http://rdf.ncbi.nlm.nih.gov/pubchem/patent/CN-114972837-A
Outgoing Links
Predicate | Object |
---|---|
assignee | http://rdf.ncbi.nlm.nih.gov/pubchem/patentassignee/MD5_343530855ce3060b5d1e403ba7e2db68 |
classificationCPCInventive | http://rdf.ncbi.nlm.nih.gov/pubchem/patentcpc/G06N3-08 http://rdf.ncbi.nlm.nih.gov/pubchem/patentcpc/G06N3-045 http://rdf.ncbi.nlm.nih.gov/pubchem/patentcpc/G06F18-241 |
classificationIPCInventive | http://rdf.ncbi.nlm.nih.gov/pubchem/patentipc/G06N3-08 http://rdf.ncbi.nlm.nih.gov/pubchem/patentipc/G06V10-764 http://rdf.ncbi.nlm.nih.gov/pubchem/patentipc/G06V10-82 http://rdf.ncbi.nlm.nih.gov/pubchem/patentipc/G06N3-04 |
filingDate | 2022-03-15-04:00^^<http://www.w3.org/2001/XMLSchema#date> |
inventor | http://rdf.ncbi.nlm.nih.gov/pubchem/patentinventor/MD5_efe6908f951ae0433a4ce5342a4e8139 http://rdf.ncbi.nlm.nih.gov/pubchem/patentinventor/MD5_384e8acfb2bf67513f6e11ddb944c357 http://rdf.ncbi.nlm.nih.gov/pubchem/patentinventor/MD5_b8d191d2eaf9e399d5030e4ef9e6eadc http://rdf.ncbi.nlm.nih.gov/pubchem/patentinventor/MD5_f77badd1f678ad372beaa3b2aaf89df2 |
publicationDate | 2022-08-30-04:00^^<http://www.w3.org/2001/XMLSchema#date> |
publicationNumber | CN-114972837-A |
titleOfInvention | A method for identifying microsatellite instability states from pathological pictures based on RNN |
abstract | The invention provides a method for recognizing the unstable state of microsatellites from pathological pictures based on RNN. First, a target pathological section map obtained by staining a patient's tissue sample with cells is obtained; Small pictures of the tissue area; classify all the small pictures as tumor area/normal area; randomly select N pre-set small pictures classified as tumor areas and use the staintools library to normalize the staining; normalize the normalized small pictures The image is input into the preset feature extraction model, encoded as an M-dimensional feature vector, and an N×M feature matrix is obtained; the N×M feature matrix is input into the pre-trained recurrent neural network prediction model, and the MSI score of the target pathological slice image is obtained. The present invention randomly selects N small pictures of the tumor area for feature encoding, adopts a cyclic neural network model for classification prediction, saves computing resources and improves the accuracy of MSI prediction. |
priorityDate | 2022-03-15-04:00^^<http://www.w3.org/2001/XMLSchema#date> |
type | http://data.epo.org/linked-data/def/patent/Publication |
Incoming Links
Total number of triples: 33.