Segmenting retinal vascular net from retinopathy of prematurity images using convolutional neural network

Monserrate Intriago-Pazmiño; Julio Ibarra-Fiallo; Raúl Alonso-Calvo; José Crespo

doi:10.1145/3368691.3368711

Segmenting retinal vascular net from retinopathy of prematurity images using convolutional neural network

Monserrate Intriago-Pazmiño
, Julio Ibarra-Fiallo
, Raúl Alonso-Calvo
, José Crespo

Matemáticas

Escuela Politecnica Nacional
Technical University of Madrid

Research output: Chapter in Book/Report/Conference proceeding › Conference contribution › peer-review

1 Scopus citations

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.

Original language	English
Title of host publication	Proceedings of the 2nd International Conference on Data Science, E-Learning and Information Systems, DATA 2019
Publisher	Association for Computing Machinery
ISBN (Electronic)	9781450372848
DOIs	https://doi.org/10.1145/3368691.3368711
State	Published - 2 Dec 2019
Event	2nd International Conference on Data Science, E-Learning and Information Systems, DATA 2019 - Dubai, United Arab Emirates Duration: 2 Dec 2019 → 5 Dec 2019

Publication series

Name	ACM International Conference Proceeding Series

Conference

Conference	2nd International Conference on Data Science, E-Learning and Information Systems, DATA 2019
Country/Territory	United Arab Emirates
City	Dubai
Period	2/12/19 → 5/12/19

Keywords

Convolutional neural network
Medical image processing
Retinopathy of Prematurity

Access to Document

10.1145/3368691.3368711

Cite this

Intriago-Pazmiño, M., Ibarra-Fiallo, J., Alonso-Calvo, R., & Crespo, J. (2019). Segmenting retinal vascular net from retinopathy of prematurity images using convolutional neural network. In Proceedings of the 2nd International Conference on Data Science, E-Learning and Information Systems, DATA 2019 Article a20 (ACM International Conference Proceeding Series). Association for Computing Machinery. https://doi.org/10.1145/3368691.3368711

Intriago-Pazmiño, Monserrate ; Ibarra-Fiallo, Julio ; Alonso-Calvo, Raúl et al. / Segmenting retinal vascular net from retinopathy of prematurity images using convolutional neural network. Proceedings of the 2nd International Conference on Data Science, E-Learning and Information Systems, DATA 2019. Association for Computing Machinery, 2019. (ACM International Conference Proceeding Series).

@inproceedings{85cc6b0d3a1743ae9b63c9f4d9ef4e65,

title = "Segmenting retinal vascular net from retinopathy of prematurity images using convolutional neural network",

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.",

keywords = "Convolutional neural network, Medical image processing, Retinopathy of Prematurity",

author = "Monserrate Intriago-Pazmi{\~n}o and Julio Ibarra-Fiallo and Ra{\'u}l Alonso-Calvo and Jos{\'e} Crespo",

note = "Publisher Copyright: {\textcopyright} 2019 Association for Computing Machinery. ACM; 2nd International Conference on Data Science, E-Learning and Information Systems, DATA 2019 ; Conference date: 02-12-2019 Through 05-12-2019",

year = "2019",

month = dec,

day = "2",

doi = "10.1145/3368691.3368711",

language = "Ingl{\'e}s",

series = "ACM International Conference Proceeding Series",

publisher = "Association for Computing Machinery",

booktitle = "Proceedings of the 2nd International Conference on Data Science, E-Learning and Information Systems, DATA 2019",

}

Intriago-Pazmiño, M, Ibarra-Fiallo, J, Alonso-Calvo, R & Crespo, J 2019, Segmenting retinal vascular net from retinopathy of prematurity images using convolutional neural network. in Proceedings of the 2nd International Conference on Data Science, E-Learning and Information Systems, DATA 2019., a20, ACM International Conference Proceeding Series, Association for Computing Machinery, 2nd International Conference on Data Science, E-Learning and Information Systems, DATA 2019, Dubai, United Arab Emirates, 2/12/19. https://doi.org/10.1145/3368691.3368711

Segmenting retinal vascular net from retinopathy of prematurity images using convolutional neural network. / Intriago-Pazmiño, Monserrate; Ibarra-Fiallo, Julio; Alonso-Calvo, Raúl et al.
Proceedings of the 2nd International Conference on Data Science, E-Learning and Information Systems, DATA 2019. Association for Computing Machinery, 2019. a20 (ACM International Conference Proceeding Series).

Research output: Chapter in Book/Report/Conference proceeding › Conference contribution › peer-review

TY - GEN

T1 - Segmenting retinal vascular net from retinopathy of prematurity images using convolutional neural network

AU - Intriago-Pazmiño, Monserrate

AU - Ibarra-Fiallo, Julio

AU - Alonso-Calvo, Raúl

AU - Crespo, José

PY - 2019/12/2

Y1 - 2019/12/2

N2 - 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.

AB - 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.

KW - Convolutional neural network

KW - Medical image processing

KW - Retinopathy of Prematurity

UR - https://www.scopus.com/pages/publications/85077118260

U2 - 10.1145/3368691.3368711

DO - 10.1145/3368691.3368711

M3 - Contribución a la conferencia

AN - SCOPUS:85077118260

T3 - ACM International Conference Proceeding Series

BT - Proceedings of the 2nd International Conference on Data Science, E-Learning and Information Systems, DATA 2019

PB - Association for Computing Machinery

T2 - 2nd International Conference on Data Science, E-Learning and Information Systems, DATA 2019

Y2 - 2 December 2019 through 5 December 2019

ER -

Intriago-Pazmiño M, Ibarra-Fiallo J, Alonso-Calvo R, Crespo J. Segmenting retinal vascular net from retinopathy of prematurity images using convolutional neural network. In Proceedings of the 2nd International Conference on Data Science, E-Learning and Information Systems, DATA 2019. Association for Computing Machinery. 2019. a20. (ACM International Conference Proceeding Series). doi: 10.1145/3368691.3368711

Segmenting retinal vascular net from retinopathy of prematurity images using convolutional neural network

Abstract

Publication series

Conference

Keywords

Access to Document

Other files and links

Fingerprint

Cite this