Home > Search Results: keywords:"fully convolution neural network"
Search:
Search Tips :: Advanced Search
Search collections:
Sort by: Display results: Output format:
National Repository of Grey Literature 2 records found  Search took 0.00 seconds. 
Deep Learning for 3D Image Analysis
 Hlavoň, David ; Herout, Adam (referee) ; Španěl, Michal (advisor)
This work deals with usage of fully convolutional neural network for segmentation of bones in CT scans. Typical issue is limited size of dataset while training on medical images. Experiments show that training on patches gives score of segmentation 95,1%. Training on whole images gives score 30% less than training on patches. As metric F-measure was used. BVLC Caffe Framework was used for training neural network.
Detailed record
Deep Learning for 3D Image Analysis
 Hlavoň, David ; Herout, Adam (referee) ; Španěl, Michal (advisor)
This work deals with usage of fully convolutional neural network for segmentation of bones in CT scans. Typical issue is limited size of dataset while training on medical images. Experiments show that training on patches gives score of segmentation 95,1%. Training on whole images gives score 30% less than training on patches. As metric F-measure was used. BVLC Caffe Framework was used for training neural network.
Detailed record

Interested in being notified about new results for this query?
Subscribe to the RSS feed.
Digital Repository :: Search :: Submit :: Personalize :: Help
Powered by Invenio v1.1.2
Maintained by admin.invenio@techlib.cz
This site is also available in the following languages:
Česky  English