Automated multi-class ground-truth labeling of H&E images for deep learning using multiplexed fluorescence microscopy.
Gouthamrajan NadarajanTyna A. HopeDan WangAlison CheungFiona GintyMartin J. YaffeScott DoylePublished in: Medical Imaging: Digital Pathology (2019)
Keyphrases
- multi class
- ground truth
- fluorescence microscopy
- deep learning
- test images
- unsupervised learning
- input image
- image sequences
- multi class classification
- multiple classes
- image retrieval
- support vector machine
- three dimensional
- pairwise
- feature selection
- data sets
- image regions
- segmentation method
- object detection
- object recognition
- image features
- image representation
- bayesian networks
- similarity measure
- multiple images
- image segmentation