http://rdf.ncbi.nlm.nih.gov/pubchem/patent/CN-109509178-B

Outgoing Links

Predicate Object
classificationCPCAdditional http://rdf.ncbi.nlm.nih.gov/pubchem/patentcpc/G06T2207-20084
http://rdf.ncbi.nlm.nih.gov/pubchem/patentcpc/G06T2207-20081
http://rdf.ncbi.nlm.nih.gov/pubchem/patentcpc/G06T2207-30041
http://rdf.ncbi.nlm.nih.gov/pubchem/patentcpc/G06T2207-10101
classificationCPCInventive http://rdf.ncbi.nlm.nih.gov/pubchem/patentcpc/G06N3-045
http://rdf.ncbi.nlm.nih.gov/pubchem/patentcpc/G06T7-194
http://rdf.ncbi.nlm.nih.gov/pubchem/patentcpc/G06N3-08
http://rdf.ncbi.nlm.nih.gov/pubchem/patentcpc/G06T7-0012
classificationIPCInventive http://rdf.ncbi.nlm.nih.gov/pubchem/patentipc/G06T7-00
http://rdf.ncbi.nlm.nih.gov/pubchem/patentipc/G06T7-194
http://rdf.ncbi.nlm.nih.gov/pubchem/patentipc/G06N3-04
http://rdf.ncbi.nlm.nih.gov/pubchem/patentipc/G06N3-08
filingDate 2018-10-24-04:00^^<http://www.w3.org/2001/XMLSchema#date>
grantDate 2021-09-10-04:00^^<http://www.w3.org/2001/XMLSchema#date>
publicationDate 2021-09-10-04:00^^<http://www.w3.org/2001/XMLSchema#date>
publicationNumber CN-109509178-B
titleOfInvention A method for choroid segmentation in OCT images based on improved U-net network
abstract The invention discloses an OCT image choroid segmentation method based on an improved U-net network. The main improvement points of the U-net network include: (1) by increasing the number of encoders and decoders in the network to extract more feature information; (2) adding a refined residual block after the encoder to enhance the recognition ability of each layer; (3) adding an attention module after the decoder to let the high-level semantic information guide the low-level detail information; (4) the loss function adopts The traditional L2 loss and the Dice loss are combined to jointly constrain the network model, and the improved U-net network of the present invention can automatically segment the upper and lower boundaries of the choroid whether it is a normal human eye or a pathological myopic human eye, and the segmentation result has high accuracy.
priorityDate 2018-10-24-04:00^^<http://www.w3.org/2001/XMLSchema#date>
type http://data.epo.org/linked-data/def/patent/Publication

Incoming Links

Predicate Subject
isDiscussedBy http://rdf.ncbi.nlm.nih.gov/pubchem/compound/CID23985
http://rdf.ncbi.nlm.nih.gov/pubchem/substance/SID482532689

Total number of triples: 22.