Matches in SemOpenAlex for { <https://semopenalex.org/work/W3204436700> ?p ?o ?g. }
- W3204436700 abstract "Deep learning networks have shown promising performance for object localization in medical images, but require large amount of annotated data for supervised training. To address this problem, we propose: 1) A novel contrastive learning method which embeds the anatomical structure by predicting the Relative Position Regression (RPR) between any two patches from the same volume; 2) An one-shot framework for organ and landmark localization in volumetric medical images. Our main idea comes from that tissues and organs from different human bodies own similar relative position and context. Therefore, we could predict the relative positions of their non-local patches, thus locate the target organ. Our one-shot localization framework is composed of three parts: 1) A deep network trained to project the input patch into a 3D latent vector, representing its anatomical position; 2) A coarse-to-fine framework contains two projection networks, providing more accurate localization of the target; 3) Based on the coarse-to-fine model, we transfer the organ bounding-box (B-box) detection to locating six extreme points along x, y and z directions in the query volume. Experiments on multi-organ localization from head-and-neck (HaN) and abdominal CT volumes showed that our method acquired competitive performance in real time, which is more accurate and (10^5) times faster than template matching methods with the same setting for one-shot localization in 3D medical images. Code is available at https://github.com/HiLab-git/RPR-Loc." @default.
- W3204436700 created "2021-10-11" @default.
- W3204436700 creator A5015311773 @default.
- W3204436700 creator A5029722566 @default.
- W3204436700 creator A5031351839 @default.
- W3204436700 creator A5044649168 @default.
- W3204436700 creator A5053013664 @default.
- W3204436700 creator A5066553616 @default.
- W3204436700 creator A5087462974 @default.
- W3204436700 date "2021-01-01" @default.
- W3204436700 modified "2023-09-27" @default.
- W3204436700 title "Contrastive Learning of Relative Position Regression for One-Shot Object Localization in 3D Medical Images" @default.
- W3204436700 cites W1994488211 @default.
- W3204436700 cites W2115733720 @default.
- W3204436700 cites W2121835671 @default.
- W3204436700 cites W2171447090 @default.
- W3204436700 cites W2592903734 @default.
- W3204436700 cites W2593013519 @default.
- W3204436700 cites W2724710774 @default.
- W3204436700 cites W2790270334 @default.
- W3204436700 cites W2912564039 @default.
- W3204436700 cites W2957780123 @default.
- W3204436700 cites W2979708377 @default.
- W3204436700 cites W2979784156 @default.
- W3204436700 cites W2991533698 @default.
- W3204436700 cites W3012573144 @default.
- W3204436700 cites W3023371261 @default.
- W3204436700 cites W3034199407 @default.
- W3204436700 cites W3035406940 @default.
- W3204436700 cites W3108655343 @default.
- W3204436700 cites W855272188 @default.
- W3204436700 doi "https://doi.org/10.1007/978-3-030-87196-3_15" @default.
- W3204436700 hasPublicationYear "2021" @default.
- W3204436700 type Work @default.
- W3204436700 sameAs 3204436700 @default.
- W3204436700 citedByCount "3" @default.
- W3204436700 countsByYear W32044367002021 @default.
- W3204436700 countsByYear W32044367002022 @default.
- W3204436700 crossrefType "book-chapter" @default.
- W3204436700 hasAuthorship W3204436700A5015311773 @default.
- W3204436700 hasAuthorship W3204436700A5029722566 @default.
- W3204436700 hasAuthorship W3204436700A5031351839 @default.
- W3204436700 hasAuthorship W3204436700A5044649168 @default.
- W3204436700 hasAuthorship W3204436700A5053013664 @default.
- W3204436700 hasAuthorship W3204436700A5066553616 @default.
- W3204436700 hasAuthorship W3204436700A5087462974 @default.
- W3204436700 hasBestOaLocation W32044367002 @default.
- W3204436700 hasConcept C10138342 @default.
- W3204436700 hasConcept C105795698 @default.
- W3204436700 hasConcept C108583219 @default.
- W3204436700 hasConcept C11413529 @default.
- W3204436700 hasConcept C115961682 @default.
- W3204436700 hasConcept C147037132 @default.
- W3204436700 hasConcept C151730666 @default.
- W3204436700 hasConcept C153180895 @default.
- W3204436700 hasConcept C154945302 @default.
- W3204436700 hasConcept C162324750 @default.
- W3204436700 hasConcept C165064840 @default.
- W3204436700 hasConcept C198082294 @default.
- W3204436700 hasConcept C2776321320 @default.
- W3204436700 hasConcept C2779343474 @default.
- W3204436700 hasConcept C2780297707 @default.
- W3204436700 hasConcept C2781238097 @default.
- W3204436700 hasConcept C31972630 @default.
- W3204436700 hasConcept C33923547 @default.
- W3204436700 hasConcept C41008148 @default.
- W3204436700 hasConcept C57493831 @default.
- W3204436700 hasConcept C86803240 @default.
- W3204436700 hasConceptScore W3204436700C10138342 @default.
- W3204436700 hasConceptScore W3204436700C105795698 @default.
- W3204436700 hasConceptScore W3204436700C108583219 @default.
- W3204436700 hasConceptScore W3204436700C11413529 @default.
- W3204436700 hasConceptScore W3204436700C115961682 @default.
- W3204436700 hasConceptScore W3204436700C147037132 @default.
- W3204436700 hasConceptScore W3204436700C151730666 @default.
- W3204436700 hasConceptScore W3204436700C153180895 @default.
- W3204436700 hasConceptScore W3204436700C154945302 @default.
- W3204436700 hasConceptScore W3204436700C162324750 @default.
- W3204436700 hasConceptScore W3204436700C165064840 @default.
- W3204436700 hasConceptScore W3204436700C198082294 @default.
- W3204436700 hasConceptScore W3204436700C2776321320 @default.
- W3204436700 hasConceptScore W3204436700C2779343474 @default.
- W3204436700 hasConceptScore W3204436700C2780297707 @default.
- W3204436700 hasConceptScore W3204436700C2781238097 @default.
- W3204436700 hasConceptScore W3204436700C31972630 @default.
- W3204436700 hasConceptScore W3204436700C33923547 @default.
- W3204436700 hasConceptScore W3204436700C41008148 @default.
- W3204436700 hasConceptScore W3204436700C57493831 @default.
- W3204436700 hasConceptScore W3204436700C86803240 @default.
- W3204436700 hasLocation W32044367001 @default.
- W3204436700 hasLocation W32044367002 @default.
- W3204436700 hasOpenAccess W3204436700 @default.
- W3204436700 hasPrimaryLocation W32044367001 @default.
- W3204436700 hasRelatedWork W11321453 @default.
- W3204436700 hasRelatedWork W11383935 @default.
- W3204436700 hasRelatedWork W1549638 @default.
- W3204436700 hasRelatedWork W1770442 @default.
- W3204436700 hasRelatedWork W2655801 @default.
- W3204436700 hasRelatedWork W2988963 @default.
- W3204436700 hasRelatedWork W4266367 @default.