Diabetic Retinopathy Grade and Macular Edema Risk Classification Using Convolutional Neural Networks

Jia He; Linlin Shen; Xingfang Ai; Xuechen Li

doi:10.1109/ICPICS47731.2019.8942426

Diabetic Retinopathy Grade and Macular Edema Risk Classification Using Convolutional Neural Networks

Jia He
, Linlin Shen
, Xingfang Ai
, Xuechen Li

Research output: Chapter in Book/Conference proceeding › Conference contribution › peer-review

17 Citations (Scopus)

Abstract

Diabetic retinopathy (DR) is one of the major causes of blindness in the western world. Effective treatment of DR is available, when detected early enough, which makes this a vital process. Computers are able to obtain much quicker classifications once trained, giving the ability to aid clinicians in real-time classification. This work employed a deep convolutional neural network (CNN) based method for diabetic retinopathy classification. Three independent CNNs were employed for the classification of DR grade, macular edema risk and multi-label, which included the combination of both grade and risk classes. A fusion method was used to combine all features extracted by the CNNs and make the final classification result. The classification accuracy of the grade and risk were 0.65 and 0.72, respectively. The classification results showed the proposed network fusion method can improve the performances on both task - DR grading and macular edema risk.

Original language	English
Title of host publication	2019 IEEE International Conference on Power, Intelligent Computing and Systems, ICPICS 2019
Publisher	Institute of Electrical and Electronics Engineers Inc.
Pages	463-466
Number of pages	4
ISBN (Electronic)	9781728137209
DOIs	https://doi.org/10.1109/ICPICS47731.2019.8942426
Publication status	Published - Jul 2019
Externally published	Yes
Event	2019 IEEE International Conference on Power, Intelligent Computing and Systems, ICPICS 2019 - Shenyang, China Duration: 12 Jul 2019 → 14 Jul 2019

Publication series

Name	2019 IEEE International Conference on Power, Intelligent Computing and Systems, ICPICS 2019

Conference

Conference	2019 IEEE International Conference on Power, Intelligent Computing and Systems, ICPICS 2019
Country/Territory	China
City	Shenyang
Period	12/07/19 → 14/07/19

UN SDGs

This output contributes to the following UN Sustainable Development Goals (SDGs)

SDG 3 Good Health and Well-being
SDG 7 Affordable and Clean Energy

Free Keywords

Diabetic Retinopathy Severity
Risk of Diabetic Macular Edema
deep learning
fundus image
multi-CNNs

ASJC Scopus subject areas

Artificial Intelligence
Computer Networks and Communications
Information Systems
Information Systems and Management
Energy Engineering and Power Technology
Renewable Energy, Sustainability and the Environment

Access to Document

10.1109/ICPICS47731.2019.8942426

Cite this

He, J., Shen, L., Ai, X., & Li, X. (2019). Diabetic Retinopathy Grade and Macular Edema Risk Classification Using Convolutional Neural Networks. In 2019 IEEE International Conference on Power, Intelligent Computing and Systems, ICPICS 2019 (pp. 463-466). Article 8942426 (2019 IEEE International Conference on Power, Intelligent Computing and Systems, ICPICS 2019). Institute of Electrical and Electronics Engineers Inc.. https://doi.org/10.1109/ICPICS47731.2019.8942426

He, Jia ; Shen, Linlin ; Ai, Xingfang et al. / Diabetic Retinopathy Grade and Macular Edema Risk Classification Using Convolutional Neural Networks. 2019 IEEE International Conference on Power, Intelligent Computing and Systems, ICPICS 2019. Institute of Electrical and Electronics Engineers Inc., 2019. pp. 463-466 (2019 IEEE International Conference on Power, Intelligent Computing and Systems, ICPICS 2019).

@inproceedings{d203f0eeec7645d9ac9d5eecbe60c430,

title = "Diabetic Retinopathy Grade and Macular Edema Risk Classification Using Convolutional Neural Networks",

abstract = "Diabetic retinopathy (DR) is one of the major causes of blindness in the western world. Effective treatment of DR is available, when detected early enough, which makes this a vital process. Computers are able to obtain much quicker classifications once trained, giving the ability to aid clinicians in real-time classification. This work employed a deep convolutional neural network (CNN) based method for diabetic retinopathy classification. Three independent CNNs were employed for the classification of DR grade, macular edema risk and multi-label, which included the combination of both grade and risk classes. A fusion method was used to combine all features extracted by the CNNs and make the final classification result. The classification accuracy of the grade and risk were 0.65 and 0.72, respectively. The classification results showed the proposed network fusion method can improve the performances on both task - DR grading and macular edema risk.",

keywords = "Diabetic Retinopathy Severity, Risk of Diabetic Macular Edema, deep learning, fundus image, multi-CNNs",

author = "Jia He and Linlin Shen and Xingfang Ai and Xuechen Li",

note = "Publisher Copyright: {\textcopyright} 2019 IEEE.; 2019 IEEE International Conference on Power, Intelligent Computing and Systems, ICPICS 2019 ; Conference date: 12-07-2019 Through 14-07-2019",

year = "2019",

month = jul,

doi = "10.1109/ICPICS47731.2019.8942426",

language = "English",

series = "2019 IEEE International Conference on Power, Intelligent Computing and Systems, ICPICS 2019",

publisher = "Institute of Electrical and Electronics Engineers Inc.",

pages = "463--466",

booktitle = "2019 IEEE International Conference on Power, Intelligent Computing and Systems, ICPICS 2019",

address = "United States",

}

He, J, Shen, L, Ai, X & Li, X 2019, Diabetic Retinopathy Grade and Macular Edema Risk Classification Using Convolutional Neural Networks. in 2019 IEEE International Conference on Power, Intelligent Computing and Systems, ICPICS 2019., 8942426, 2019 IEEE International Conference on Power, Intelligent Computing and Systems, ICPICS 2019, Institute of Electrical and Electronics Engineers Inc., pp. 463-466, 2019 IEEE International Conference on Power, Intelligent Computing and Systems, ICPICS 2019, Shenyang, China, 12/07/19. https://doi.org/10.1109/ICPICS47731.2019.8942426

Diabetic Retinopathy Grade and Macular Edema Risk Classification Using Convolutional Neural Networks. / He, Jia; Shen, Linlin; Ai, Xingfang et al.
2019 IEEE International Conference on Power, Intelligent Computing and Systems, ICPICS 2019. Institute of Electrical and Electronics Engineers Inc., 2019. p. 463-466 8942426 (2019 IEEE International Conference on Power, Intelligent Computing and Systems, ICPICS 2019).

Research output: Chapter in Book/Conference proceeding › Conference contribution › peer-review

TY - GEN

T1 - Diabetic Retinopathy Grade and Macular Edema Risk Classification Using Convolutional Neural Networks

AU - He, Jia

AU - Shen, Linlin

AU - Ai, Xingfang

AU - Li, Xuechen

PY - 2019/7

Y1 - 2019/7

N2 - Diabetic retinopathy (DR) is one of the major causes of blindness in the western world. Effective treatment of DR is available, when detected early enough, which makes this a vital process. Computers are able to obtain much quicker classifications once trained, giving the ability to aid clinicians in real-time classification. This work employed a deep convolutional neural network (CNN) based method for diabetic retinopathy classification. Three independent CNNs were employed for the classification of DR grade, macular edema risk and multi-label, which included the combination of both grade and risk classes. A fusion method was used to combine all features extracted by the CNNs and make the final classification result. The classification accuracy of the grade and risk were 0.65 and 0.72, respectively. The classification results showed the proposed network fusion method can improve the performances on both task - DR grading and macular edema risk.

AB - Diabetic retinopathy (DR) is one of the major causes of blindness in the western world. Effective treatment of DR is available, when detected early enough, which makes this a vital process. Computers are able to obtain much quicker classifications once trained, giving the ability to aid clinicians in real-time classification. This work employed a deep convolutional neural network (CNN) based method for diabetic retinopathy classification. Three independent CNNs were employed for the classification of DR grade, macular edema risk and multi-label, which included the combination of both grade and risk classes. A fusion method was used to combine all features extracted by the CNNs and make the final classification result. The classification accuracy of the grade and risk were 0.65 and 0.72, respectively. The classification results showed the proposed network fusion method can improve the performances on both task - DR grading and macular edema risk.

KW - Diabetic Retinopathy Severity

KW - Risk of Diabetic Macular Edema

KW - deep learning

KW - fundus image

KW - multi-CNNs

UR - https://www.scopus.com/pages/publications/85077957832

U2 - 10.1109/ICPICS47731.2019.8942426

DO - 10.1109/ICPICS47731.2019.8942426

M3 - Conference contribution

AN - SCOPUS:85077957832

T3 - 2019 IEEE International Conference on Power, Intelligent Computing and Systems, ICPICS 2019

SP - 463

EP - 466

BT - 2019 IEEE International Conference on Power, Intelligent Computing and Systems, ICPICS 2019

PB - Institute of Electrical and Electronics Engineers Inc.

T2 - 2019 IEEE International Conference on Power, Intelligent Computing and Systems, ICPICS 2019

Y2 - 12 July 2019 through 14 July 2019

ER -

He J, Shen L, Ai X, Li X. Diabetic Retinopathy Grade and Macular Edema Risk Classification Using Convolutional Neural Networks. In 2019 IEEE International Conference on Power, Intelligent Computing and Systems, ICPICS 2019. Institute of Electrical and Electronics Engineers Inc. 2019. p. 463-466. 8942426. (2019 IEEE International Conference on Power, Intelligent Computing and Systems, ICPICS 2019). doi: 10.1109/ICPICS47731.2019.8942426

Diabetic Retinopathy Grade and Macular Edema Risk Classification Using Convolutional Neural Networks

Abstract

Publication series

Conference

UN SDGs

Free Keywords

ASJC Scopus subject areas

Access to Document

Other files and links

Fingerprint

Cite this