Development of training environment for deep learning with medical images on supercomputer system based on asynchronous parallel Bayesian optimization.
Yukihiro NomuraIssei SatoToshihiro HanawaShouhei HanaokaTakahiro NakaoTomomi TakenagaTetsuya HoshinoYuji SekiyaSoichiro MikiTakeharu YoshikawaNaoto HayashiOsamu AbePublished in: J. Supercomput. (2020)
Keyphrases
- medical images
- deep learning
- anatomical structures
- deep architectures
- deformable models
- medical imaging
- restricted boltzmann machine
- medical image analysis
- unsupervised learning
- mr images
- region of interest
- segmentation of medical images
- unsupervised feature learning
- maximum likelihood
- training examples
- online learning
- active learning
- training set