Automatic system for diabetic retinopathy screening based on AM-FM, partial least squares, and support vector machines

E. Simon Barriga; Victor Murray; Carla Agurto; Marios Pattichis; Wendall Bauman; Gilberto Zamora; Peter Soliz

doi:10.1109/ISBI.2010.5490247

Automatic system for diabetic retinopathy screening based on AM-FM, partial least squares, and support vector machines

E. Simon Barriga
, Victor Murray
, Carla Agurto
, Marios Pattichis
, Wendall Bauman
, Gilberto Zamora
, Peter Soliz

VisionQuest Biomedical
University of New Mexico
Retina Institute of South Texas
University of Iowa Department of Ophthalmology and Visual Sciences

Producción científica: Capítulo del libro/informe/acta de congreso › Contribución a la conferencia › revisión exhaustiva

20 Citas (Scopus)

Resumen

Diabetic retinopathy (DR) is a disease that affects over 170 million people worldwide. In the United States, it is estimated that over 10 million diabetics do not receive the recommended annual eye examinations, significantly increasing their risk of vision loss. In this paper we present an automatic system to detect the presence of DR by analyzing a photograph of the central field of the retina. The system applies Amplitude Modulation-Frequency Modulation (AM-FM) for feature extraction, and partial least squares (PLS) and support vector machines (SVM) for classification. We tested the system on a total of 400 images, and obtained an area under the ROC curve (AUC) of 0.86, and corresponding sensitivity/specificity of 98%/68%. We also tested the accuracy of the system for patients needing immediate referral to a specialist, obtaining an AUC of 0.98.

Idioma original	Inglés
Título de la publicación alojada	2010 7th IEEE International Symposium on Biomedical Imaging
Subtítulo de la publicación alojada	From Nano to Macro, ISBI 2010 - Proceedings
Editorial	IEEE Computer Society
Páginas	1349-1352
Número de páginas	4
ISBN (versión impresa)	9781424441266
DOI	https://doi.org/10.1109/ISBI.2010.5490247
Estado	Publicada - 2010
Publicado de forma externa	Sí
Evento	7th IEEE International Symposium on Biomedical Imaging: From Nano to Macro, ISBI 2010 - Rotterdam, Países Bajos Duración: 14 abr. 2010 → 17 abr. 2010

Serie de la publicación

Nombre	2010 7th IEEE International Symposium on Biomedical Imaging: From Nano to Macro, ISBI 2010 - Proceedings

Conferencia

Conferencia	7th IEEE International Symposium on Biomedical Imaging: From Nano to Macro, ISBI 2010
País/Territorio	Países Bajos
Ciudad	Rotterdam
Período	14/04/10 → 17/04/10

ODS de las Naciones Unidas

Este resultado contribuye a los siguientes Objetivos de Desarrollo Sostenible

ODS 3: Salud y bienestar

Acceder al documento

10.1109/ISBI.2010.5490247

Otros archivos y enlaces

Enlace a la publicación en Scopus

Citar esto

Barriga, E. S., Murray, V., Agurto, C., Pattichis, M., Bauman, W., Zamora, G., & Soliz, P. (2010). Automatic system for diabetic retinopathy screening based on AM-FM, partial least squares, and support vector machines. En 2010 7th IEEE International Symposium on Biomedical Imaging: From Nano to Macro, ISBI 2010 - Proceedings (pp. 1349-1352). Artículo 5490247 (2010 7th IEEE International Symposium on Biomedical Imaging: From Nano to Macro, ISBI 2010 - Proceedings). IEEE Computer Society. https://doi.org/10.1109/ISBI.2010.5490247

Barriga, E. Simon ; Murray, Victor ; Agurto, Carla et al. / Automatic system for diabetic retinopathy screening based on AM-FM, partial least squares, and support vector machines. 2010 7th IEEE International Symposium on Biomedical Imaging: From Nano to Macro, ISBI 2010 - Proceedings. IEEE Computer Society, 2010. pp. 1349-1352 (2010 7th IEEE International Symposium on Biomedical Imaging: From Nano to Macro, ISBI 2010 - Proceedings).

@inproceedings{05bff1dc5cd6489998e15a884f5b6c7c,

title = "Automatic system for diabetic retinopathy screening based on AM-FM, partial least squares, and support vector machines",

abstract = "Diabetic retinopathy (DR) is a disease that affects over 170 million people worldwide. In the United States, it is estimated that over 10 million diabetics do not receive the recommended annual eye examinations, significantly increasing their risk of vision loss. In this paper we present an automatic system to detect the presence of DR by analyzing a photograph of the central field of the retina. The system applies Amplitude Modulation-Frequency Modulation (AM-FM) for feature extraction, and partial least squares (PLS) and support vector machines (SVM) for classification. We tested the system on a total of 400 images, and obtained an area under the ROC curve (AUC) of 0.86, and corresponding sensitivity/specificity of 98\%/68\%. We also tested the accuracy of the system for patients needing immediate referral to a specialist, obtaining an AUC of 0.98.",

keywords = "AM-FM, Amplitude modulation-frequency modulation, Diabetic retinopathy, Partial least squares, Support vector machines",

author = "Barriga, \{E. Simon\} and Victor Murray and Carla Agurto and Marios Pattichis and Wendall Bauman and Gilberto Zamora and Peter Soliz",

year = "2010",

doi = "10.1109/ISBI.2010.5490247",

language = "English",

isbn = "9781424441266",

series = "2010 7th IEEE International Symposium on Biomedical Imaging: From Nano to Macro, ISBI 2010 - Proceedings",

publisher = "IEEE Computer Society",

pages = "1349--1352",

booktitle = "2010 7th IEEE International Symposium on Biomedical Imaging",

note = "7th IEEE International Symposium on Biomedical Imaging: From Nano to Macro, ISBI 2010 ; Conference date: 14-04-2010 Through 17-04-2010",

}

Barriga, ES, Murray, V, Agurto, C, Pattichis, M, Bauman, W, Zamora, G & Soliz, P 2010, Automatic system for diabetic retinopathy screening based on AM-FM, partial least squares, and support vector machines. En 2010 7th IEEE International Symposium on Biomedical Imaging: From Nano to Macro, ISBI 2010 - Proceedings., 5490247, 2010 7th IEEE International Symposium on Biomedical Imaging: From Nano to Macro, ISBI 2010 - Proceedings, IEEE Computer Society, pp. 1349-1352, 7th IEEE International Symposium on Biomedical Imaging: From Nano to Macro, ISBI 2010, Rotterdam, Países Bajos, 14/04/10. https://doi.org/10.1109/ISBI.2010.5490247

Automatic system for diabetic retinopathy screening based on AM-FM, partial least squares, and support vector machines. / Barriga, E. Simon; Murray, Victor; Agurto, Carla et al.
2010 7th IEEE International Symposium on Biomedical Imaging: From Nano to Macro, ISBI 2010 - Proceedings. IEEE Computer Society, 2010. p. 1349-1352 5490247 (2010 7th IEEE International Symposium on Biomedical Imaging: From Nano to Macro, ISBI 2010 - Proceedings).

Producción científica: Capítulo del libro/informe/acta de congreso › Contribución a la conferencia › revisión exhaustiva

TY - GEN

T1 - Automatic system for diabetic retinopathy screening based on AM-FM, partial least squares, and support vector machines

AU - Barriga, E. Simon

AU - Murray, Victor

AU - Agurto, Carla

AU - Pattichis, Marios

AU - Bauman, Wendall

AU - Zamora, Gilberto

AU - Soliz, Peter

PY - 2010

Y1 - 2010

N2 - Diabetic retinopathy (DR) is a disease that affects over 170 million people worldwide. In the United States, it is estimated that over 10 million diabetics do not receive the recommended annual eye examinations, significantly increasing their risk of vision loss. In this paper we present an automatic system to detect the presence of DR by analyzing a photograph of the central field of the retina. The system applies Amplitude Modulation-Frequency Modulation (AM-FM) for feature extraction, and partial least squares (PLS) and support vector machines (SVM) for classification. We tested the system on a total of 400 images, and obtained an area under the ROC curve (AUC) of 0.86, and corresponding sensitivity/specificity of 98%/68%. We also tested the accuracy of the system for patients needing immediate referral to a specialist, obtaining an AUC of 0.98.

AB - Diabetic retinopathy (DR) is a disease that affects over 170 million people worldwide. In the United States, it is estimated that over 10 million diabetics do not receive the recommended annual eye examinations, significantly increasing their risk of vision loss. In this paper we present an automatic system to detect the presence of DR by analyzing a photograph of the central field of the retina. The system applies Amplitude Modulation-Frequency Modulation (AM-FM) for feature extraction, and partial least squares (PLS) and support vector machines (SVM) for classification. We tested the system on a total of 400 images, and obtained an area under the ROC curve (AUC) of 0.86, and corresponding sensitivity/specificity of 98%/68%. We also tested the accuracy of the system for patients needing immediate referral to a specialist, obtaining an AUC of 0.98.

KW - AM-FM

KW - Amplitude modulation-frequency modulation

KW - Diabetic retinopathy

KW - Partial least squares

KW - Support vector machines

UR - https://www.scopus.com/pages/publications/77955210788

U2 - 10.1109/ISBI.2010.5490247

DO - 10.1109/ISBI.2010.5490247

M3 - Conference contribution

AN - SCOPUS:77955210788

SN - 9781424441266

T3 - 2010 7th IEEE International Symposium on Biomedical Imaging: From Nano to Macro, ISBI 2010 - Proceedings

SP - 1349

EP - 1352

BT - 2010 7th IEEE International Symposium on Biomedical Imaging

PB - IEEE Computer Society

T2 - 7th IEEE International Symposium on Biomedical Imaging: From Nano to Macro, ISBI 2010

Y2 - 14 April 2010 through 17 April 2010

ER -

Barriga ES, Murray V, Agurto C, Pattichis M, Bauman W, Zamora G et al. Automatic system for diabetic retinopathy screening based on AM-FM, partial least squares, and support vector machines. En 2010 7th IEEE International Symposium on Biomedical Imaging: From Nano to Macro, ISBI 2010 - Proceedings. IEEE Computer Society. 2010. p. 1349-1352. 5490247. (2010 7th IEEE International Symposium on Biomedical Imaging: From Nano to Macro, ISBI 2010 - Proceedings). doi: 10.1109/ISBI.2010.5490247

Automatic system for diabetic retinopathy screening based on AM-FM, partial least squares, and support vector machines

Resumen

Serie de la publicación

Conferencia

ODS de las Naciones Unidas

Acceder al documento

Otros archivos y enlaces

Huella

Citar esto