http://rdf.ncbi.nlm.nih.gov/pubchem/patent/CN-113298855-B
Outgoing Links
Predicate | Object |
---|---|
classificationCPCAdditional | http://rdf.ncbi.nlm.nih.gov/pubchem/patentcpc/G06T2207-20081 http://rdf.ncbi.nlm.nih.gov/pubchem/patentcpc/G06T2207-20076 http://rdf.ncbi.nlm.nih.gov/pubchem/patentcpc/G06T2207-10084 http://rdf.ncbi.nlm.nih.gov/pubchem/patentcpc/G06T2207-20084 |
classificationCPCInventive | http://rdf.ncbi.nlm.nih.gov/pubchem/patentcpc/G06T7-12 http://rdf.ncbi.nlm.nih.gov/pubchem/patentcpc/G06N3-08 http://rdf.ncbi.nlm.nih.gov/pubchem/patentcpc/G06N3-04 http://rdf.ncbi.nlm.nih.gov/pubchem/patentcpc/G06T7-33 http://rdf.ncbi.nlm.nih.gov/pubchem/patentcpc/G06V10-752 |
classificationIPCInventive | http://rdf.ncbi.nlm.nih.gov/pubchem/patentipc/G06N3-08 http://rdf.ncbi.nlm.nih.gov/pubchem/patentipc/G06T7-33 http://rdf.ncbi.nlm.nih.gov/pubchem/patentipc/G06K9-62 http://rdf.ncbi.nlm.nih.gov/pubchem/patentipc/G06N3-04 http://rdf.ncbi.nlm.nih.gov/pubchem/patentipc/G06T7-12 |
filingDate | 2021-05-27-04:00^^<http://www.w3.org/2001/XMLSchema#date> |
grantDate | 2021-12-28-04:00^^<http://www.w3.org/2001/XMLSchema#date> |
publicationDate | 2021-12-28-04:00^^<http://www.w3.org/2001/XMLSchema#date> |
publicationNumber | CN-113298855-B |
titleOfInvention | Image registration method based on automatic delineation |
abstract | The invention discloses an image registration method based on automatic delineation, which includes: inputting two medical images of arbitrary modes; training a neural network by adopting a domain-adaptive migration learning strategy, and when the training data only has the gold standard of OAR delineation of CT , so that it has the ability to recognize OAR for other modalities except CT; input the two input images into the above neural network to obtain their own whole body OAR segmentation results; based on OAR contour points, iterative optimization method is used to obtain rigid matching. Based on the rigid registration, for each OAR, the contour points of the OAR in the fixed image and the OAR in the corresponding moving image are compared. The contour points are matched to obtain the displacement value of the contour points; the complete three-dimensional matrix of the displacement field is obtained through the interpolation method based on the control points, so as to obtain the medical image warped image after non-rigid registration. In this way, the problem of lack of OAR gold standard can be effectively solved. |
priorityDate | 2021-05-27-04:00^^<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: 24.