Predicate |
Object |
assignee |
http://rdf.ncbi.nlm.nih.gov/pubchem/patentassignee/MD5_f84ee979ca4ddd6b7311193dd3fca7d9 |
classificationCPCAdditional |
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/G06T2207-30041 http://rdf.ncbi.nlm.nih.gov/pubchem/patentcpc/G06T2207-30101 |
classificationCPCInventive |
http://rdf.ncbi.nlm.nih.gov/pubchem/patentcpc/G06N3-084 http://rdf.ncbi.nlm.nih.gov/pubchem/patentcpc/G06T7-11 |
classificationIPCInventive |
http://rdf.ncbi.nlm.nih.gov/pubchem/patentipc/G06T7-11 http://rdf.ncbi.nlm.nih.gov/pubchem/patentipc/G06N3-04 http://rdf.ncbi.nlm.nih.gov/pubchem/patentipc/G06N3-08 |
filingDate |
2022-05-18-04:00^^<http://www.w3.org/2001/XMLSchema#date> |
inventor |
http://rdf.ncbi.nlm.nih.gov/pubchem/patentinventor/MD5_c4b0eb5e006dd1a1822944ca70575d5d http://rdf.ncbi.nlm.nih.gov/pubchem/patentinventor/MD5_bd4d0af75cecb19b94014ac98cad0f16 http://rdf.ncbi.nlm.nih.gov/pubchem/patentinventor/MD5_822c6625c33ab903915880ec659b1b3b http://rdf.ncbi.nlm.nih.gov/pubchem/patentinventor/MD5_b89901bb266e53185b51382a877404c2 http://rdf.ncbi.nlm.nih.gov/pubchem/patentinventor/MD5_7b7f31a7aa3c9cf82f173c8db490eb2e http://rdf.ncbi.nlm.nih.gov/pubchem/patentinventor/MD5_113ed7e45e88d1c28e2292584fc0c68e http://rdf.ncbi.nlm.nih.gov/pubchem/patentinventor/MD5_a52e53c8fa8a5cb802359dc97a97a6a5 |
publicationDate |
2022-10-18-04:00^^<http://www.w3.org/2001/XMLSchema#date> |
publicationNumber |
CN-115205308-A |
titleOfInvention |
A method for segmentation of blood vessels in fundus images based on linear filtering and deep learning |
abstract |
The invention relates to a fundus image blood vessel segmentation method based on linear filtering and deep learning, and belongs to the field of medical image processing. The method includes: S1: input the fundus image, use the linear filtering algorithm based on Hessian matrix to enhance the blood vessel area; S2: use MobileNetV3 as the basic model of the blood vessel segmentation model, establish a segmentation network VSegNet, and then add recursion-based segmentation network VSegNet to the segmentation network VSegNet. The encoder of the module performs downsampling; S3: Add a decoder to the segmentation network VSegNet to upsample and aggregate the feature map output by the encoder; S4: When training the segmentation network VsegNet, use the segmentation prediction result and segment the L1 of the ground-truth image. The norm calculates the loss value of the segmentation result. The present invention enhances the feature information extraction capability, thereby improving the model segmentation performance. |
priorityDate |
2022-05-18-04:00^^<http://www.w3.org/2001/XMLSchema#date> |
type |
http://data.epo.org/linked-data/def/patent/Publication |