http://rdf.ncbi.nlm.nih.gov/pubchem/patent/CN-112508175-A
Outgoing Links
| Predicate | Object |
|---|---|
| assignee | http://rdf.ncbi.nlm.nih.gov/pubchem/patentassignee/MD5_c6655263ba4852e71280f7529b0065f3 |
| 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/G06T11-003 |
| classificationIPCInventive | http://rdf.ncbi.nlm.nih.gov/pubchem/patentipc/G06N3-04 http://rdf.ncbi.nlm.nih.gov/pubchem/patentipc/G06N3-08 http://rdf.ncbi.nlm.nih.gov/pubchem/patentipc/G06T11-00 |
| filingDate | 2020-12-10^^<http://www.w3.org/2001/XMLSchema#date> |
| inventor | http://rdf.ncbi.nlm.nih.gov/pubchem/patentinventor/MD5_af3d12926d2ad9ae3966e73653350551 http://rdf.ncbi.nlm.nih.gov/pubchem/patentinventor/MD5_5c965bce28749c0e244e8396514addef http://rdf.ncbi.nlm.nih.gov/pubchem/patentinventor/MD5_539f5de9c08a6d4360288d39a05ea97d http://rdf.ncbi.nlm.nih.gov/pubchem/patentinventor/MD5_a9d800b0087769087163015c9595ead2 http://rdf.ncbi.nlm.nih.gov/pubchem/patentinventor/MD5_7c9aa52273022aaf9f6bdb8127607a96 http://rdf.ncbi.nlm.nih.gov/pubchem/patentinventor/MD5_f6852b2ac50388f56b0aee9d13c807b2 http://rdf.ncbi.nlm.nih.gov/pubchem/patentinventor/MD5_5dd7f29a49e0b7df26a44ad5cd3122c5 |
| publicationDate | 2021-03-16^^<http://www.w3.org/2001/XMLSchema#date> |
| publicationNumber | CN-112508175-A |
| titleOfInvention | Multi-task learning generative adversarial network generation method and system for low-dose PET reconstruction |
| abstract | The present application relates to a multi-task learning-type generative confrontation network generation method and system for low-dose PET reconstruction, belonging to the technical field of deep learning. U-Net type image generator; generative adversarial network group generation, one-to-one correspondence between multiple image generators and multiple discriminators to obtain a set of generative adversarial network generation groups, and obtain a generative adversarial network group; get the first A multi-task learning generative adversarial network; a joint loss function l designed to improve imaging quality; according to the joint loss function l, combined with an optimizer, the first multi-task learning generative adversarial network is trained to obtain the second multi-task Learning Generative Adversarial Networks. Compared with the related art, the present application has the effect of improving the problems of low signal-to-noise ratio and loss of details in reconstructed low-dose PET images. |
| isCitedBy | http://rdf.ncbi.nlm.nih.gov/pubchem/patent/CN-113298807-A |
| priorityDate | 2020-12-10^^<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/SID426284978 http://rdf.ncbi.nlm.nih.gov/pubchem/compound/CID11501341 |
Showing number of triples: 1 to 24 of 24.