Matches in SemOpenAlex for { <https://semopenalex.org/work/W3105334672> ?p ?o ?g. }
Showing items 1 to 88 of
88
with 100 items per page.
- W3105334672 endingPage "107756" @default.
- W3105334672 startingPage "107756" @default.
- W3105334672 abstract "Accurate boundary segmentation in medical images is significant yet challenging due to large variation of shape, size and appearance within intra- and inter- samples. In this paper, we present a novel deep model termed as Crossover-Net for robust segmentation in medical images. The proposed model is inspired by an interesting observation – the features learned from horizontal and vertical directions can provide informative and complement contextual information to enhance discriminative ability between different tissues. Specifically, we first originally propose a cross-shaped patch, namely crossover-patch which consists of a pair of (orthogonal and overlapping) vertical and horizontal patches. Then, we develop our Crossover-Net to learn the vertical and horizontal crossover relation according to the proposed crossover-patches. To train our model end-to-end, we design a novel loss function to (1) impose the consistency on overlapping region of vertical and horizontal patches and (2) preserve the diversity on their non-overlapping regions. We have extensively evaluated our method on CT kidney tumor, MR cardiac, and X-ray breast mass segmentation tasks, showing promising results compared with the current state-of-the-art methods. The code is available at https://github.com/Qianyu1226/Crossover-Net." @default.
- W3105334672 created "2020-11-23" @default.
- W3105334672 creator A5021953784 @default.
- W3105334672 creator A5029636169 @default.
- W3105334672 creator A5048487219 @default.
- W3105334672 creator A5051649145 @default.
- W3105334672 creator A5055917015 @default.
- W3105334672 creator A5074250521 @default.
- W3105334672 date "2021-05-01" @default.
- W3105334672 modified "2023-10-06" @default.
- W3105334672 title "Crossover-Net: Leveraging vertical-horizontal crossover relation for robust medical image segmentation" @default.
- W3105334672 cites W1254779325 @default.
- W3105334672 cites W2029098063 @default.
- W3105334672 cites W2161640927 @default.
- W3105334672 cites W2301358467 @default.
- W3105334672 cites W2464708700 @default.
- W3105334672 cites W2589647984 @default.
- W3105334672 cites W2732063980 @default.
- W3105334672 cites W2888570268 @default.
- W3105334672 cites W2895056585 @default.
- W3105334672 cites W2905713042 @default.
- W3105334672 cites W2917055433 @default.
- W3105334672 cites W2952222533 @default.
- W3105334672 cites W2964227007 @default.
- W3105334672 cites W2964307255 @default.
- W3105334672 cites W304373761 @default.
- W3105334672 cites W3100331755 @default.
- W3105334672 cites W3101874879 @default.
- W3105334672 cites W3103010481 @default.
- W3105334672 cites W3104258355 @default.
- W3105334672 doi "https://doi.org/10.1016/j.patcog.2020.107756" @default.
- W3105334672 hasPublicationYear "2021" @default.
- W3105334672 type Work @default.
- W3105334672 sameAs 3105334672 @default.
- W3105334672 citedByCount "18" @default.
- W3105334672 countsByYear W31053346722021 @default.
- W3105334672 countsByYear W31053346722022 @default.
- W3105334672 countsByYear W31053346722023 @default.
- W3105334672 crossrefType "journal-article" @default.
- W3105334672 hasAuthorship W3105334672A5021953784 @default.
- W3105334672 hasAuthorship W3105334672A5029636169 @default.
- W3105334672 hasAuthorship W3105334672A5048487219 @default.
- W3105334672 hasAuthorship W3105334672A5051649145 @default.
- W3105334672 hasAuthorship W3105334672A5055917015 @default.
- W3105334672 hasAuthorship W3105334672A5074250521 @default.
- W3105334672 hasConcept C11413529 @default.
- W3105334672 hasConcept C122507166 @default.
- W3105334672 hasConcept C124504099 @default.
- W3105334672 hasConcept C134306372 @default.
- W3105334672 hasConcept C153180895 @default.
- W3105334672 hasConcept C154945302 @default.
- W3105334672 hasConcept C31972630 @default.
- W3105334672 hasConcept C33923547 @default.
- W3105334672 hasConcept C41008148 @default.
- W3105334672 hasConcept C62354387 @default.
- W3105334672 hasConcept C89600930 @default.
- W3105334672 hasConceptScore W3105334672C11413529 @default.
- W3105334672 hasConceptScore W3105334672C122507166 @default.
- W3105334672 hasConceptScore W3105334672C124504099 @default.
- W3105334672 hasConceptScore W3105334672C134306372 @default.
- W3105334672 hasConceptScore W3105334672C153180895 @default.
- W3105334672 hasConceptScore W3105334672C154945302 @default.
- W3105334672 hasConceptScore W3105334672C31972630 @default.
- W3105334672 hasConceptScore W3105334672C33923547 @default.
- W3105334672 hasConceptScore W3105334672C41008148 @default.
- W3105334672 hasConceptScore W3105334672C62354387 @default.
- W3105334672 hasConceptScore W3105334672C89600930 @default.
- W3105334672 hasFunder F4320321001 @default.
- W3105334672 hasLocation W31053346721 @default.
- W3105334672 hasOpenAccess W3105334672 @default.
- W3105334672 hasPrimaryLocation W31053346721 @default.
- W3105334672 hasRelatedWork W1522196789 @default.
- W3105334672 hasRelatedWork W1943663474 @default.
- W3105334672 hasRelatedWork W1978349322 @default.
- W3105334672 hasRelatedWork W2110294633 @default.
- W3105334672 hasRelatedWork W2306830238 @default.
- W3105334672 hasRelatedWork W2347477706 @default.
- W3105334672 hasRelatedWork W2392589811 @default.
- W3105334672 hasRelatedWork W2630967916 @default.
- W3105334672 hasRelatedWork W2969059916 @default.
- W3105334672 hasRelatedWork W4299389082 @default.
- W3105334672 hasVolume "113" @default.
- W3105334672 isParatext "false" @default.
- W3105334672 isRetracted "false" @default.
- W3105334672 magId "3105334672" @default.
- W3105334672 workType "article" @default.