http://rdf.ncbi.nlm.nih.gov/pubchem/patent/CN-112927243-B
Outgoing Links
| Predicate | Object |
|---|---|
| classificationCPCAdditional | http://rdf.ncbi.nlm.nih.gov/pubchem/patentcpc/G06T2207-30101 http://rdf.ncbi.nlm.nih.gov/pubchem/patentcpc/G06T2207-30096 http://rdf.ncbi.nlm.nih.gov/pubchem/patentcpc/G06T2207-20221 http://rdf.ncbi.nlm.nih.gov/pubchem/patentcpc/G06T2207-20132 http://rdf.ncbi.nlm.nih.gov/pubchem/patentcpc/G06T2207-30204 http://rdf.ncbi.nlm.nih.gov/pubchem/patentcpc/G06T2207-20084 http://rdf.ncbi.nlm.nih.gov/pubchem/patentcpc/G06T2207-20081 |
| classificationCPCInventive | http://rdf.ncbi.nlm.nih.gov/pubchem/patentcpc/G06T7-11 http://rdf.ncbi.nlm.nih.gov/pubchem/patentcpc/G06F18-241 http://rdf.ncbi.nlm.nih.gov/pubchem/patentcpc/G06N3-08 http://rdf.ncbi.nlm.nih.gov/pubchem/patentcpc/G06F18-253 http://rdf.ncbi.nlm.nih.gov/pubchem/patentcpc/G06N3-045 http://rdf.ncbi.nlm.nih.gov/pubchem/patentcpc/G06N3-048 |
| classificationIPCInventive | http://rdf.ncbi.nlm.nih.gov/pubchem/patentipc/G06T7-11 http://rdf.ncbi.nlm.nih.gov/pubchem/patentipc/G06V10-82 http://rdf.ncbi.nlm.nih.gov/pubchem/patentipc/G06N3-08 http://rdf.ncbi.nlm.nih.gov/pubchem/patentipc/G06V10-80 http://rdf.ncbi.nlm.nih.gov/pubchem/patentipc/G06V10-26 http://rdf.ncbi.nlm.nih.gov/pubchem/patentipc/G06N3-04 http://rdf.ncbi.nlm.nih.gov/pubchem/patentipc/G06V10-25 http://rdf.ncbi.nlm.nih.gov/pubchem/patentipc/G06V10-764 |
| filingDate | 2021-03-31-04:00^^<http://www.w3.org/2001/XMLSchema#date> |
| grantDate | 2022-12-23-04:00^^<http://www.w3.org/2001/XMLSchema#date> |
| publicationDate | 2022-12-23-04:00^^<http://www.w3.org/2001/XMLSchema#date> |
| publicationNumber | CN-112927243-B |
| titleOfInvention | A Convolutional Neural Network Based Microbleed Lesion Segmentation Method |
| abstract | The present invention designs a nailfold microhemorrhage lesion segmentation method based on convolutional neural network. The method collects and processes nailfold microhemorrhage images; marks the microhemorrhage lesion area to obtain a gold standard image; constructs a method based on convolutional neural network Nailfold microhemorrhage lesion segmentation model; divide training set and test set; perform data amplification on the training set, and use the amplified data to train the model; use the test set to test the trained model. The present invention introduces the dual-attention mechanism including channel attention and spatial attention into the classic U-shaped feature extraction network, emphasizes key features, suppresses irrelevant features, and promotes the model to pay more attention to the microbleed lesion area; Normalization is used as a regularization method to speed up model convergence, prevent overfitting, and improve overall segmentation performance. The invention can obtain high-precision segmentation images of nailfold micro-bleeding lesions. |
| priorityDate | 2021-03-31-04:00^^<http://www.w3.org/2001/XMLSchema#date> |
| type | http://data.epo.org/linked-data/def/patent/Publication |
Incoming Links
Total number of triples: 33.