Pathological OCT Retinal Layer Segmentation using Branch Residual U-style Networks

Apostolopoulos, Stefanos; De Zanet, Sandro; Ciller, Carlos; Wolf, Sebastian; Sznitman, Raphael (16 July 2017). Pathological OCT Retinal Layer Segmentation using Branch Residual U-style Networks. In: International Conference on Medical Image Computing and Computer Assisted Intervention (MICCAI).

[img]
Preview
Text
1707.04931.pdf - Published Version
Available under License BORIS Standard License.

Download (2MB) | Preview

The automatic segmentation of retinal layer structures enables clinically-relevant quantification and monitoring of eye disorders over time in OCT imaging. Eyes with late-stage diseases are particularly challenging to segment, as their shape is highly warped due to pathological biomarkers. In this context, we propose a novel fully Convolutional Neural Network (CNN) architecture which combines dilated residual blocks in an asymmetric U-shape configuration, and can segment multiple layers of highly pathological eyes in one shot. We validate our approach on a dataset of late-stage AMD patients and demonstrate lower computational costs and higher performance compared to other state-of-the-art methods.

Item Type:

Conference or Workshop Item (Paper)

Division/Institute:

10 Strategic Research Centers > ARTORG Center for Biomedical Engineering Research > ARTORG Center - Image Guided Therapy > ARTORG Center - Ophthalmic Technology Lab
04 Faculty of Medicine > Department of Head Organs and Neurology (DKNS) > Clinic of Ophthalmology
10 Strategic Research Centers > ARTORG Center for Biomedical Engineering Research

Graduate School:

Graduate School for Cellular and Biomedical Sciences (GCB)

UniBE Contributor:

Apostolopoulos, Stefanos; Ciller, Carlos; Wolf, Sebastian and Sznitman, Raphael

Subjects:

500 Science > 570 Life sciences; biology
600 Technology > 610 Medicine & health
600 Technology > 620 Engineering

Language:

English

Submitter:

Raphael Sznitman

Date Deposited:

01 Mar 2018 11:27

Last Modified:

01 Mar 2018 11:27

ArXiv ID:

1707.04931v1

BORIS DOI:

10.7892/boris.108436

URI:

https://boris.unibe.ch/id/eprint/108436

Actions (login required)

Edit item Edit item
Provide Feedback