Fundus image classification for diabetic retinopathy using disease severity grading

Aiki Sakaguchi, Renjie Wu, Seiichiro Kamata

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

Abstract

Diabetic Retinopathy (DR) is ranked at the top of blindness causes. It progresses without subjective symptoms and leads to blindness in the worst case. However early detections and proper treatments can prevent visual disturbance. Because it takes time and cost for diagnoses by clinicians, research and development of diagnostic support systems has actively been conducted. This research aims to establish a fundus image classification method based on disease severity assessment for a diagnostic support by a fundus image analysis. In this paper, we propose a Graph Neural Network (GNN)-based method to improve accuracy for severity classification. Our method has two features. The first is to extract Region-Of-Interest (ROI) sub-images focusing on regions locally capturing lesions in order to minimize background noise in image preprocessing for the classification. The second is to utilize the GNN which is not yet applied for fundus image classification. In order to evaluate our proposed method, we use Indian Diabetic Retinopathy Image Dataset (IDRiD) utilized in "Diabetic Retinopathy: Segmentation and Grading Challenge" on Biomedical Imaging held at the IEEE International Symposium in 2018. We verified that the accuracy of our method improved 2.9% over the conventional method in this contest.

Original languageEnglish
Title of host publicationProceedings of the 2019 9th International Conference on Biomedical Engineering and Technology, ICBET 2019
PublisherAssociation for Computing Machinery
Pages190-196
Number of pages7
ISBN (Electronic)9781450361309
DOIs
Publication statusPublished - 2019 Mar 28
Event9th International Conference on Biomedical Engineering and Technology, ICBET 2019 - Tokyo, Japan
Duration: 2019 Mar 282019 Mar 30

Publication series

NameACM International Conference Proceeding Series

Conference

Conference9th International Conference on Biomedical Engineering and Technology, ICBET 2019
CountryJapan
CityTokyo
Period19/3/2819/3/30

Fingerprint

Image classification
Neural networks
Image analysis
Imaging techniques
Costs

Keywords

  • Diabetic retinopathy
  • Graph neural network
  • Sparse graph

ASJC Scopus subject areas

  • Computer Networks and Communications
  • Computer Vision and Pattern Recognition
  • Human-Computer Interaction
  • Software

Cite this

Sakaguchi, A., Wu, R., & Kamata, S. (2019). Fundus image classification for diabetic retinopathy using disease severity grading. In Proceedings of the 2019 9th International Conference on Biomedical Engineering and Technology, ICBET 2019 (pp. 190-196). (ACM International Conference Proceeding Series). Association for Computing Machinery. https://doi.org/10.1145/3326172.3326198

Fundus image classification for diabetic retinopathy using disease severity grading. / Sakaguchi, Aiki; Wu, Renjie; Kamata, Seiichiro.

Proceedings of the 2019 9th International Conference on Biomedical Engineering and Technology, ICBET 2019. Association for Computing Machinery, 2019. p. 190-196 (ACM International Conference Proceeding Series).

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

Sakaguchi, A, Wu, R & Kamata, S 2019, Fundus image classification for diabetic retinopathy using disease severity grading. in Proceedings of the 2019 9th International Conference on Biomedical Engineering and Technology, ICBET 2019. ACM International Conference Proceeding Series, Association for Computing Machinery, pp. 190-196, 9th International Conference on Biomedical Engineering and Technology, ICBET 2019, Tokyo, Japan, 19/3/28. https://doi.org/10.1145/3326172.3326198
Sakaguchi A, Wu R, Kamata S. Fundus image classification for diabetic retinopathy using disease severity grading. In Proceedings of the 2019 9th International Conference on Biomedical Engineering and Technology, ICBET 2019. Association for Computing Machinery. 2019. p. 190-196. (ACM International Conference Proceeding Series). https://doi.org/10.1145/3326172.3326198
Sakaguchi, Aiki ; Wu, Renjie ; Kamata, Seiichiro. / Fundus image classification for diabetic retinopathy using disease severity grading. Proceedings of the 2019 9th International Conference on Biomedical Engineering and Technology, ICBET 2019. Association for Computing Machinery, 2019. pp. 190-196 (ACM International Conference Proceeding Series).
@inproceedings{6636adab15af4e4e8281d4600585429f,
title = "Fundus image classification for diabetic retinopathy using disease severity grading",
abstract = "Diabetic Retinopathy (DR) is ranked at the top of blindness causes. It progresses without subjective symptoms and leads to blindness in the worst case. However early detections and proper treatments can prevent visual disturbance. Because it takes time and cost for diagnoses by clinicians, research and development of diagnostic support systems has actively been conducted. This research aims to establish a fundus image classification method based on disease severity assessment for a diagnostic support by a fundus image analysis. In this paper, we propose a Graph Neural Network (GNN)-based method to improve accuracy for severity classification. Our method has two features. The first is to extract Region-Of-Interest (ROI) sub-images focusing on regions locally capturing lesions in order to minimize background noise in image preprocessing for the classification. The second is to utilize the GNN which is not yet applied for fundus image classification. In order to evaluate our proposed method, we use Indian Diabetic Retinopathy Image Dataset (IDRiD) utilized in {"}Diabetic Retinopathy: Segmentation and Grading Challenge{"} on Biomedical Imaging held at the IEEE International Symposium in 2018. We verified that the accuracy of our method improved 2.9{\%} over the conventional method in this contest.",
keywords = "Diabetic retinopathy, Graph neural network, Sparse graph",
author = "Aiki Sakaguchi and Renjie Wu and Seiichiro Kamata",
year = "2019",
month = "3",
day = "28",
doi = "10.1145/3326172.3326198",
language = "English",
series = "ACM International Conference Proceeding Series",
publisher = "Association for Computing Machinery",
pages = "190--196",
booktitle = "Proceedings of the 2019 9th International Conference on Biomedical Engineering and Technology, ICBET 2019",

}

TY - GEN

T1 - Fundus image classification for diabetic retinopathy using disease severity grading

AU - Sakaguchi, Aiki

AU - Wu, Renjie

AU - Kamata, Seiichiro

PY - 2019/3/28

Y1 - 2019/3/28

N2 - Diabetic Retinopathy (DR) is ranked at the top of blindness causes. It progresses without subjective symptoms and leads to blindness in the worst case. However early detections and proper treatments can prevent visual disturbance. Because it takes time and cost for diagnoses by clinicians, research and development of diagnostic support systems has actively been conducted. This research aims to establish a fundus image classification method based on disease severity assessment for a diagnostic support by a fundus image analysis. In this paper, we propose a Graph Neural Network (GNN)-based method to improve accuracy for severity classification. Our method has two features. The first is to extract Region-Of-Interest (ROI) sub-images focusing on regions locally capturing lesions in order to minimize background noise in image preprocessing for the classification. The second is to utilize the GNN which is not yet applied for fundus image classification. In order to evaluate our proposed method, we use Indian Diabetic Retinopathy Image Dataset (IDRiD) utilized in "Diabetic Retinopathy: Segmentation and Grading Challenge" on Biomedical Imaging held at the IEEE International Symposium in 2018. We verified that the accuracy of our method improved 2.9% over the conventional method in this contest.

AB - Diabetic Retinopathy (DR) is ranked at the top of blindness causes. It progresses without subjective symptoms and leads to blindness in the worst case. However early detections and proper treatments can prevent visual disturbance. Because it takes time and cost for diagnoses by clinicians, research and development of diagnostic support systems has actively been conducted. This research aims to establish a fundus image classification method based on disease severity assessment for a diagnostic support by a fundus image analysis. In this paper, we propose a Graph Neural Network (GNN)-based method to improve accuracy for severity classification. Our method has two features. The first is to extract Region-Of-Interest (ROI) sub-images focusing on regions locally capturing lesions in order to minimize background noise in image preprocessing for the classification. The second is to utilize the GNN which is not yet applied for fundus image classification. In order to evaluate our proposed method, we use Indian Diabetic Retinopathy Image Dataset (IDRiD) utilized in "Diabetic Retinopathy: Segmentation and Grading Challenge" on Biomedical Imaging held at the IEEE International Symposium in 2018. We verified that the accuracy of our method improved 2.9% over the conventional method in this contest.

KW - Diabetic retinopathy

KW - Graph neural network

KW - Sparse graph

UR - http://www.scopus.com/inward/record.url?scp=85069168349&partnerID=8YFLogxK

UR - http://www.scopus.com/inward/citedby.url?scp=85069168349&partnerID=8YFLogxK

U2 - 10.1145/3326172.3326198

DO - 10.1145/3326172.3326198

M3 - Conference contribution

AN - SCOPUS:85069168349

T3 - ACM International Conference Proceeding Series

SP - 190

EP - 196

BT - Proceedings of the 2019 9th International Conference on Biomedical Engineering and Technology, ICBET 2019

PB - Association for Computing Machinery

ER -