Robust total retina thickness segmentation in optical coherence tomography images using convolutional neural networks.

Autor:	Venhuizen FG; Diagnostic Image Analysis Group, Radboud University Medical Center, Nijmegen, the Netherlands.; Department of Ophthalmology, Radboud University Medical Center, Nijmegen, the Netherlands., van Ginneken B; Diagnostic Image Analysis Group, Radboud University Medical Center, Nijmegen, the Netherlands., Liefers B; Diagnostic Image Analysis Group, Radboud University Medical Center, Nijmegen, the Netherlands.; Department of Ophthalmology, Radboud University Medical Center, Nijmegen, the Netherlands., van Grinsven MJJP; Diagnostic Image Analysis Group, Radboud University Medical Center, Nijmegen, the Netherlands.; Department of Ophthalmology, Radboud University Medical Center, Nijmegen, the Netherlands., Fauser S; Roche Pharma Research and Early Development, F. Hoffmann-La Roche Ltd, Basel, Switzerland.; Cologne University Eye Clinic, Cologne, Germany., Hoyng C; Department of Ophthalmology, Radboud University Medical Center, Nijmegen, the Netherlands., Theelen T; Diagnostic Image Analysis Group, Radboud University Medical Center, Nijmegen, the Netherlands.; Department of Ophthalmology, Radboud University Medical Center, Nijmegen, the Netherlands., Sánchez CI; Diagnostic Image Analysis Group, Radboud University Medical Center, Nijmegen, the Netherlands.; Department of Ophthalmology, Radboud University Medical Center, Nijmegen, the Netherlands.
Jazyk:	angličtina
Zdroj:	Biomedical optics express [Biomed Opt Express] 2017 Jun 16; Vol. 8 (7), pp. 3292-3316. Date of Electronic Publication: 2017 Jun 16 (Print Publication: 2017).
DOI:	10.1364/BOE.8.003292
Abstrakt:	We developed a fully automated system using a convolutional neural network (CNN) for total retina segmentation in optical coherence tomography (OCT) that is robust to the presence of severe retinal pathology. A generalized U-net network architecture was introduced to include the large context needed to account for large retinal changes. The proposed algorithm outperformed qualitative and quantitatively two available algorithms. The algorithm accurately estimated macular thickness with an error of 14.0 ± 22.1 µm, substantially lower than the error obtained using the other algorithms (42.9 ± 116.0 µm and 27.1 ± 69.3 µm, respectively). These results highlighted the proposed algorithm's capability of modeling the wide variability in retinal appearance and obtained a robust and reliable retina segmentation even in severe pathological cases.
Databáze:	MEDLINE
Externí odkaz:	Zobrazit plný text záznamu