http://rdf.ncbi.nlm.nih.gov/pubchem/patent/KR-20200062764-A
Outgoing Links
Predicate | Object |
---|---|
assignee | http://rdf.ncbi.nlm.nih.gov/pubchem/patentassignee/MD5_f7b72691b61448140b9a080282c2ccf0 http://rdf.ncbi.nlm.nih.gov/pubchem/patentassignee/MD5_a74935159a0a871dd85e00c138f7fe6b |
classificationCPCInventive | http://rdf.ncbi.nlm.nih.gov/pubchem/patentcpc/A61B5-7275 http://rdf.ncbi.nlm.nih.gov/pubchem/patentcpc/G06N20-00 http://rdf.ncbi.nlm.nih.gov/pubchem/patentcpc/A61B5-0071 |
classificationIPCInventive | http://rdf.ncbi.nlm.nih.gov/pubchem/patentipc/G06N20-00 http://rdf.ncbi.nlm.nih.gov/pubchem/patentipc/A61B5-00 |
filingDate | 2018-11-27-04:00^^<http://www.w3.org/2001/XMLSchema#date> |
inventor | http://rdf.ncbi.nlm.nih.gov/pubchem/patentinventor/MD5_86b07d2151fcdb730858f7ab870bb390 http://rdf.ncbi.nlm.nih.gov/pubchem/patentinventor/MD5_e49a97a38b659b11c6ad04f804785da9 http://rdf.ncbi.nlm.nih.gov/pubchem/patentinventor/MD5_f93d5926d06e18e94ff7c188d6484532 http://rdf.ncbi.nlm.nih.gov/pubchem/patentinventor/MD5_e5478e4197441c8a347ed412b63fb458 |
publicationDate | 2020-06-04-04:00^^<http://www.w3.org/2001/XMLSchema#date> |
publicationNumber | KR-20200062764-A |
titleOfInvention | Method and system for segmentation of vessel using deep learning |
abstract | According to an embodiment of the present invention, an image acquisition unit for acquiring a visible light image and an indocyanine green infrared fluorescence angiography image; An image matching unit configured to match the visible light image and the indocyanine green infrared angiography image to the same location to generate matching information; A verification image production unit that converts the indocyanine green infrared fluorescence angiography image into thresholding or other types of algorithms to produce ground truth information; A training unit based on the matching information and supervised training a deep learning vascular classification algorithm using the actual verification information as a correct answer image; A deep learning blood vessel classification system is provided. The actual verification information production unit, the training unit, and the verification unit can be integrated and operated as one deep learning network. |
isCitedBy | http://rdf.ncbi.nlm.nih.gov/pubchem/patent/KR-102264152-B1 http://rdf.ncbi.nlm.nih.gov/pubchem/patent/WO-2023286948-A1 |
priorityDate | 2018-11-27-04:00^^<http://www.w3.org/2001/XMLSchema#date> |
type | http://data.epo.org/linked-data/def/patent/Publication |
Incoming Links
Total number of triples: 23.