Semi-supervised training of deep convolutional neural networks with heterogeneous data and few local annotations: An experiment on prostate histopathology image classification.
Niccolò MariniSebastian OtáloraHenning MüllerManfredo AtzoriPublished in: Medical Image Anal. (2021)
Keyphrases
- heterogeneous data
- image classification
- semi supervised
- convolutional neural networks
- metadata
- data integration
- prostate cancer
- supervised learning
- data sources
- data management
- databases
- heterogeneous databases
- complex data
- semantic heterogeneity
- semi supervised learning
- feature extraction
- unlabeled data
- convolutional network
- active learning
- case study
- feature vectors
- training set
- image features
- social network analysis
- labeled data