FRINK Linked Data Fragments server

Matches in SemOpenAlex for { <https://semopenalex.org/work/W3003558126> ?p ?o ?g. }

• W3003558126 endingPage "2720" @default.
• W3003558126 startingPage "2710" @default.
• W3003558126 abstract "Obtaining accurate segmentation of the prostate and nearby organs at risk (e.g., bladder and rectum) in CT images is critical for radiotherapy of prostate cancer. Currently, the leading automatic segmentation algorithms are based on Fully Convolutional Networks (FCNs), which achieve remarkable performance but usually need large-scale datasets with high-quality voxel-wise annotations for full supervision of the training. Unfortunately, such annotations are difficult to acquire, which becomes a bottleneck to build accurate segmentation models in real clinical applications. In this paper, we propose a novel weakly supervised segmentation approach that only needs 3D bounding box annotations covering the organs of interest to start the training. Obviously, the bounding box includes many non-organ voxels that carry noisy labels to mislead the segmentation model. To this end, we propose the label denoising module and embed it into the iterative training scheme of the label denoising network (LDnet) for segmentation. The labels of the training voxels are predicted by the tentative LDnet, while the label denoising module identifies the voxels with unreliable labels. As only the good training voxels are preserved, the iteratively re-trained LDnet can refine its segmentation capability gradually. Our results are remarkable, i.e., reaching <inline-formula xmlns:mml=http://www.w3.org/1998/Math/MathML xmlns:xlink=http://www.w3.org/1999/xlink><tex-math notation=LaTeX>$sim$</tex-math></inline-formula> 94% (prostate), <inline-formula xmlns:mml=http://www.w3.org/1998/Math/MathML xmlns:xlink=http://www.w3.org/1999/xlink><tex-math notation=LaTeX>$sim$</tex-math></inline-formula> 91% (bladder), and <inline-formula xmlns:mml=http://www.w3.org/1998/Math/MathML xmlns:xlink=http://www.w3.org/1999/xlink><tex-math notation=LaTeX>$sim$</tex-math></inline-formula> 86% (rectum) of the Dice Similarity Coefficients (DSCs), compared to the case of fully supervised learning upon high-quality voxel-wise annotations and also superior to several state-of-the-art approaches. To our best knowledge, this is the first work to achieve voxel-wise segmentation in CT images from simple 3D bounding box annotations, which can greatly reduce many labeling efforts and meet the demands of the practical clinical applications." @default.
• W3003558126 created "2020-02-07" @default.
• W3003558126 creator A5000937401 @default.
• W3003558126 creator A5046225712 @default.
• W3003558126 creator A5054666507 @default.
• W3003558126 creator A5077300873 @default.
• W3003558126 creator A5082878649 @default.
• W3003558126 creator A5083630052 @default.
• W3003558126 creator A5091407514 @default.
• W3003558126 date "2020-10-01" @default.
• W3003558126 modified "2023-09-27" @default.
• W3003558126 title "Iterative Label Denoising Network: Segmenting Male Pelvic Organs in CT From 3D Bounding Box Annotations" @default.
• W3003558126 cites W1495267108 @default.
• W3003558126 cites W1608700414 @default.
• W3003558126 cites W1903029394 @default.
• W3003558126 cites W1985161468 @default.
• W3003558126 cites W1985689242 @default.
• W3003558126 cites W2001992768 @default.
• W3003558126 cites W2016053056 @default.
• W3003558126 cites W2040029648 @default.
• W3003558126 cites W2065875833 @default.
• W3003558126 cites W2070493638 @default.
• W3003558126 cites W2088776202 @default.
• W3003558126 cites W2096470308 @default.
• W3003558126 cites W2116628223 @default.
• W3003558126 cites W2133515615 @default.
• W3003558126 cites W2194775991 @default.
• W3003558126 cites W2230799606 @default.
• W3003558126 cites W2296118542 @default.
• W3003558126 cites W2344669114 @default.
• W3003558126 cites W2344778348 @default.
• W3003558126 cites W2396622801 @default.
• W3003558126 cites W2410641892 @default.
• W3003558126 cites W2469003029 @default.
• W3003558126 cites W2516803306 @default.
• W3003558126 cites W2533800772 @default.
• W3003558126 cites W2552414813 @default.
• W3003558126 cites W2559348937 @default.
• W3003558126 cites W2559597482 @default.
• W3003558126 cites W2577784528 @default.
• W3003558126 cites W2589647984 @default.
• W3003558126 cites W2592929672 @default.
• W3003558126 cites W2732931556 @default.
• W3003558126 cites W2762363380 @default.
• W3003558126 cites W2769833683 @default.
• W3003558126 cites W2793399378 @default.
• W3003558126 cites W2799597343 @default.
• W3003558126 cites W2799738340 @default.
• W3003558126 cites W2800284869 @default.
• W3003558126 cites W28199049 @default.
• W3003558126 cites W2889147523 @default.
• W3003558126 cites W2923425487 @default.
• W3003558126 cites W2962914239 @default.
• W3003558126 cites W2963198662 @default.
• W3003558126 cites W2963668037 @default.
• W3003558126 cites W2963803174 @default.
• W3003558126 cites W2964309882 @default.
• W3003558126 cites W3103010481 @default.
• W3003558126 cites W3106105822 @default.
• W3003558126 cites W4248635988 @default.
• W3003558126 doi "https://doi.org/10.1109/tbme.2020.2969608" @default.
• W3003558126 hasPubMedCentralId "https://www.ncbi.nlm.nih.gov/pmc/articles/8195631" @default.
• W3003558126 hasPubMedId "https://pubmed.ncbi.nlm.nih.gov/31995472" @default.
• W3003558126 hasPublicationYear "2020" @default.
• W3003558126 type Work @default.
• W3003558126 sameAs 3003558126 @default.
• W3003558126 citedByCount "21" @default.
• W3003558126 countsByYear W30035581262020 @default.
• W3003558126 countsByYear W30035581262021 @default.
• W3003558126 countsByYear W30035581262022 @default.
• W3003558126 countsByYear W30035581262023 @default.
• W3003558126 crossrefType "journal-article" @default.
• W3003558126 hasAuthorship W3003558126A5000937401 @default.
• W3003558126 hasAuthorship W3003558126A5046225712 @default.
• W3003558126 hasAuthorship W3003558126A5054666507 @default.
• W3003558126 hasAuthorship W3003558126A5077300873 @default.
• W3003558126 hasAuthorship W3003558126A5082878649 @default.
• W3003558126 hasAuthorship W3003558126A5083630052 @default.
• W3003558126 hasAuthorship W3003558126A5091407514 @default.
• W3003558126 hasBestOaLocation W30035581262 @default.
• W3003558126 hasConcept C115961682 @default.
• W3003558126 hasConcept C147037132 @default.
• W3003558126 hasConcept C153180895 @default.
• W3003558126 hasConcept C154945302 @default.
• W3003558126 hasConcept C31972630 @default.
• W3003558126 hasConcept C41008148 @default.
• W3003558126 hasConcept C54170458 @default.
• W3003558126 hasConcept C63584917 @default.
• W3003558126 hasConcept C89600930 @default.
• W3003558126 hasConcept C99498987 @default.
• W3003558126 hasConceptScore W3003558126C115961682 @default.
• W3003558126 hasConceptScore W3003558126C147037132 @default.
• W3003558126 hasConceptScore W3003558126C153180895 @default.
• W3003558126 hasConceptScore W3003558126C154945302 @default.
• W3003558126 hasConceptScore W3003558126C31972630 @default.
• W3003558126 hasConceptScore W3003558126C41008148 @default.
• W3003558126 hasConceptScore W3003558126C54170458 @default.
• W3003558126 hasConceptScore W3003558126C63584917 @default.

• next