http://rdf.ncbi.nlm.nih.gov/pubchem/patent/CN-114041776-A
Outgoing Links
Predicate | Object |
---|---|
assignee | http://rdf.ncbi.nlm.nih.gov/pubchem/patentassignee/MD5_b4711b7defc1422cdb7f86d2c95657bf |
classificationCPCInventive | http://rdf.ncbi.nlm.nih.gov/pubchem/patentcpc/G06N3-088 http://rdf.ncbi.nlm.nih.gov/pubchem/patentcpc/A61B5-0033 http://rdf.ncbi.nlm.nih.gov/pubchem/patentcpc/G06T11-008 http://rdf.ncbi.nlm.nih.gov/pubchem/patentcpc/A61B5-055 http://rdf.ncbi.nlm.nih.gov/pubchem/patentcpc/G06N3-08 http://rdf.ncbi.nlm.nih.gov/pubchem/patentcpc/G06N3-045 |
classificationIPCInventive | http://rdf.ncbi.nlm.nih.gov/pubchem/patentipc/A61B5-055 http://rdf.ncbi.nlm.nih.gov/pubchem/patentipc/G06N3-04 http://rdf.ncbi.nlm.nih.gov/pubchem/patentipc/G06T11-00 http://rdf.ncbi.nlm.nih.gov/pubchem/patentipc/G06N3-08 |
filingDate | 2021-10-28-04:00^^<http://www.w3.org/2001/XMLSchema#date> |
inventor | http://rdf.ncbi.nlm.nih.gov/pubchem/patentinventor/MD5_58db9f42eaf8cf1ac0559f58a45257f9 http://rdf.ncbi.nlm.nih.gov/pubchem/patentinventor/MD5_66155b387a3fcceed2bbb627ffc4cae8 http://rdf.ncbi.nlm.nih.gov/pubchem/patentinventor/MD5_981eaaa304a8bdd4f092f8fde40666ee |
publicationDate | 2022-02-15-04:00^^<http://www.w3.org/2001/XMLSchema#date> |
publicationNumber | CN-114041776-A |
titleOfInvention | A deep learning-based EPI phase correction method |
abstract | The invention discloses an EPI phase correction method based on deep learning. The method of the invention is as follows: the positive and negative readout gradient polarities are used for EPI data acquisition, and the collected echoes are sequentially filled into the trajectory after the K space; the positive and negative echoes are separated from the K space and become two polarities. K-space with consistent consistency; eliminate the curling artifacts in the above images, the process includes: selecting a neural network; collecting a set of EPI raw data for network training; using traditional phase correction methods to calculate the gold standard image; The separated images are fed into the neural network for training at the same time; the images obtained by separating and reconstructing the test data according to positive and negative echoes are fed into the trained network model to obtain the restored images. The invention can restore low-magnification and under-acquisition data well, realize EPI acquisition acceleration and image artifact elimination, and can be used in magnetic resonance technologies such as brain function imaging and diffusion weighted imaging based on the EPI acquisition mode. |
priorityDate | 2021-10-28-04:00^^<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/SID482532689 http://rdf.ncbi.nlm.nih.gov/pubchem/compound/CID23985 |
Total number of triples: 23.