Abstract | ||
---|---|---|
This paper studies automated categorization of age-related macular degeneration (AMD) given a multi-modal input, which consists of a color fundus image and an optical coherence tomography (OCT) image from a specific eye. Previous work uses a traditional method, comprised of feature extraction and classifier training that cannot be optimized jointly. By contrast, we propose a two-stream convolutional neural network (CNN) that is end-to-end. The CNN's fusion layer is tailored to the need of fusing information from the fundus and OCT streams. For generating more multi-modal training instances, we introduce Loose Pair training, where a fundus image and an OCT image are paired based on class labels rather than eyes. Moreover, for a visual interpretation of how the individual modalities make contributions, we extend the class activation mapping technique to the multi-modal scenario. Experiments on a real-world dataset collected from an outpatient clinic justify the viability of our proposal for multi-modal AMD categorization. |
Year | DOI | Venue |
---|---|---|
2019 | 10.1007/978-3-030-32239-7_18 | Lecture Notes in Computer Science |
Keywords | DocType | Volume |
AMD categorization,Multi-modal,Fundus,OCT,Two-stream CNN | Conference | 11764 |
ISSN | Citations | PageRank |
0302-9743 | 1 | 0.37 |
References | Authors | |
0 | 11 |
Name | Order | Citations | PageRank |
---|---|---|---|
Weisen Wang | 1 | 1 | 0.71 |
Zhiyan Xu | 2 | 1 | 0.37 |
Weihong Yu | 3 | 1 | 0.71 |
Jianchun Zhao | 4 | 1 | 1.38 |
jingyuan yang | 5 | 44 | 5.74 |
Feng He | 6 | 1 | 0.71 |
Zhikun Yang | 7 | 1 | 0.37 |
Di Chen | 8 | 1 | 0.37 |
Dayong Ding | 9 | 3 | 2.47 |
Youxin Chen | 10 | 1 | 0.37 |
Xirong Li | 11 | 1191 | 68.62 |