http://rdf.ncbi.nlm.nih.gov/pubchem/patent/CN-109559296-A
Outgoing Links
Predicate | Object |
---|---|
assignee | http://rdf.ncbi.nlm.nih.gov/pubchem/patentassignee/MD5_0fdac9717ae5887bf47ca96fc8b29ad6 |
classificationCPCAdditional | http://rdf.ncbi.nlm.nih.gov/pubchem/patentcpc/G06T2207-20081 http://rdf.ncbi.nlm.nih.gov/pubchem/patentcpc/G06T2207-10088 http://rdf.ncbi.nlm.nih.gov/pubchem/patentcpc/G06T2207-10081 http://rdf.ncbi.nlm.nih.gov/pubchem/patentcpc/G06T2207-30004 |
classificationCPCInventive | http://rdf.ncbi.nlm.nih.gov/pubchem/patentcpc/G06T7-0012 http://rdf.ncbi.nlm.nih.gov/pubchem/patentcpc/G06N3-045 http://rdf.ncbi.nlm.nih.gov/pubchem/patentcpc/G06T7-344 |
classificationIPCInventive | http://rdf.ncbi.nlm.nih.gov/pubchem/patentipc/G06T7-33 http://rdf.ncbi.nlm.nih.gov/pubchem/patentipc/G06N3-04 http://rdf.ncbi.nlm.nih.gov/pubchem/patentipc/G06T7-00 |
filingDate | 2018-10-08-04:00^^<http://www.w3.org/2001/XMLSchema#date> |
inventor | http://rdf.ncbi.nlm.nih.gov/pubchem/patentinventor/MD5_fcefa6331cee36d91bea7598e0d958d8 http://rdf.ncbi.nlm.nih.gov/pubchem/patentinventor/MD5_0d8c11162026fbda15a6df3e8f4e56e4 http://rdf.ncbi.nlm.nih.gov/pubchem/patentinventor/MD5_ed6ee71f01ae61c2a14394e0b8b4f776 |
publicationDate | 2019-04-02-04:00^^<http://www.w3.org/2001/XMLSchema#date> |
publicationNumber | CN-109559296-A |
titleOfInvention | Method and system for medical image registration based on fully convolutional neural network and mutual information |
abstract | The invention discloses a medical image registration method and system based on a fully convolutional neural network and mutual information. The method includes the following steps: using a fully convolutional neural network model to image a first two-dimensional image and a second two-dimensional image. Transform to obtain three-dimensional transformation parameters; update the second three-dimensional image according to the three-dimensional transformation parameters; calculate mutual information values of the first three-dimensional image and the second three-dimensional image; and iteratively optimize the mutual information values to obtain optimal three-dimensional transformation parameters. The invention obtains the initial value of mutual information registration through the full convolutional neural network, so that the search value is near the global optimal solution, thereby reducing the number of searches and improving the registration speed; accuracy of image registration. The invention can be widely used in the field of image processing. |
isCitedBy | http://rdf.ncbi.nlm.nih.gov/pubchem/patent/US-11756319-B2 http://rdf.ncbi.nlm.nih.gov/pubchem/patent/CN-112598028-A http://rdf.ncbi.nlm.nih.gov/pubchem/patent/CN-115004241-B http://rdf.ncbi.nlm.nih.gov/pubchem/patent/CN-115004241-A |
priorityDate | 2018-10-08-04:00^^<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/substance/SID415713197 http://rdf.ncbi.nlm.nih.gov/pubchem/compound/CID25572 |
Total number of triples: 27.