TY - GEN
T1 - Automated Diabetic Macular Edema (DME) analysis using fine tuning with inception-resnet-v2 on oct images
AU - Kamble, Ravi M.
AU - Kokare, Manesh
AU - Chan, Genevieve C.Y.
AU - Perdomo, Oscar
AU - González, Fabio A.
AU - Müller, Henning
AU - Mériaudeau, Fabrice
N1 - Funding Information:
The authors acknowledge the funding for this research by the Fundamental Research Grant Scheme (FRGS) grant FRGS/1/2017/TK04/UTP/01/1 Ministry of Education (MOE), and Universiti Research Internal Fund (URIF) grant, Universiti Teknologi PETRONAS Malaysia.
Publisher Copyright:
© 2018 IEEE
Copyright:
Copyright 2019 Elsevier B.V., All rights reserved.
PY - 2019/1/24
Y1 - 2019/1/24
N2 - Accurate detection of diabetic macular edema (DME) is an important task in optical coherence tomography (OCT) images of the eye. A relatively simple and practical approach is proposed in this paper. A pre-trained convolutional neural network (CNN) is fine tuned for a classification of DME versus normal cases. The fine-tuned Inception-Resnet-v2 CNN model can effectively identify pathologies in comparison to classical learning. Experiments were carried out on the publicly available data set of the Singapore Eye Research Institute (SERI). The developed model was also compared to other fine tuned models, such as Resnet-50 and Inception-v3. The proposed method achieved 100% classification accuracy with the Inception-Resnet-v2 model using a leave-one-out cross-validation strategy. For robustness, the model trained on the SERI dataset was tested on another dataset provided by the Chinese University HongKong (CUHK), also with 100% accuracy. The proposed method is a potentially impactful tool for accurately detecting DME vs. normal cases.
AB - Accurate detection of diabetic macular edema (DME) is an important task in optical coherence tomography (OCT) images of the eye. A relatively simple and practical approach is proposed in this paper. A pre-trained convolutional neural network (CNN) is fine tuned for a classification of DME versus normal cases. The fine-tuned Inception-Resnet-v2 CNN model can effectively identify pathologies in comparison to classical learning. Experiments were carried out on the publicly available data set of the Singapore Eye Research Institute (SERI). The developed model was also compared to other fine tuned models, such as Resnet-50 and Inception-v3. The proposed method achieved 100% classification accuracy with the Inception-Resnet-v2 model using a leave-one-out cross-validation strategy. For robustness, the model trained on the SERI dataset was tested on another dataset provided by the Chinese University HongKong (CUHK), also with 100% accuracy. The proposed method is a potentially impactful tool for accurately detecting DME vs. normal cases.
UR - http://www.scopus.com/inward/record.url?scp=85062772479&partnerID=8YFLogxK
UR - http://www.scopus.com/inward/citedby.url?scp=85062772479&partnerID=8YFLogxK
U2 - 10.1109/IECBES.2018.8626616
DO - 10.1109/IECBES.2018.8626616
M3 - Conference contribution
AN - SCOPUS:85062772479
T3 - 2018 IEEE EMBS Conference on Biomedical Engineering and Sciences, IECBES 2018 - Proceedings
SP - 442
EP - 446
BT - 2018 IEEE EMBS Conference on Biomedical Engineering and Sciences, IECBES 2018 - Proceedings
PB - Institute of Electrical and Electronics Engineers Inc.
T2 - 2018 IEEE EMBS Conference on Biomedical Engineering and Sciences, IECBES 2018
Y2 - 3 December 2018 through 6 December 2018
ER -
