Classification of diabetic retinopathy and normal retinal images using CNN and SVM

Dinial Utami Nurul Qomariah; Handayani Tjandrasa; Chastine Fatichah

doi:10.1109/ICTS.2019.8850940

Classification of diabetic retinopathy and normal retinal images using CNN and SVM

Dinial Utami Nurul Qomariah
, Handayani Tjandrasa
, Chastine Fatichah

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

104 Citations (Scopus)

Abstract

Diabetic retinopathy is a disease caused by chronic diabetes and can cause blindness. Therefore early detection of diabetic retinopathy is essential to prevent the increased severity. An automated system can help detect diabetic retinopathy quickly for determining the follow-up treatment to avoid further damage to the retina. This study proposes a deep learning method for extracting features and classification using a support vector machine. We use the high-level features of the last fully connected layer based on transfer learning from Convolutional Neural Network (CNN) as the input features for classification using the support vector machine (SVM). This method reduces the computation time required by the classification process using CNN with fine-tuning. The proposed method is tested using 77 and 70 retinal images from Messidor database of base 12 and base 13 respectively. From the results of the experiments, the highest accuracy values are 95.83% and 95.24% for base 12 and base 13 respectively.

Original language	English
Title of host publication	Proceedings of 2019 International Conference on Information and Communication Technology and Systems, ICTS 2019
Publisher	Institute of Electrical and Electronics Engineers Inc.
Pages	152-157
Number of pages	6
ISBN (Electronic)	9781728121338
DOIs	https://doi.org/10.1109/ICTS.2019.8850940
Publication status	Published - Jul 2019
Event	12th International Conference on Information and Communication Technology and Systems, ICTS 2019 - Surabaya, Indonesia Duration: 18 Jul 2019 → …

Publication series

Name	Proceedings of 2019 International Conference on Information and Communication Technology and Systems, ICTS 2019

Conference

Conference	12th International Conference on Information and Communication Technology and Systems, ICTS 2019
Country/Territory	Indonesia
City	Surabaya
Period	18/07/19 → …

UN SDGs

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

SDG 3 Good Health and Well-being

Keywords

CNN
Diabetic Retinopathy
Retinal Fundus Images
SVM
Transfer Learning

Access to Document

10.1109/ICTS.2019.8850940

Cite this

Qomariah, D. U. N., Tjandrasa, H., & Fatichah, C. (2019). Classification of diabetic retinopathy and normal retinal images using CNN and SVM. In Proceedings of 2019 International Conference on Information and Communication Technology and Systems, ICTS 2019 (pp. 152-157). Article 8850940 (Proceedings of 2019 International Conference on Information and Communication Technology and Systems, ICTS 2019). Institute of Electrical and Electronics Engineers Inc.. https://doi.org/10.1109/ICTS.2019.8850940

Qomariah, Dinial Utami Nurul ; Tjandrasa, Handayani ; Fatichah, Chastine. / Classification of diabetic retinopathy and normal retinal images using CNN and SVM. Proceedings of 2019 International Conference on Information and Communication Technology and Systems, ICTS 2019. Institute of Electrical and Electronics Engineers Inc., 2019. pp. 152-157 (Proceedings of 2019 International Conference on Information and Communication Technology and Systems, ICTS 2019).

@inproceedings{1064b3030e4b41d4a2c7ecef4d9670dd,

title = "Classification of diabetic retinopathy and normal retinal images using CNN and SVM",

abstract = "Diabetic retinopathy is a disease caused by chronic diabetes and can cause blindness. Therefore early detection of diabetic retinopathy is essential to prevent the increased severity. An automated system can help detect diabetic retinopathy quickly for determining the follow-up treatment to avoid further damage to the retina. This study proposes a deep learning method for extracting features and classification using a support vector machine. We use the high-level features of the last fully connected layer based on transfer learning from Convolutional Neural Network (CNN) as the input features for classification using the support vector machine (SVM). This method reduces the computation time required by the classification process using CNN with fine-tuning. The proposed method is tested using 77 and 70 retinal images from Messidor database of base 12 and base 13 respectively. From the results of the experiments, the highest accuracy values are 95.83\% and 95.24\% for base 12 and base 13 respectively.",

keywords = "CNN, Diabetic Retinopathy, Retinal Fundus Images, SVM, Transfer Learning",

author = "Qomariah, \{Dinial Utami Nurul\} and Handayani Tjandrasa and Chastine Fatichah",

note = "Publisher Copyright: {\textcopyright} 2019 IEEE.; 12th International Conference on Information and Communication Technology and Systems, ICTS 2019 ; Conference date: 18-07-2019",

year = "2019",

month = jul,

doi = "10.1109/ICTS.2019.8850940",

language = "English",

series = "Proceedings of 2019 International Conference on Information and Communication Technology and Systems, ICTS 2019",

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

pages = "152--157",

booktitle = "Proceedings of 2019 International Conference on Information and Communication Technology and Systems, ICTS 2019",

address = "United States",

}

Qomariah, DUN, Tjandrasa, H & Fatichah, C 2019, Classification of diabetic retinopathy and normal retinal images using CNN and SVM. in Proceedings of 2019 International Conference on Information and Communication Technology and Systems, ICTS 2019., 8850940, Proceedings of 2019 International Conference on Information and Communication Technology and Systems, ICTS 2019, Institute of Electrical and Electronics Engineers Inc., pp. 152-157, 12th International Conference on Information and Communication Technology and Systems, ICTS 2019, Surabaya, Indonesia, 18/07/19. https://doi.org/10.1109/ICTS.2019.8850940

Classification of diabetic retinopathy and normal retinal images using CNN and SVM. / Qomariah, Dinial Utami Nurul; Tjandrasa, Handayani; Fatichah, Chastine.
Proceedings of 2019 International Conference on Information and Communication Technology and Systems, ICTS 2019. Institute of Electrical and Electronics Engineers Inc., 2019. p. 152-157 8850940 (Proceedings of 2019 International Conference on Information and Communication Technology and Systems, ICTS 2019).

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

TY - GEN

T1 - Classification of diabetic retinopathy and normal retinal images using CNN and SVM

AU - Qomariah, Dinial Utami Nurul

AU - Tjandrasa, Handayani

AU - Fatichah, Chastine

PY - 2019/7

Y1 - 2019/7

N2 - Diabetic retinopathy is a disease caused by chronic diabetes and can cause blindness. Therefore early detection of diabetic retinopathy is essential to prevent the increased severity. An automated system can help detect diabetic retinopathy quickly for determining the follow-up treatment to avoid further damage to the retina. This study proposes a deep learning method for extracting features and classification using a support vector machine. We use the high-level features of the last fully connected layer based on transfer learning from Convolutional Neural Network (CNN) as the input features for classification using the support vector machine (SVM). This method reduces the computation time required by the classification process using CNN with fine-tuning. The proposed method is tested using 77 and 70 retinal images from Messidor database of base 12 and base 13 respectively. From the results of the experiments, the highest accuracy values are 95.83% and 95.24% for base 12 and base 13 respectively.

AB - Diabetic retinopathy is a disease caused by chronic diabetes and can cause blindness. Therefore early detection of diabetic retinopathy is essential to prevent the increased severity. An automated system can help detect diabetic retinopathy quickly for determining the follow-up treatment to avoid further damage to the retina. This study proposes a deep learning method for extracting features and classification using a support vector machine. We use the high-level features of the last fully connected layer based on transfer learning from Convolutional Neural Network (CNN) as the input features for classification using the support vector machine (SVM). This method reduces the computation time required by the classification process using CNN with fine-tuning. The proposed method is tested using 77 and 70 retinal images from Messidor database of base 12 and base 13 respectively. From the results of the experiments, the highest accuracy values are 95.83% and 95.24% for base 12 and base 13 respectively.

KW - CNN

KW - Diabetic Retinopathy

KW - Retinal Fundus Images

KW - SVM

KW - Transfer Learning

UR - https://www.scopus.com/pages/publications/85073556525

U2 - 10.1109/ICTS.2019.8850940

DO - 10.1109/ICTS.2019.8850940

M3 - Conference contribution

AN - SCOPUS:85073556525

T3 - Proceedings of 2019 International Conference on Information and Communication Technology and Systems, ICTS 2019

SP - 152

EP - 157

BT - Proceedings of 2019 International Conference on Information and Communication Technology and Systems, ICTS 2019

PB - Institute of Electrical and Electronics Engineers Inc.

T2 - 12th International Conference on Information and Communication Technology and Systems, ICTS 2019

Y2 - 18 July 2019

ER -

Qomariah DUN, Tjandrasa H, Fatichah C. Classification of diabetic retinopathy and normal retinal images using CNN and SVM. In Proceedings of 2019 International Conference on Information and Communication Technology and Systems, ICTS 2019. Institute of Electrical and Electronics Engineers Inc. 2019. p. 152-157. 8850940. (Proceedings of 2019 International Conference on Information and Communication Technology and Systems, ICTS 2019). doi: 10.1109/ICTS.2019.8850940

Classification of diabetic retinopathy and normal retinal images using CNN and SVM

Abstract

Publication series

Conference

UN SDGs

Keywords

Access to Document

Other files and links

Fingerprint

Cite this