http://rdf.ncbi.nlm.nih.gov/pubchem/patent/CN-110490212-A
Outgoing Links
Predicate | Object |
---|---|
assignee | http://rdf.ncbi.nlm.nih.gov/pubchem/patentassignee/MD5_1fefd66fdbc3870bbaa8e5a4f87bdb0a http://rdf.ncbi.nlm.nih.gov/pubchem/patentassignee/MD5_31565373c08678b1a7e68d5a1e4c5878 |
classificationCPCAdditional | http://rdf.ncbi.nlm.nih.gov/pubchem/patentcpc/G06T2207-20132 |
classificationCPCInventive | http://rdf.ncbi.nlm.nih.gov/pubchem/patentcpc/G06T7-11 http://rdf.ncbi.nlm.nih.gov/pubchem/patentcpc/G06T5-002 http://rdf.ncbi.nlm.nih.gov/pubchem/patentcpc/G06V10-44 http://rdf.ncbi.nlm.nih.gov/pubchem/patentcpc/G06V10-464 |
classificationIPCInventive | http://rdf.ncbi.nlm.nih.gov/pubchem/patentipc/G06T5-00 http://rdf.ncbi.nlm.nih.gov/pubchem/patentipc/G06K9-46 http://rdf.ncbi.nlm.nih.gov/pubchem/patentipc/G06T7-11 |
filingDate | 2019-02-26-04:00^^<http://www.w3.org/2001/XMLSchema#date> |
inventor | http://rdf.ncbi.nlm.nih.gov/pubchem/patentinventor/MD5_53476c5ac1ef00fd39a9b8bd30fb33c5 http://rdf.ncbi.nlm.nih.gov/pubchem/patentinventor/MD5_ba026134ca38a0668a59d7826fe8af14 http://rdf.ncbi.nlm.nih.gov/pubchem/patentinventor/MD5_154563e4f1c232789a44ebb980477cb4 http://rdf.ncbi.nlm.nih.gov/pubchem/patentinventor/MD5_b7574a21ef359c5decde7e5c352f7175 http://rdf.ncbi.nlm.nih.gov/pubchem/patentinventor/MD5_13bb17c8d91f5a80642f5b227ddc932b |
publicationDate | 2019-11-22-04:00^^<http://www.w3.org/2001/XMLSchema#date> |
publicationNumber | CN-110490212-A |
titleOfInvention | Mammography target image processing equipment, method and device |
abstract | The present application relates to a mammography image processing device, method, device, computer readable storage medium and computer equipment, the method comprising: acquiring mammography images; inputting the mammography images into a target object detection model to obtain the corresponding According to the prediction map, the relationship degree of each pixel of the mammary target image belonging to the target detection object is obtained, and contour extraction is performed according to the relationship degree to obtain the salient area of the target detection object; according to the salient area of the target detection object, a number of different objects are determined from the prediction map. The salient region sub-map of the scale, each salient region sub-map of different scales includes the salient region of the target detection object; input each salient region sub-map into each feature extraction sub-network in the target object classification model, and extract the sub-network according to each feature. The feature extraction result of , obtains the target detection object prediction area in the mammography image. The solution provided in this application can improve the accuracy of the region where the tumor is located in the mammography image. |
priorityDate | 2019-02-26-04:00^^<http://www.w3.org/2001/XMLSchema#date> |
type | http://data.epo.org/linked-data/def/patent/Publication |
Incoming Links
Total number of triples: 30.