http://rdf.ncbi.nlm.nih.gov/pubchem/patent/CN-114343682-A

Outgoing Links

Predicate Object
assignee http://rdf.ncbi.nlm.nih.gov/pubchem/patentassignee/MD5_b18e8dc2e20bf77a566ee020bf12d34f
classificationIPCInventive http://rdf.ncbi.nlm.nih.gov/pubchem/patentipc/A61B6-00
filingDate 2021-12-27-04:00^^<http://www.w3.org/2001/XMLSchema#date>
inventor http://rdf.ncbi.nlm.nih.gov/pubchem/patentinventor/MD5_36ade6ef8c6bd3dca376dd9e5d7a8e5a
http://rdf.ncbi.nlm.nih.gov/pubchem/patentinventor/MD5_8d9bc77a63561a4e4b05725ab2b7c091
http://rdf.ncbi.nlm.nih.gov/pubchem/patentinventor/MD5_b7ef354feb8af1b9d10839478eb6f2bd
http://rdf.ncbi.nlm.nih.gov/pubchem/patentinventor/MD5_5db0b9ca5ed06cf9b43857a4d08ee863
http://rdf.ncbi.nlm.nih.gov/pubchem/patentinventor/MD5_a6850fc8dae8e58972583bf1afdd2c16
http://rdf.ncbi.nlm.nih.gov/pubchem/patentinventor/MD5_194344469be4371ade2be56d4f2d4abf
publicationDate 2022-04-15-04:00^^<http://www.w3.org/2001/XMLSchema#date>
publicationNumber CN-114343682-A
titleOfInvention A kind of breast mammography target lesion detection method and system
abstract The invention provides a method and system for detecting mammary mammography lesions. The method includes acquiring historical mammography image data, performing mammography marking on the historical mammography image data; selecting several windows for the image according to the window value, and The selected window is normalized as the input of the training model; unsupervised training is performed on the input unlabeled image data set to obtain an intermediate representation state, and the input labeled image data set is trained to adjust the intermediate representation The state information is obtained to obtain a training model; the mammography image data to be detected is normalized and then input into the training model to obtain the detection result of the mammary target lesion. The invention uses a large amount of clinical data for training to obtain a prediction model, which is used for detection and analysis of breast mammary target lesions, and obtains detailed detection results of various lesions, which can quickly and accurately detect lesions in the mammography target, and the diagnosis is more professional and fast .
priorityDate 2021-12-27-04:00^^<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/CID23932
http://rdf.ncbi.nlm.nih.gov/pubchem/substance/SID419405613

Total number of triples: 17.