Matches in SemOpenAlex for { <https://semopenalex.org/work/W3107103656> ?p ?o ?g. }
Showing items 1 to 74 of
74
with 100 items per page.
- W3107103656 endingPage "3652" @default.
- W3107103656 startingPage "3648" @default.
- W3107103656 abstract "Manual recognition of the cerebrum tumor for malignant growth determination from MRI pictures is a troublesome, repetitive and tedious assignment. The precision and the power of cerebrum Tumor discovery in this way, are significant for the determination, treatment arranging, and treatment result assessment. Generally, the programmed cerebrum tumor location techniques use hand structured highlights. Correspondingly, customary strategies for profound learning, for example, ordinary neural systems require a lot of commented on information to learn from, which is frequently hard to acquire in clinical area. Here, we portray another model two-pathway-bunch CNN (Convolutional Neural Network) design for cerebrum tumor recognition, which misuses neighborhood highlights and worldwide relevant highlights at the same time. This model implements equivariance in the two-pathway CNN model to decrease dangers and over fitting parameter sharing. At last, we implant the course engineering into two-pathway-brunch CNN in which the yield of an essential CNN is treated as an extra source and connected at the last year. Approval of the model on BRATS2013 and BRATS2015 information collections uncovered that inserting of a gathering CNN in to a two pathway engineering improved the general execution over the as of now distributed best in class while computational multifaceted nature stays alluring." @default.
- W3107103656 created "2020-12-07" @default.
- W3107103656 creator A5049158053 @default.
- W3107103656 creator A5050786357 @default.
- W3107103656 creator A5054939296 @default.
- W3107103656 creator A5073764061 @default.
- W3107103656 date "2020-08-01" @default.
- W3107103656 modified "2023-10-06" @default.
- W3107103656 title "Brain Tumor Segmentation Using Deep Learning" @default.
- W3107103656 cites W2302541206 @default.
- W3107103656 cites W2310992461 @default.
- W3107103656 cites W2473661711 @default.
- W3107103656 cites W2777439179 @default.
- W3107103656 cites W2892854744 @default.
- W3107103656 cites W2929906044 @default.
- W3107103656 cites W2946489756 @default.
- W3107103656 cites W2995003683 @default.
- W3107103656 cites W3005533972 @default.
- W3107103656 doi "https://doi.org/10.1166/jctn.2020.9247" @default.
- W3107103656 hasPublicationYear "2020" @default.
- W3107103656 type Work @default.
- W3107103656 sameAs 3107103656 @default.
- W3107103656 citedByCount "2" @default.
- W3107103656 countsByYear W31071036562023 @default.
- W3107103656 crossrefType "journal-article" @default.
- W3107103656 hasAuthorship W3107103656A5049158053 @default.
- W3107103656 hasAuthorship W3107103656A5050786357 @default.
- W3107103656 hasAuthorship W3107103656A5054939296 @default.
- W3107103656 hasAuthorship W3107103656A5073764061 @default.
- W3107103656 hasConcept C108583219 @default.
- W3107103656 hasConcept C119857082 @default.
- W3107103656 hasConcept C153180895 @default.
- W3107103656 hasConcept C154945302 @default.
- W3107103656 hasConcept C169760540 @default.
- W3107103656 hasConcept C2777212361 @default.
- W3107103656 hasConcept C41008148 @default.
- W3107103656 hasConcept C529278444 @default.
- W3107103656 hasConcept C533869091 @default.
- W3107103656 hasConcept C81363708 @default.
- W3107103656 hasConcept C86803240 @default.
- W3107103656 hasConcept C89600930 @default.
- W3107103656 hasConceptScore W3107103656C108583219 @default.
- W3107103656 hasConceptScore W3107103656C119857082 @default.
- W3107103656 hasConceptScore W3107103656C153180895 @default.
- W3107103656 hasConceptScore W3107103656C154945302 @default.
- W3107103656 hasConceptScore W3107103656C169760540 @default.
- W3107103656 hasConceptScore W3107103656C2777212361 @default.
- W3107103656 hasConceptScore W3107103656C41008148 @default.
- W3107103656 hasConceptScore W3107103656C529278444 @default.
- W3107103656 hasConceptScore W3107103656C533869091 @default.
- W3107103656 hasConceptScore W3107103656C81363708 @default.
- W3107103656 hasConceptScore W3107103656C86803240 @default.
- W3107103656 hasConceptScore W3107103656C89600930 @default.
- W3107103656 hasIssue "8" @default.
- W3107103656 hasLocation W31071036561 @default.
- W3107103656 hasOpenAccess W3107103656 @default.
- W3107103656 hasPrimaryLocation W31071036561 @default.
- W3107103656 hasRelatedWork W2731899572 @default.
- W3107103656 hasRelatedWork W2790662084 @default.
- W3107103656 hasRelatedWork W2999805992 @default.
- W3107103656 hasRelatedWork W3116150086 @default.
- W3107103656 hasRelatedWork W3133861977 @default.
- W3107103656 hasRelatedWork W4200173597 @default.
- W3107103656 hasRelatedWork W4291897433 @default.
- W3107103656 hasRelatedWork W4312417841 @default.
- W3107103656 hasRelatedWork W4321369474 @default.
- W3107103656 hasRelatedWork W4380075502 @default.
- W3107103656 hasVolume "17" @default.
- W3107103656 isParatext "false" @default.
- W3107103656 isRetracted "false" @default.
- W3107103656 magId "3107103656" @default.
- W3107103656 workType "article" @default.