http://rdf.ncbi.nlm.nih.gov/pubchem/patent/CN-109584246-B
Outgoing Links
Predicate | Object |
---|---|
classificationCPCAdditional | http://rdf.ncbi.nlm.nih.gov/pubchem/patentcpc/G06T2207-20081 http://rdf.ncbi.nlm.nih.gov/pubchem/patentcpc/G06V2201-03 http://rdf.ncbi.nlm.nih.gov/pubchem/patentcpc/G06T2207-30048 http://rdf.ncbi.nlm.nih.gov/pubchem/patentcpc/G06T2207-10088 http://rdf.ncbi.nlm.nih.gov/pubchem/patentcpc/G06T2207-20016 http://rdf.ncbi.nlm.nih.gov/pubchem/patentcpc/G06T2207-20084 http://rdf.ncbi.nlm.nih.gov/pubchem/patentcpc/G06T2207-20104 |
classificationCPCInventive | http://rdf.ncbi.nlm.nih.gov/pubchem/patentcpc/G06F18-253 http://rdf.ncbi.nlm.nih.gov/pubchem/patentcpc/G06F18-2414 http://rdf.ncbi.nlm.nih.gov/pubchem/patentcpc/G06T7-11 http://rdf.ncbi.nlm.nih.gov/pubchem/patentcpc/G06T7-12 http://rdf.ncbi.nlm.nih.gov/pubchem/patentcpc/G06V10-44 |
classificationIPCInventive | http://rdf.ncbi.nlm.nih.gov/pubchem/patentipc/G06V10-80 http://rdf.ncbi.nlm.nih.gov/pubchem/patentipc/G06V10-764 http://rdf.ncbi.nlm.nih.gov/pubchem/patentipc/G06V10-52 http://rdf.ncbi.nlm.nih.gov/pubchem/patentipc/G06V10-44 http://rdf.ncbi.nlm.nih.gov/pubchem/patentipc/G06V10-82 http://rdf.ncbi.nlm.nih.gov/pubchem/patentipc/G06V10-26 |
filingDate | 2018-11-16-04:00^^<http://www.w3.org/2001/XMLSchema#date> |
grantDate | 2022-12-16-04:00^^<http://www.w3.org/2001/XMLSchema#date> |
publicationDate | 2022-12-16-04:00^^<http://www.w3.org/2001/XMLSchema#date> |
publicationNumber | CN-109584246-B |
titleOfInvention | Radiological image segmentation method for DCM myocardial diagnosis and treatment based on multi-scale feature pyramid |
abstract | The invention belongs to the technical field of medical image processing, and discloses a multi-scale feature pyramid-based DCM myocardial diagnosis and treatment radiation image segmentation method, which can segment cardiac MRI images and completely segment medical anatomical structures such as cardiac muscle and blood pool. The present invention replaces the traditional convolution by using atrous convolution, which has the advantage that the receptive field of the convolution kernel is larger and can obtain larger context information; by using spatial pyramid pooling, images can be processed on different scales. Information extraction, to cope with the multi-scale characteristics of the image, even small objects can be effectively captured; by using the encoder and decoder structure, the detailed information can be recovered, and the shallow features and high-level features can be fused to obtain rich semantics. And a segmentation mask with complete details; the invention reduces the workload of doctors, and has great significance for disease analysis, follow-up treatment plan and postoperative evaluation. |
priorityDate | 2018-11-16-04:00^^<http://www.w3.org/2001/XMLSchema#date> |
type | http://data.epo.org/linked-data/def/patent/Publication |
Incoming Links
Total number of triples: 29.