Full text
Preview |
PDF
- Requires a PDF viewer, such as GSview, Xpdf or Adobe Acrobat Reader
Download (518kB) | Preview |
Segmenting retinal vascular net from retinopathy of prematurity images using convolutional neural network
Citation
Intriago Pazmiño, Monserrate, Ibarra Fiallo, Julio, Alonso Calvo, Raúl 
ORCID: https://orcid.org/0000-0002-2803-0215 and Crespo Del Arco, José ORCID: https://orcid.org/0000-0002-0772-5421
(2019).
Segmenting retinal vascular net from retinopathy of prematurity images using convolutional neural network.
In: "Second International Conference on Data Science, E-Learning and Information Systems (DATA '19)", 02-05 Dic 2019, Dubai, Emiratos Árabes. ISBN 978-1-4503-7284-8. pp. 1-5.
https://doi.org/10.1145/3368691.3368711.
Description
| Title: | Segmenting retinal vascular net from retinopathy of prematurity images using convolutional neural network |
|---|---|
| Author/s: |
|
| Item Type: | Presentation at Congress or Conference (Article) |
| Event Title: | Second International Conference on Data Science, E-Learning and Information Systems (DATA '19) |
| Event Dates: | 02-05 Dic 2019 |
| Event Location: | Dubai, Emiratos Árabes |
| Title of Book: | DATA '19: Proceedings of the Second International Conference on Data Science, E-Learning and Information Systems |
| Date: | 2019 |
| ISBN: | 978-1-4503-7284-8 |
| Subjects: | |
| Freetext Keywords: | Retinopathy of prematurity; Convolutional neural network; Medical image processing |
| Faculty: | E.T.S. de Ingenieros Informáticos (UPM) |
| Department: | Lenguajes y Sistemas Informáticos e Ingeniería del Software |
| Creative Commons Licenses: | Recognition - No derivative works - Non commercial |
Abstract
In this paper, we describe the experimentation with a convolutional neural network for segmenting retinal net from pathological fundus images of preterm born children. Segmenting retinal net from pathological fundus images is a fundamental task to aid computer diagnosis. We used U-net architecture for training and testing. Testing with ROPFI dataset, we obtained an area under the receiver operating curve equal to 0.9180; when average sensitivity is equal to 0.700, the average specificity is equal to 0.9710. This performance is higher than prior works using a similar dataset.
More information
| Item ID: | 65283 |
|---|---|
| DC Identifier: | https://oa.upm.es/65283/ |
| OAI Identifier: | oai:oa.upm.es:65283 |
| DOI: | 10.1145/3368691.3368711 |
| Official URL: | https://dl.acm.org/doi/pdf/10.1145/3368691.3368711 |
| Deposited by: | Memoria Investigacion |
| Deposited on: | 10 Nov 2020 07:25 |
| Last Modified: | 10 Nov 2020 07:25 |
