Universität zu Köln

Venhuizen, Freerk G., van Ginneken, Bram ORCID: 0000-0003-2028-8972, Liefers, Bart, van Grinsven, Mark J. J. P., Fauser, Sascha, Hoyng, Carel, Theelen, Thomas and Sanchez, Clara I. (2017). Robust total retina thickness segmentation in optical coherence tomography images using convolutional neural networks. Biomed. Opt. Express, 8 (7). S. 3292 - 3317. WASHINGTON: OPTICAL SOC AMER. ISSN 2156-7085

Full text not available from this repository.

Abstract

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 mu m, substantially lower than the error obtained using the other algorithms (42.9 +/- 116.0 mu m and 27.1 +/- 69.3 mu m, 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. (C) 2017 Optical Society of America

Item Type:	Journal Article
Creators:	Creators Email ORCID ORCID Put Code Venhuizen, Freerk G. UNSPECIFIED UNSPECIFIED UNSPECIFIED van Ginneken, Bram UNSPECIFIED orcid.org/0000-0003-2028-8972 UNSPECIFIED Liefers, Bart UNSPECIFIED UNSPECIFIED UNSPECIFIED van Grinsven, Mark J. J. P. UNSPECIFIED UNSPECIFIED UNSPECIFIED Fauser, Sascha UNSPECIFIED UNSPECIFIED UNSPECIFIED Hoyng, Carel UNSPECIFIED UNSPECIFIED UNSPECIFIED Theelen, Thomas UNSPECIFIED UNSPECIFIED UNSPECIFIED Sanchez, Clara I. UNSPECIFIED UNSPECIFIED UNSPECIFIED
URN:	urn:nbn:de:hbz:38-225963
DOI:	10.1364/BOE.8.003292
Journal or Publication Title:	Biomed. Opt. Express
Volume:	8
Number:	7
Page Range:	S. 3292 - 3317
Date:	2017
Publisher:	OPTICAL SOC AMER
Place of Publication:	WASHINGTON
ISSN:	2156-7085
Language:	English
Faculty:	Unspecified
Divisions:	Unspecified
Subjects:	no entry
Uncontrolled Keywords:	Keywords Language AUTOMATED LAYER SEGMENTATION; DIABETIC MACULAR EDEMA; SD-OCT IMAGES; GEOGRAPHIC ATROPHY; VISUAL-ACUITY; FLUID; EYES; BOUNDARIES; PATHOLOGY; CIRRUS Multiple languages Biochemical Research Methods; Optics; Radiology, Nuclear Medicine & Medical Imaging Multiple languages
Refereed:	Yes
URI:	http://kups.ub.uni-koeln.de/id/eprint/22596