Multi-modal, multi-task, multi-attention (M3) deep learning detection of reticular pseudodrusen: towards automated and accessible classification of age-related macular degeneration.
Qingyu ChenTiarnan D. L. KeenanAlexis AllotYifan PengElvira AgrónAmitha DomalpallyCaroline C. W. KlaverDaniel T. LuttikhuizenMarcus H. ColyerCatherine A. CukrasHenry E. WileyM. Teresa MagoneChantal Cousineau-KriegerWai T. WongYingying ZhuEmily Y. ChewZhiyong LuPublished in: CoRR (2020)
Keyphrases
- multi modal
- deep learning
- multi task
- age related macular degeneration
- feature selection
- machine learning
- multi modality
- unsupervised learning
- classification accuracy
- learning tasks
- text classification
- decision trees
- retinal images
- feature vectors
- feature space
- supervised learning
- mutual information
- support vector
- multiscale
- class labels
- multi class
- high dimensional
- image classification
- object detection
- transfer learning
- learning problems
- feature extraction
- support vector machine