TY  - CONF
PB  - Institute of Electrical and Electronics Engineers Inc.
SN  - 9781538624715
Y1  - 2019///
EP  - 446
A1  - Kamble, R.M.
A1  - Kokare, M.
A1  - Chan, G.C.Y.
A1  - Perdomo, O.
A1  - González, F.A.
A1  - Müller, H.
A1  - Mériaudeau, F.
UR  - https://www.scopus.com/inward/record.uri?eid=2-s2.0-85062772479&doi=10.1109%2fIECBES.2018.8626616&partnerID=40&md5=5afcb4ca34c7fd4c0676b9c468644f97
AV  - none
SP  - 442
TI  - Automated Diabetic Macular Edema (DME) analysis using fine tuning with inception-resnet-v2 on oct images
ID  - scholars11827
KW  - Biomedical engineering; Convolution; Medicine; Neural networks; Statistical methods; Tomography
KW  -  Chinese universities; Classification accuracy; Convolutional neural network; Developed model; Fine tuning; Leave-one-out cross validations; Macular edema; Research institutes
KW  -  Optical tomography
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. © 2018 IEEE
N1  - cited By 35; Conference of 2018 IEEE EMBS Conference on Biomedical Engineering and Sciences, IECBES 2018 ; Conference Date: 3 December 2018 Through 6 December 2018; Conference Code:144644
ER  -