OCT-NET : a convolutional network for automatic classification of normal and diabetic macular edema using sd-oct volumes

Perdomo, Oscar (MindLab Research Group, Universidad Nacional de Colombia, Colombia) ; Otálora, Sebastian (University of Applied Sciences and Arts Western Switzerland (HES-SO Valais-Wallis)) ; González, Fabio A. (University of Applied Sciences and Arts Western Switzerland (HES-SO Valais-Wallis)) ; Meriaudeau, Fabrice (Universiti Teknologi PETRONAS, Malaysia) ; Müller, Henning (University of Applied Sciences and Arts Western Switzerland (HES-SO Valais-Wallis))

Diabetic macular edema (DME) is one of the most common eye complication caused by diabetes mellitus, resulting in partial or total loss of vision. Optical Coherence Tomography (OCT) volumes have been widely used to diagnose different eye diseases, thanks to their sensitivity to represent small amounts of fluid, thickness between layers and swelling. However, the lack of tools for automatic image analysis for supporting disease diagnosis is still a problem. Convolutional neural networks (CNNs) have shown outstanding performance when applied to several medical images analysis tasks. This paper presents a model, OCT-NET, based on a CNN for the automatic classification of OCT volumes. The model was evaluated on a dataset of OCT volumes for DME diagnosis using a leave-one-out cross-validation strategy obtaining an accuracy, sensitivity, and specificity of 93.75%.


Keywords:
Conference Type:
full paper
Faculty:
Economie et Services
School:
HEG-VS
Institute:
Institut Informatique de gestion
Subject(s):
Informatique
Publisher:
Washington, USA, 4-7 April 2018
Date:
2018-04
Washington, USA
4-7 April 2018
Pagination:
4 p.
Published in:
Proceedings of the 15th International Symposium on Biomedical Imaging IEEE 2018 (ISBI 2018)
DOI:
ISSN:
1945-8452
Appears in Collection:

Note: The status of this file is: public


 Record created 2018-11-30, last modified 2019-06-11

Fulltext:
Download fulltext
PDF

Rate this document:

Rate this document:
1
2
3
 
(Not yet reviewed)