Predicate |
Object |
assignee |
http://rdf.ncbi.nlm.nih.gov/pubchem/patentassignee/MD5_ac31afbea1cbbb03498644721ffb4a62 http://rdf.ncbi.nlm.nih.gov/pubchem/patentassignee/MD5_2f31a75828117cf9907805b3508f6888 http://rdf.ncbi.nlm.nih.gov/pubchem/patentassignee/MD5_2245a05871e755490915da68b0c7bd31 |
classificationCPCAdditional |
http://rdf.ncbi.nlm.nih.gov/pubchem/patentcpc/G06T2207-30028 |
classificationCPCInventive |
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/G06T7-10 http://rdf.ncbi.nlm.nih.gov/pubchem/patentcpc/G06N3-045 http://rdf.ncbi.nlm.nih.gov/pubchem/patentcpc/G06F18-214 |
classificationIPCInventive |
http://rdf.ncbi.nlm.nih.gov/pubchem/patentipc/G06V10-764 http://rdf.ncbi.nlm.nih.gov/pubchem/patentipc/G06N3-08 http://rdf.ncbi.nlm.nih.gov/pubchem/patentipc/G06T7-10 http://rdf.ncbi.nlm.nih.gov/pubchem/patentipc/G06N3-04 http://rdf.ncbi.nlm.nih.gov/pubchem/patentipc/G06K9-62 http://rdf.ncbi.nlm.nih.gov/pubchem/patentipc/G06V10-774 |
filingDate |
2021-11-12-04:00^^<http://www.w3.org/2001/XMLSchema#date> |
inventor |
http://rdf.ncbi.nlm.nih.gov/pubchem/patentinventor/MD5_88bae865d621a6235625bace42c58b7e http://rdf.ncbi.nlm.nih.gov/pubchem/patentinventor/MD5_0690e1cdf436b5301c789d0bb747e2c2 http://rdf.ncbi.nlm.nih.gov/pubchem/patentinventor/MD5_0fc17190d6d9bd50fbec17011586f835 http://rdf.ncbi.nlm.nih.gov/pubchem/patentinventor/MD5_d957737cbe1c92414a25efca03b59c75 http://rdf.ncbi.nlm.nih.gov/pubchem/patentinventor/MD5_078c83ab09a16781fd71591eb3684588 http://rdf.ncbi.nlm.nih.gov/pubchem/patentinventor/MD5_4685ef74d1b38d6da78adc28d7c35725 http://rdf.ncbi.nlm.nih.gov/pubchem/patentinventor/MD5_634f226e1b33fda13b40ea04acf265bd http://rdf.ncbi.nlm.nih.gov/pubchem/patentinventor/MD5_b346290d50d5f1ab02e6f098c5be7976 http://rdf.ncbi.nlm.nih.gov/pubchem/patentinventor/MD5_a0cdc39f747c89fdbb66a811fcf826af http://rdf.ncbi.nlm.nih.gov/pubchem/patentinventor/MD5_d14ee794df19cdbc81553bbf14db0a18 |
publicationDate |
2022-02-25-04:00^^<http://www.w3.org/2001/XMLSchema#date> |
publicationNumber |
CN-114091591-A |
titleOfInvention |
A rapid intraoperative identification method of enteric ganglion cells based on knowledge distillation |
abstract |
The invention discloses an intraoperative rapid identification method for enteric ganglion cells based on knowledge distillation, comprising the following steps: collecting a hematoxylin-eosin-stained image data set of intestinal tissue slices of a dilated segment and performing preliminary image processing, as training data set; build an image segmentation model for image segmentation; use the training dataset to train an image segmentation network; build an image classification model; preprocess the training dataset again; use the reprocessed training dataset to classify the image model Carry out training; use the trained image segmentation model and image classification model to identify enteric ganglion cells, and obtain ganglion cell development and function grade assessment. The present invention reduces the model through knowledge distillation, and the model can achieve a better training effect on the basis of a small number of samples, and the trained model can achieve a fast and accurate recognition effect. |
priorityDate |
2021-11-12-04:00^^<http://www.w3.org/2001/XMLSchema#date> |
type |
http://data.epo.org/linked-data/def/patent/Publication |