Validation of microaneurysm-based diabetic retinopathy screening across retina fundus datasets

L. Giancardo, T. P. Karnowski, K. W. Tobin, F. Meriaudeau, E. Chaum

Research output: Contribution to journalArticle

3 Citations (Scopus)

Abstract

In recent years, automated retina image analysis (ARIA) algorithms have received increasing interest by the medical imaging analysis community. Particular attention has been given to techniques able to automate the pre-screening of Diabetic Retinopathy (DR) using inexpensive retina fundus cameras. With the growing number of diabetics worldwide, these techniques have the potential benefits of broad-based, inexpensive screening. The contribution of this paper is twofold: first, we propose a straightforward pipeline from microaneurysm (an early sign of DR) detection to automatic classification of DR without employing any additional features; then, we quantify the generalisation ability of the MA detection method by employing synthetic examples and, more importantly, we experiment with two public datasets which consist of more than 1,350 images graded as normal or showing signs of DR. With cross-datasets tests, we obtained results better or comparable to other recent methods. Since our experiments are performed only on publicly available datasets, our results are directly comparable with those of other research groups.

Original languageEnglish (US)
Article number6627776
Pages (from-to)125-130
Number of pages6
JournalProceedings of the IEEE Symposium on Computer-Based Medical Systems
StatePublished - 2013

Fingerprint

Diabetic Retinopathy
Retina
Screening
Medical imaging
Image analysis
Pipelines
Experiments
Cameras
Diagnostic Imaging
Microaneurysm
Datasets
Research

All Science Journal Classification (ASJC) codes

  • Computer Science Applications
  • Radiology Nuclear Medicine and imaging

Cite this

Validation of microaneurysm-based diabetic retinopathy screening across retina fundus datasets. / Giancardo, L.; Karnowski, T. P.; Tobin, K. W.; Meriaudeau, F.; Chaum, E.

In: Proceedings of the IEEE Symposium on Computer-Based Medical Systems, 2013, p. 125-130.

Research output: Contribution to journalArticle

@article{a8e9e0bac5114ba784ad65f5db814fad,
title = "Validation of microaneurysm-based diabetic retinopathy screening across retina fundus datasets",
abstract = "In recent years, automated retina image analysis (ARIA) algorithms have received increasing interest by the medical imaging analysis community. Particular attention has been given to techniques able to automate the pre-screening of Diabetic Retinopathy (DR) using inexpensive retina fundus cameras. With the growing number of diabetics worldwide, these techniques have the potential benefits of broad-based, inexpensive screening. The contribution of this paper is twofold: first, we propose a straightforward pipeline from microaneurysm (an early sign of DR) detection to automatic classification of DR without employing any additional features; then, we quantify the generalisation ability of the MA detection method by employing synthetic examples and, more importantly, we experiment with two public datasets which consist of more than 1,350 images graded as normal or showing signs of DR. With cross-datasets tests, we obtained results better or comparable to other recent methods. Since our experiments are performed only on publicly available datasets, our results are directly comparable with those of other research groups.",
author = "L. Giancardo and Karnowski, {T. P.} and Tobin, {K. W.} and F. Meriaudeau and E. Chaum",
year = "2013",
language = "English (US)",
pages = "125--130",
journal = "Proceedings of the IEEE Symposium on Computer-Based Medical Systems",
issn = "1063-7125",
publisher = "Institute of Electrical and Electronics Engineers Inc.",

}

TY - JOUR

T1 - Validation of microaneurysm-based diabetic retinopathy screening across retina fundus datasets

AU - Giancardo, L.

AU - Karnowski, T. P.

AU - Tobin, K. W.

AU - Meriaudeau, F.

AU - Chaum, E.

PY - 2013

Y1 - 2013

N2 - In recent years, automated retina image analysis (ARIA) algorithms have received increasing interest by the medical imaging analysis community. Particular attention has been given to techniques able to automate the pre-screening of Diabetic Retinopathy (DR) using inexpensive retina fundus cameras. With the growing number of diabetics worldwide, these techniques have the potential benefits of broad-based, inexpensive screening. The contribution of this paper is twofold: first, we propose a straightforward pipeline from microaneurysm (an early sign of DR) detection to automatic classification of DR without employing any additional features; then, we quantify the generalisation ability of the MA detection method by employing synthetic examples and, more importantly, we experiment with two public datasets which consist of more than 1,350 images graded as normal or showing signs of DR. With cross-datasets tests, we obtained results better or comparable to other recent methods. Since our experiments are performed only on publicly available datasets, our results are directly comparable with those of other research groups.

AB - In recent years, automated retina image analysis (ARIA) algorithms have received increasing interest by the medical imaging analysis community. Particular attention has been given to techniques able to automate the pre-screening of Diabetic Retinopathy (DR) using inexpensive retina fundus cameras. With the growing number of diabetics worldwide, these techniques have the potential benefits of broad-based, inexpensive screening. The contribution of this paper is twofold: first, we propose a straightforward pipeline from microaneurysm (an early sign of DR) detection to automatic classification of DR without employing any additional features; then, we quantify the generalisation ability of the MA detection method by employing synthetic examples and, more importantly, we experiment with two public datasets which consist of more than 1,350 images graded as normal or showing signs of DR. With cross-datasets tests, we obtained results better or comparable to other recent methods. Since our experiments are performed only on publicly available datasets, our results are directly comparable with those of other research groups.

UR - http://www.scopus.com/inward/record.url?scp=84897036726&partnerID=8YFLogxK

UR - http://www.scopus.com/inward/citedby.url?scp=84897036726&partnerID=8YFLogxK

M3 - Article

SP - 125

EP - 130

JO - Proceedings of the IEEE Symposium on Computer-Based Medical Systems

JF - Proceedings of the IEEE Symposium on Computer-Based Medical Systems

SN - 1063-7125

M1 - 6627776

ER -