Memorias de investigación
Communications at congresses:
Segmenting retinal vascular net from retinopathy of prematurity images using convolutional neural network
Year:2019
Research Areas
  • Medical computing,
  • Medical images
Information
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.
International
Si
Congress
DATA '19: Proceedings of the Second International Conference on Data Science, E-Learning and Information Systems
960
Place
Reviewers
Si
ISBN/ISSN
978-1-4503-7284-8
https://doi.org/10.1145/3368691.3368711
Start Date
09/12/2019
End Date
12/12/2019
From page
1
To page
5
DATA '19: Proceedings of the Second International Conference on Data Science, E-Learning and Information Systems
Participants
Research Group, Departaments and Institutes related
  • Creador: Grupo de Investigación: Grupo de Informática Biomédica (GIB)
  • Departamento: Lenguajes y Sistemas Informáticos e Ingeniería de Software