interest for the clinical diagnosis and management of this pathology. A deep learning algorithm (custom U-NET) was designed and trained to segment 6 ONH tissue layers by capturing both the local (tissue texture) and contextual information (spatial arrangement of tissues). The overall Dice coefficient (mean of all tissues) was 0.91 ± 0.05 when assessed against manual segmentations performed by an expert observer. Further, we automatically extracted six clinically relevant neural and connective tissue structural parameters from the segmented tissues. We offer here a robust segmentation framework that could also be extended to the 3D segmentation of the ONH tissues. "Comparison of Bruch's membrane opening minimum rim width and peripapillary retinal nerve fiber layer thickness in early glaucoma assessment BMO-MRW and RNFLT in early glaucoma assessment," Invest.
Fichier principal
Vignette du fichier
Mari-13-2018-gepasud.pdf (7.45 Mo) Télécharger le fichier
Origine : Fichiers éditeurs autorisés sur une archive ouverte
Loading...

Dates et versions

hal-02145030 , version 1 (31-05-2019)

Identifiants

Citer

Sripad Krishna Devalla, Prajwal P. Renukanand, Bharathwaj K. Sreedhar, Giridhar Subramanian, Liang Zhang, et al.. DRUNET : a dilated-residual U-Net deep learning network to segment optic nerve head tissues in optical coherence tomography images. Biomedical optics express, 2018, 9 (7), pp.3244-3265. ⟨10.1364/BOE.9.003244⟩. ⟨hal-02145030⟩

Collections

UPF
109 Consultations
123 Téléchargements

Altmetric

Partager

Gmail Facebook X LinkedIn More