http://rdf.ncbi.nlm.nih.gov/pubchem/patent/CN-112883770-A

Outgoing Links

Predicate Object
assignee http://rdf.ncbi.nlm.nih.gov/pubchem/patentassignee/MD5_2a3168af63318108c782254905f7ad4c
classificationCPCInventive http://rdf.ncbi.nlm.nih.gov/pubchem/patentcpc/G06N3-045
http://rdf.ncbi.nlm.nih.gov/pubchem/patentcpc/G06V20-698
http://rdf.ncbi.nlm.nih.gov/pubchem/patentcpc/G06N3-08
http://rdf.ncbi.nlm.nih.gov/pubchem/patentcpc/G06V20-695
classificationIPCInventive http://rdf.ncbi.nlm.nih.gov/pubchem/patentipc/G06N3-08
http://rdf.ncbi.nlm.nih.gov/pubchem/patentipc/G06K9-00
http://rdf.ncbi.nlm.nih.gov/pubchem/patentipc/G06N3-04
filingDate 2020-04-20-04:00^^<http://www.w3.org/2001/XMLSchema#date>
inventor http://rdf.ncbi.nlm.nih.gov/pubchem/patentinventor/MD5_e4932da0f24167654a99cdb06cf1e6e1
http://rdf.ncbi.nlm.nih.gov/pubchem/patentinventor/MD5_94a05267054c1c15fd2268223296748d
http://rdf.ncbi.nlm.nih.gov/pubchem/patentinventor/MD5_afd1c8a9c5de4545869e6936abf7e1b3
http://rdf.ncbi.nlm.nih.gov/pubchem/patentinventor/MD5_c1c4666c6daaccd9eb34c547538110f9
publicationDate 2021-06-01-04:00^^<http://www.w3.org/2001/XMLSchema#date>
publicationNumber CN-112883770-A
titleOfInvention A PD-1/PD-L1 pathological image recognition method and device based on deep learning
abstract The present application relates to the field of image recognition technology and medical technology, and provides a PD-1/PD-L1 pathological image recognition method based on deep learning, including step S1: constructing a deep residual network model; step S2: obtaining manually marked images PD-1/PD-L1 immunohistochemical staining images; S3 step: construct PD-1/PD-L1 pathological staining image recognition model with immunohistochemical staining images on the deep residual network model; S4 step: use the recognition model to identify PD-1/PD-L1 pathological pictures of the patient to be tested. The present application also provides a corresponding deep learning-based PD-1/PD-L1 pathological image recognition device, computer equipment and computer-readable storage medium. The identification model of the present application can replace manual judgment, and can correctly, quickly and stably judge whether there is positive expression of PD-1/PD-L1 in a patient.
isCitedBy http://rdf.ncbi.nlm.nih.gov/pubchem/patent/CN-114235539-A
priorityDate 2020-04-20-04:00^^<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/CID22978774
http://rdf.ncbi.nlm.nih.gov/pubchem/substance/SID419701332

Total number of triples: 22.