http://rdf.ncbi.nlm.nih.gov/pubchem/patent/CN-104537642-B
Outgoing Links
| Predicate | Object |
|---|---|
| classificationCPCAdditional | http://rdf.ncbi.nlm.nih.gov/pubchem/patentcpc/G06V2201-03 |
| classificationCPCInventive | http://rdf.ncbi.nlm.nih.gov/pubchem/patentcpc/A61B5-055 http://rdf.ncbi.nlm.nih.gov/pubchem/patentcpc/G06F18-24323 |
| classificationIPCInventive | http://rdf.ncbi.nlm.nih.gov/pubchem/patentipc/A61B5-055 http://rdf.ncbi.nlm.nih.gov/pubchem/patentipc/G06T7-00 |
| filingDate | 2014-12-08-04:00^^<http://www.w3.org/2001/XMLSchema#date> |
| grantDate | 2018-09-04-04:00^^<http://www.w3.org/2001/XMLSchema#date> |
| publicationDate | 2018-09-04-04:00^^<http://www.w3.org/2001/XMLSchema#date> |
| publicationNumber | CN-104537642-B |
| titleOfInvention | A Tissue Classification Method for Malignant Glioblastoma Based on Nonnegative Matrix Factorization |
| abstract | The invention discloses a malignant glioblastoma tissue classification method based on non-negative matrix decomposition, which analyzes nuclear magnetic resonance spectrum imaging data through signal processing technology, and then completes the tissue classification of brain glioblastoma. In the present invention, two NMF decompositions are performed on the MRSI data of the patient, thereby identifying and classifying the three tissue types of glioblastoma, normal, tumor and necrosis. Firstly, the NMF decomposition with the wave source number of 2 was performed on the MRSI data, and the wave source and spatial distribution h-map corresponding to normal tissue and abnormal tissue were obtained. Then determine the optimal mask and perform NMF decomposition with 2 wave sources on the mask again to obtain the corresponding wave sources of tumor tissue and necrotic tissue. Finally, NNLS is used to estimate the spatial distribution h-map corresponding to the three wave sources. |
| priorityDate | 2014-12-08-04:00^^<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/substance/SID457068667 http://rdf.ncbi.nlm.nih.gov/pubchem/compound/CID2230 |
Total number of triples: 15.