Predicate |
Object |
assignee |
http://rdf.ncbi.nlm.nih.gov/pubchem/patentassignee/MD5_e2a522f5f37b570a64ab915ce8f7aaa6 |
classificationCPCAdditional |
http://rdf.ncbi.nlm.nih.gov/pubchem/patentcpc/G06T2207-10024 http://rdf.ncbi.nlm.nih.gov/pubchem/patentcpc/G06T2207-20084 http://rdf.ncbi.nlm.nih.gov/pubchem/patentcpc/G06T2207-20081 http://rdf.ncbi.nlm.nih.gov/pubchem/patentcpc/G06T2207-10056 http://rdf.ncbi.nlm.nih.gov/pubchem/patentcpc/G06T2207-30004 |
classificationCPCInventive |
http://rdf.ncbi.nlm.nih.gov/pubchem/patentcpc/G06T7-0004 http://rdf.ncbi.nlm.nih.gov/pubchem/patentcpc/G06T7-11 http://rdf.ncbi.nlm.nih.gov/pubchem/patentcpc/G06N3-045 http://rdf.ncbi.nlm.nih.gov/pubchem/patentcpc/G06T7-181 http://rdf.ncbi.nlm.nih.gov/pubchem/patentcpc/G06N3-08 http://rdf.ncbi.nlm.nih.gov/pubchem/patentcpc/G06T7-194 http://rdf.ncbi.nlm.nih.gov/pubchem/patentcpc/G06F18-241 http://rdf.ncbi.nlm.nih.gov/pubchem/patentcpc/G06V10-28 |
classificationIPCInventive |
http://rdf.ncbi.nlm.nih.gov/pubchem/patentipc/G06T7-11 http://rdf.ncbi.nlm.nih.gov/pubchem/patentipc/G06T7-00 http://rdf.ncbi.nlm.nih.gov/pubchem/patentipc/G06T7-194 http://rdf.ncbi.nlm.nih.gov/pubchem/patentipc/G06K9-62 http://rdf.ncbi.nlm.nih.gov/pubchem/patentipc/G06T7-181 http://rdf.ncbi.nlm.nih.gov/pubchem/patentipc/G06N3-04 http://rdf.ncbi.nlm.nih.gov/pubchem/patentipc/G06K9-38 http://rdf.ncbi.nlm.nih.gov/pubchem/patentipc/G06N3-08 |
filingDate |
2021-03-18-04:00^^<http://www.w3.org/2001/XMLSchema#date> |
inventor |
http://rdf.ncbi.nlm.nih.gov/pubchem/patentinventor/MD5_13fb26799b1a57d0a6c0e4fbeadccfdf http://rdf.ncbi.nlm.nih.gov/pubchem/patentinventor/MD5_6dcd3adc95bad22fb9013a8fbcda4f96 http://rdf.ncbi.nlm.nih.gov/pubchem/patentinventor/MD5_7baa38c141b67b228c21ea2adb0825dc |
publicationDate |
2021-06-15-04:00^^<http://www.w3.org/2001/XMLSchema#date> |
publicationNumber |
CN-112967262-A |
titleOfInvention |
A Urinary Sediment Cast Recognition Method Based on Morphological Segmentation and Deep Learning |
abstract |
A urine sediment cast identification method based on morphological segmentation and deep learning relates to the field of medical image processing and is used to solve the problems of high missed detection rate and false positive rate in the existing automatic identification of urinary sediment casts. The method includes the following steps : Use the color migration method to perform linear transformation on the original color urine sediment images taken to reduce the background color difference of the original images between different samples, maximally reduce the overall color span of the same type of cast, and make the data distribution of the same type of cast more concentrated; The morphological combination algorithm is used to segment the cast image after color migration, and the cast candidate region is obtained after preliminary screening; the candidate sub-images are rotated and Poisson fusion to synthesize the standard input image; the normalized image data Input Residual Neural Network The model performs network training and automatic classification. The invention has the beneficial effects that the robustness is better, the recognition rate is higher, and the missed detection rate and false positive rate of casts in the clinical detection of urinary sediment are greatly reduced. |
isCitedBy |
http://rdf.ncbi.nlm.nih.gov/pubchem/patent/CN-114494804-A http://rdf.ncbi.nlm.nih.gov/pubchem/patent/CN-114494804-B |
priorityDate |
2021-03-18-04:00^^<http://www.w3.org/2001/XMLSchema#date> |
type |
http://data.epo.org/linked-data/def/patent/Publication |