FRINK Linked Data Fragments server

Matches in SemOpenAlex for { <https://semopenalex.org/work/W3159284873> ?p ?o ?g. }

• W3159284873 abstract "Weakly supervised segmentation is an important problem in medical image analysis due to the high cost of pixelwise annotation. Prior methods, while often focusing on weak labels of 2D images, exploit few structural cues of volumetric medical images. To address this, we propose a novel weakly-supervised segmentation strategy capable of better capturing 3D shape prior in both model prediction and learning. Our main idea is to extract a self-taught shape representation by leveraging weak labels, and then integrate this representation into segmentation prediction for shape refinement. To this end, we design a deep network consisting of a segmentation module and a shape denoising module, which are trained by an iterative learning strategy. Moreover, we introduce a weak annotation scheme with a hybrid label design for volumetric images, which improves model learning without increasing the overall annotation cost. The empirical experiments show that our approach outperforms existing SOTA strategies on three organ segmentation benchmarks with distinctive shape properties. Notably, we can achieve strong performance with even 10% labeled slices, which is significantly superior to other methods." @default.
• W3159284873 created "2021-05-10" @default.
• W3159284873 creator A5015970030 @default.
• W3159284873 creator A5059293587 @default.
• W3159284873 creator A5088148603 @default.
• W3159284873 date "2021-04-27" @default.
• W3159284873 modified "2023-09-27" @default.
• W3159284873 title "Weakly Supervised Volumetric Segmentation via Self-taught Shape Denoising Model" @default.
• W3159284873 cites W1495267108 @default.
• W3159284873 cites W1586079445 @default.
• W3159284873 cites W1783315696 @default.
• W3159284873 cites W1945608308 @default.
• W3159284873 cites W2031489346 @default.
• W3159284873 cites W2106033751 @default.
• W3159284873 cites W2109693548 @default.
• W3159284873 cites W2115575686 @default.
• W3159284873 cites W2122922389 @default.
• W3159284873 cites W2145094598 @default.
• W3159284873 cites W2221898772 @default.
• W3159284873 cites W2306289963 @default.
• W3159284873 cites W2337429362 @default.
• W3159284873 cites W2396622801 @default.
• W3159284873 cites W2552414813 @default.
• W3159284873 cites W2563833337 @default.
• W3159284873 cites W2606831796 @default.
• W3159284873 cites W2620296437 @default.
• W3159284873 cites W2799124825 @default.
• W3159284873 cites W2799738340 @default.
• W3159284873 cites W2895439318 @default.
• W3159284873 cites W2909704326 @default.
• W3159284873 cites W2950476796 @default.
• W3159284873 cites W2952289000 @default.
• W3159284873 cites W2952461140 @default.
• W3159284873 cites W2956648669 @default.
• W3159284873 cites W2962885625 @default.
• W3159284873 cites W2962914239 @default.
• W3159284873 cites W2963072537 @default.
• W3159284873 cites W2963687373 @default.
• W3159284873 cites W2979770789 @default.
• W3159284873 cites W2993018413 @default.
• W3159284873 cites W3015272069 @default.
• W3159284873 cites W3017788695 @default.
• W3159284873 cites W3034333089 @default.
• W3159284873 cites W3040243606 @default.
• W3159284873 cites W3042302007 @default.
• W3159284873 cites W3047498618 @default.
• W3159284873 cites W3100040694 @default.
• W3159284873 cites W3112701542 @default.
• W3159284873 cites W611457968 @default.
• W3159284873 hasPublicationYear "2021" @default.
• W3159284873 type Work @default.
• W3159284873 sameAs 3159284873 @default.
• W3159284873 citedByCount "0" @default.
• W3159284873 crossrefType "posted-content" @default.
• W3159284873 hasAuthorship W3159284873A5015970030 @default.
• W3159284873 hasAuthorship W3159284873A5059293587 @default.
• W3159284873 hasAuthorship W3159284873A5088148603 @default.
• W3159284873 hasConcept C119857082 @default.
• W3159284873 hasConcept C124504099 @default.
• W3159284873 hasConcept C134306372 @default.
• W3159284873 hasConcept C153180895 @default.
• W3159284873 hasConcept C154945302 @default.
• W3159284873 hasConcept C165696696 @default.
• W3159284873 hasConcept C17744445 @default.
• W3159284873 hasConcept C199539241 @default.
• W3159284873 hasConcept C2776321320 @default.
• W3159284873 hasConcept C2776359362 @default.
• W3159284873 hasConcept C31972630 @default.
• W3159284873 hasConcept C33923547 @default.
• W3159284873 hasConcept C38652104 @default.
• W3159284873 hasConcept C41008148 @default.
• W3159284873 hasConcept C77618280 @default.
• W3159284873 hasConcept C89600930 @default.
• W3159284873 hasConcept C94625758 @default.
• W3159284873 hasConceptScore W3159284873C119857082 @default.
• W3159284873 hasConceptScore W3159284873C124504099 @default.
• W3159284873 hasConceptScore W3159284873C134306372 @default.
• W3159284873 hasConceptScore W3159284873C153180895 @default.
• W3159284873 hasConceptScore W3159284873C154945302 @default.
• W3159284873 hasConceptScore W3159284873C165696696 @default.
• W3159284873 hasConceptScore W3159284873C17744445 @default.
• W3159284873 hasConceptScore W3159284873C199539241 @default.
• W3159284873 hasConceptScore W3159284873C2776321320 @default.
• W3159284873 hasConceptScore W3159284873C2776359362 @default.
• W3159284873 hasConceptScore W3159284873C31972630 @default.
• W3159284873 hasConceptScore W3159284873C33923547 @default.
• W3159284873 hasConceptScore W3159284873C38652104 @default.
• W3159284873 hasConceptScore W3159284873C41008148 @default.
• W3159284873 hasConceptScore W3159284873C77618280 @default.
• W3159284873 hasConceptScore W3159284873C89600930 @default.
• W3159284873 hasConceptScore W3159284873C94625758 @default.
• W3159284873 hasLocation W31592848731 @default.
• W3159284873 hasOpenAccess W3159284873 @default.
• W3159284873 hasPrimaryLocation W31592848731 @default.
• W3159284873 hasRelatedWork W1945608308 @default.
• W3159284873 hasRelatedWork W2117132237 @default.
• W3159284873 hasRelatedWork W2121147683 @default.
• W3159284873 hasRelatedWork W2931673846 @default.
• W3159284873 hasRelatedWork W2953122916 @default.
• W3159284873 hasRelatedWork W2979980586 @default.

• next