A machine-learning approach to retrieving diabetic retinopathy images

Parag S. Chandakkar, Ragav Venkatesan, Baoxin Li, Helen K. Li

Research output: Chapter in Book/Report/Conference proceedingConference contribution

1 Citation (Scopus)

Abstract

Diabetic retinopathy (DR) is a vision-threatening complication that affects people suffering from diabetes. Diagnosis of DR during early stages can significantly reduce the risk of severe vision loss. The process of DR severity grading is prone to human error and it also depends on the expertise of the ophthalmologist. As a result, many researchers have started exploring automated detection and evaluation of diabetic retinal lesions. Unfortunately, to date there is no automated system that can perform DR lesion detection with the accuracy that is comparable to a human expert. In this poster, we present a novel way of employing content-based image retrieval for providing a clinician with instant reference to archival and standardized DR images that are used for assisting the ophthalmologist with the diagnosis of a given DR image. The focus of the poster is on retrieving DR images with two significant DR clinical findings, namely, microaneurysm (MA) and neovascularization (NV). We propose a multi-class multiple-instance DR image retrieval framework that makes use of a modified color correlogram (CC) and statistics of steerable Gaussian filter (SGF) responses. Experiments using real DR images with comparisons to other prior-art methods demonstrate the improved performance of the proposed approach.

Original languageEnglish (US)
Title of host publication2012 ACM Conference on Bioinformatics, Computational Biology and Biomedicine, BCB 2012
Pages588-589
Number of pages2
DOIs
StatePublished - 2012
Event2012 ACM Conference on Bioinformatics, Computational Biology and Biomedicine, BCB 2012 - Orlando, FL, United States
Duration: Oct 7 2012Oct 10 2012

Other

Other2012 ACM Conference on Bioinformatics, Computational Biology and Biomedicine, BCB 2012
CountryUnited States
CityOrlando, FL
Period10/7/1210/10/12

Fingerprint

Image retrieval
Diabetic Retinopathy
Learning systems
Medical problems
Statistics
Color
Posters
Experiments
Machine Learning
Art
Research Personnel

Keywords

  • Color correlogram
  • Diabetic retinopathy
  • Fast radial symmetric transform
  • Image retrieval
  • Multiple-instance learning
  • Steerable Gaussian filters

ASJC Scopus subject areas

  • Biomedical Engineering
  • Health Information Management

Cite this

Chandakkar, P. S., Venkatesan, R., Li, B., & Li, H. K. (2012). A machine-learning approach to retrieving diabetic retinopathy images. In 2012 ACM Conference on Bioinformatics, Computational Biology and Biomedicine, BCB 2012 (pp. 588-589) https://doi.org/10.1145/2382936.2383030

A machine-learning approach to retrieving diabetic retinopathy images. / Chandakkar, Parag S.; Venkatesan, Ragav; Li, Baoxin; Li, Helen K.

2012 ACM Conference on Bioinformatics, Computational Biology and Biomedicine, BCB 2012. 2012. p. 588-589.

Research output: Chapter in Book/Report/Conference proceedingConference contribution

Chandakkar, PS, Venkatesan, R, Li, B & Li, HK 2012, A machine-learning approach to retrieving diabetic retinopathy images. in 2012 ACM Conference on Bioinformatics, Computational Biology and Biomedicine, BCB 2012. pp. 588-589, 2012 ACM Conference on Bioinformatics, Computational Biology and Biomedicine, BCB 2012, Orlando, FL, United States, 10/7/12. https://doi.org/10.1145/2382936.2383030
Chandakkar PS, Venkatesan R, Li B, Li HK. A machine-learning approach to retrieving diabetic retinopathy images. In 2012 ACM Conference on Bioinformatics, Computational Biology and Biomedicine, BCB 2012. 2012. p. 588-589 https://doi.org/10.1145/2382936.2383030
Chandakkar, Parag S. ; Venkatesan, Ragav ; Li, Baoxin ; Li, Helen K. / A machine-learning approach to retrieving diabetic retinopathy images. 2012 ACM Conference on Bioinformatics, Computational Biology and Biomedicine, BCB 2012. 2012. pp. 588-589
@inproceedings{b44b16ca1dbc4f02acf7306128d2c9b2,
title = "A machine-learning approach to retrieving diabetic retinopathy images",
abstract = "Diabetic retinopathy (DR) is a vision-threatening complication that affects people suffering from diabetes. Diagnosis of DR during early stages can significantly reduce the risk of severe vision loss. The process of DR severity grading is prone to human error and it also depends on the expertise of the ophthalmologist. As a result, many researchers have started exploring automated detection and evaluation of diabetic retinal lesions. Unfortunately, to date there is no automated system that can perform DR lesion detection with the accuracy that is comparable to a human expert. In this poster, we present a novel way of employing content-based image retrieval for providing a clinician with instant reference to archival and standardized DR images that are used for assisting the ophthalmologist with the diagnosis of a given DR image. The focus of the poster is on retrieving DR images with two significant DR clinical findings, namely, microaneurysm (MA) and neovascularization (NV). We propose a multi-class multiple-instance DR image retrieval framework that makes use of a modified color correlogram (CC) and statistics of steerable Gaussian filter (SGF) responses. Experiments using real DR images with comparisons to other prior-art methods demonstrate the improved performance of the proposed approach.",
keywords = "Color correlogram, Diabetic retinopathy, Fast radial symmetric transform, Image retrieval, Multiple-instance learning, Steerable Gaussian filters",
author = "Chandakkar, {Parag S.} and Ragav Venkatesan and Baoxin Li and Li, {Helen K.}",
year = "2012",
doi = "10.1145/2382936.2383030",
language = "English (US)",
isbn = "9781450316705",
pages = "588--589",
booktitle = "2012 ACM Conference on Bioinformatics, Computational Biology and Biomedicine, BCB 2012",

}

TY - GEN

T1 - A machine-learning approach to retrieving diabetic retinopathy images

AU - Chandakkar, Parag S.

AU - Venkatesan, Ragav

AU - Li, Baoxin

AU - Li, Helen K.

PY - 2012

Y1 - 2012

N2 - Diabetic retinopathy (DR) is a vision-threatening complication that affects people suffering from diabetes. Diagnosis of DR during early stages can significantly reduce the risk of severe vision loss. The process of DR severity grading is prone to human error and it also depends on the expertise of the ophthalmologist. As a result, many researchers have started exploring automated detection and evaluation of diabetic retinal lesions. Unfortunately, to date there is no automated system that can perform DR lesion detection with the accuracy that is comparable to a human expert. In this poster, we present a novel way of employing content-based image retrieval for providing a clinician with instant reference to archival and standardized DR images that are used for assisting the ophthalmologist with the diagnosis of a given DR image. The focus of the poster is on retrieving DR images with two significant DR clinical findings, namely, microaneurysm (MA) and neovascularization (NV). We propose a multi-class multiple-instance DR image retrieval framework that makes use of a modified color correlogram (CC) and statistics of steerable Gaussian filter (SGF) responses. Experiments using real DR images with comparisons to other prior-art methods demonstrate the improved performance of the proposed approach.

AB - Diabetic retinopathy (DR) is a vision-threatening complication that affects people suffering from diabetes. Diagnosis of DR during early stages can significantly reduce the risk of severe vision loss. The process of DR severity grading is prone to human error and it also depends on the expertise of the ophthalmologist. As a result, many researchers have started exploring automated detection and evaluation of diabetic retinal lesions. Unfortunately, to date there is no automated system that can perform DR lesion detection with the accuracy that is comparable to a human expert. In this poster, we present a novel way of employing content-based image retrieval for providing a clinician with instant reference to archival and standardized DR images that are used for assisting the ophthalmologist with the diagnosis of a given DR image. The focus of the poster is on retrieving DR images with two significant DR clinical findings, namely, microaneurysm (MA) and neovascularization (NV). We propose a multi-class multiple-instance DR image retrieval framework that makes use of a modified color correlogram (CC) and statistics of steerable Gaussian filter (SGF) responses. Experiments using real DR images with comparisons to other prior-art methods demonstrate the improved performance of the proposed approach.

KW - Color correlogram

KW - Diabetic retinopathy

KW - Fast radial symmetric transform

KW - Image retrieval

KW - Multiple-instance learning

KW - Steerable Gaussian filters

UR - http://www.scopus.com/inward/record.url?scp=84869467637&partnerID=8YFLogxK

UR - http://www.scopus.com/inward/citedby.url?scp=84869467637&partnerID=8YFLogxK

U2 - 10.1145/2382936.2383030

DO - 10.1145/2382936.2383030

M3 - Conference contribution

AN - SCOPUS:84869467637

SN - 9781450316705

SP - 588

EP - 589

BT - 2012 ACM Conference on Bioinformatics, Computational Biology and Biomedicine, BCB 2012

ER -