Deep learning detection of reticular pseudodrusen using multi-modal, multi-task, and multi-attention mechanisms: towards automated and accessible classification of age-related macular degeneration.
Qingyu ChenTiarnan D. KeenanEmily Y. ChewZhiyong LuPublished in: AMIA (2021)
Keyphrases
- multi modal
- deep learning
- age related macular degeneration
- multi task
- feature selection
- unsupervised learning
- multi modality
- machine learning
- learning tasks
- high dimensional
- image classification
- feature vectors
- data sets
- decision trees
- feature extraction
- training data
- multi class
- model selection
- object detection
- retinal images
- classification accuracy
- training set
- support vector
- text classification
- weakly supervised
- learning algorithm