WeGleNet: A weakly-supervised convolutional neural network for the semantic segmentation of Gleason grades in prostate histology images.
Julio Silva-RodríguezAdrián ColomerValery NaranjoPublished in: Comput. Medical Imaging Graph. (2021)
Keyphrases
- image segmentation
- weakly supervised
- semantic segmentation
- superpixels
- segmentation algorithm
- segmentation method
- image understanding
- object segmentation
- prostate cancer
- input image
- multiscale
- image set
- object class
- multiple images
- markov random field
- image retrieval
- conditional random fields
- scene classification
- bounding box
- image features
- image classification
- topic models
- image database
- object detectors
- test images
- natural images
- object recognition
- semi supervised
- object detection
- ground truth
- object classes
- object categories
- image annotation
- viewpoint
- hidden markov models