Automated analysis of diabetic retinopathy images: Principles, recent developments, and emerging trends

Baoxin Li, Helen K. Li

Research output: Contribution to journalArticle

12 Citations (Scopus)

Abstract

Diabetic retinopathy (DR) is a vision-threatening complication of diabetes. Timely diagnosis and intervention are essential for treatment that reduces the risk of vision loss. A good color retinal (fundus) photograph can be used as a surrogate for face-to-face evaluation of DR. The use of computers to assist or fully automate DR evaluation from retinal images has been studied for many years. Early work showed promising results for algorithms in detecting and classifying DR pathology. Newer techniques include those that adapt machine learning technology to DR image analysis. Challenges remain, however, that must be overcome before fully automatic DR detection and analysis systems become practical clinical tools.

Original languageEnglish (US)
Pages (from-to)453-459
Number of pages7
JournalCurrent Diabetes Reports
Volume13
Issue number4
DOIs
StatePublished - Aug 2013

Fingerprint

Diabetic Retinopathy
Diabetes Complications
Color
Pathology
Technology

Keywords

  • Computer-aided diagnosis
  • Diabetic retinopathy
  • Fundus photography
  • Image analysis
  • Machine learning

ASJC Scopus subject areas

  • Endocrinology, Diabetes and Metabolism
  • Internal Medicine

Cite this

Automated analysis of diabetic retinopathy images : Principles, recent developments, and emerging trends. / Li, Baoxin; Li, Helen K.

In: Current Diabetes Reports, Vol. 13, No. 4, 08.2013, p. 453-459.

Research output: Contribution to journalArticle

@article{d66974dd7d91411ba7a8c7822c728fa0,
title = "Automated analysis of diabetic retinopathy images: Principles, recent developments, and emerging trends",
abstract = "Diabetic retinopathy (DR) is a vision-threatening complication of diabetes. Timely diagnosis and intervention are essential for treatment that reduces the risk of vision loss. A good color retinal (fundus) photograph can be used as a surrogate for face-to-face evaluation of DR. The use of computers to assist or fully automate DR evaluation from retinal images has been studied for many years. Early work showed promising results for algorithms in detecting and classifying DR pathology. Newer techniques include those that adapt machine learning technology to DR image analysis. Challenges remain, however, that must be overcome before fully automatic DR detection and analysis systems become practical clinical tools.",
keywords = "Computer-aided diagnosis, Diabetic retinopathy, Fundus photography, Image analysis, Machine learning",
author = "Baoxin Li and Li, {Helen K.}",
year = "2013",
month = "8",
doi = "10.1007/s11892-013-0393-9",
language = "English (US)",
volume = "13",
pages = "453--459",
journal = "Current Diabetes Reports",
issn = "1534-4827",
publisher = "Current Medicine Group",
number = "4",

}

TY - JOUR

T1 - Automated analysis of diabetic retinopathy images

T2 - Principles, recent developments, and emerging trends

AU - Li, Baoxin

AU - Li, Helen K.

PY - 2013/8

Y1 - 2013/8

N2 - Diabetic retinopathy (DR) is a vision-threatening complication of diabetes. Timely diagnosis and intervention are essential for treatment that reduces the risk of vision loss. A good color retinal (fundus) photograph can be used as a surrogate for face-to-face evaluation of DR. The use of computers to assist or fully automate DR evaluation from retinal images has been studied for many years. Early work showed promising results for algorithms in detecting and classifying DR pathology. Newer techniques include those that adapt machine learning technology to DR image analysis. Challenges remain, however, that must be overcome before fully automatic DR detection and analysis systems become practical clinical tools.

AB - Diabetic retinopathy (DR) is a vision-threatening complication of diabetes. Timely diagnosis and intervention are essential for treatment that reduces the risk of vision loss. A good color retinal (fundus) photograph can be used as a surrogate for face-to-face evaluation of DR. The use of computers to assist or fully automate DR evaluation from retinal images has been studied for many years. Early work showed promising results for algorithms in detecting and classifying DR pathology. Newer techniques include those that adapt machine learning technology to DR image analysis. Challenges remain, however, that must be overcome before fully automatic DR detection and analysis systems become practical clinical tools.

KW - Computer-aided diagnosis

KW - Diabetic retinopathy

KW - Fundus photography

KW - Image analysis

KW - Machine learning

UR - http://www.scopus.com/inward/record.url?scp=84880132882&partnerID=8YFLogxK

UR - http://www.scopus.com/inward/citedby.url?scp=84880132882&partnerID=8YFLogxK

U2 - 10.1007/s11892-013-0393-9

DO - 10.1007/s11892-013-0393-9

M3 - Article

C2 - 23686810

AN - SCOPUS:84880132882

VL - 13

SP - 453

EP - 459

JO - Current Diabetes Reports

JF - Current Diabetes Reports

SN - 1534-4827

IS - 4

ER -