Extracting 2D weak labels from volume labels using multiple instance learning in CT hemorrhage detection.
Samuel RemediosZihao WuCamilo BermudezCailey I. KerleySnehashis RoyMayur B. PatelJohn A. ButmanBennett A. LandmanDzung L. PhamPublished in: Medical Imaging: Image Processing (2020)
Keyphrases
- multiple instance learning
- multiple instance
- pairwise
- ct images
- object based image retrieval
- multi class
- image categorization
- class labels
- supervised learning
- computerized tomography
- object detection
- multi label
- real valued data
- training set
- dimensionality reduction
- image classification
- data sets
- semi supervised
- prior knowledge
- multiscale
- training data