Conditional Adversarial Transfer for Glaucoma Diagnosis

Wang, Jingwen1,5; Yan, Yuguang1,5; Xu, Yanwu2; Zhao, Wei4; Min, Huaqing1; Tan, Mingkui1; Liu, Jiang3

10.1109/EMBC.2019.8857308

2019

1557-170X

1558-4615

978-1-5386-1312-2

41st Annual International Conference of the IEEE Engineering in Medicine and Biology Society, EMBC 2019

2032-2035

23-27 July 2019

Berlin, Germany

345 E 47TH ST, NEW YORK, NY 10017 USA

Institute of Electrical and Electronics Engineers Inc.

Deep learning has achieved great success in image classification task when given sufficient labeled training images. However, in fundus image based glaucoma diagnosis, we often have very limited training data due to expensive cost in data labeling. Moreover, when facing a new application environment, it is difficult to train a network with limited labeled training images. In this case, some images from some auxiliary domains (i.e., source domain) could be exploited to improve the performance. Unfortunately, direct using the source domain data may not achieve promising performance for the domain of interest (i.e., target domain) due to reasons like distribution discrepancy between two domains. In this paper, focusing on glaucoma diagnosis, we propose a deep adversarial transfer learning method conditioned on label information to match the distributions of source and target domains, so that the labeled source images can be leveraged to improve the classification performance in the target domain. Different from the most existing adversarial transfer learning methods which consider marginal distribution matching only, we seek to match the label conditional distributions by handling images with different labels separately. We conduct experiments on three glaucoma datasets and adopt multiple evaluation metrics to verify the effectiveness of our proposed method.
© 2019 IEEE.

Training Task analysis Learning systems Measurement Biomedical optical imaging Optical imaging Deep learning

其他

英语

EI ; CPCI-S

National Natural Science Foundation of China[61602185]

Engineering

Engineering, Biomedical ; Engineering, Electrical & Electronic

WOS:000557295302105

20200308035711

Ophthalmology ; Computer aided diagnosis ; Learning systems ; Classification (of information) ; Deep learning ; Computer vision

Biomedical Engineering:461.1 ; Ergonomics and Human Factors Engineering:461.4 ; Medicine and Pharmacology:461.6 ; Information Theory and Signal Processing:716.1 ; Computer Applications:723.5 ; Vision:741.2 ; Information Sources and Analysis:903.1

EV Compendex

1.South China University of Technology, China
2.Baidu, Inc., China
3.Southern University of Science and Technology, Chinese Academy of Sciences, China
4.CVTE Research, China
5.Medical Image and Signal Processing Group, CVTE Research

Wang, Jingwen,Yan, Yuguang,Xu, Yanwu,et al. Conditional Adversarial Transfer for Glaucoma Diagnosis[C]. 345 E 47TH ST, NEW YORK, NY 10017 USA:Institute of Electrical and Electronics Engineers Inc.,2019:2032-2035.