Matches in SemOpenAlex for { <https://semopenalex.org/work/W2890173316> ?p ?o ?g. }
Showing items 1 to 89 of
89
with 100 items per page.
- W2890173316 endingPage "539" @default.
- W2890173316 startingPage "531" @default.
- W2890173316 abstract "We propose a method for automatic segmentation of the prostate clinical target volume for brachytherapy in transrectal ultrasound (TRUS) images. Because of the large variability in the strength of image landmarks and characteristics of artifacts in TRUS images, existing methods achieve a poor worst-case performance, especially at the prostate base and apex. We aim at devising a method that produces accurate segmentations on easy and difficult images alike. Our method is based on a novel convolutional neural network (CNN) architecture. We propose two strategies for improving the segmentation accuracy on difficult images. First, we cluster the training images using a sparse subspace clustering method based on features learned with a convolutional autoencoder. Using this clustering, we suggest an adaptive sampling strategy that drives the training process to give more attention to images that are difficult to segment. Secondly, we train multiple CNN models using subsets of the training data. The disagreement within this CNN ensemble is used to estimate the segmentation uncertainty due to a lack of reliable landmarks. We employ a statistical shape model to improve the uncertain segmentations produced by the CNN ensemble. On test images from 225 subjects, our method achieves a Hausdorff distance of $$2.7,pm ,2.1$$ mm, Dice score of $$93.9,pm ,3.5$$ , and it significantly reduces the likelihood of committing large segmentation errors." @default.
- W2890173316 created "2018-09-27" @default.
- W2890173316 creator A5023095072 @default.
- W2890173316 creator A5028375560 @default.
- W2890173316 creator A5037044795 @default.
- W2890173316 creator A5049261765 @default.
- W2890173316 creator A5049350816 @default.
- W2890173316 creator A5058091444 @default.
- W2890173316 creator A5063201022 @default.
- W2890173316 creator A5076562643 @default.
- W2890173316 date "2018-01-01" @default.
- W2890173316 modified "2023-10-01" @default.
- W2890173316 title "Accurate and Robust Segmentation of the Clinical Target Volume for Prostate Brachytherapy" @default.
- W2890173316 cites W1901129140 @default.
- W2890173316 cites W1993962865 @default.
- W2890173316 cites W2051684526 @default.
- W2890173316 cites W2115629999 @default.
- W2890173316 cites W2145179397 @default.
- W2890173316 cites W2158378386 @default.
- W2890173316 cites W2963446712 @default.
- W2890173316 doi "https://doi.org/10.1007/978-3-030-00937-3_61" @default.
- W2890173316 hasPublicationYear "2018" @default.
- W2890173316 type Work @default.
- W2890173316 sameAs 2890173316 @default.
- W2890173316 citedByCount "5" @default.
- W2890173316 countsByYear W28901733162019 @default.
- W2890173316 countsByYear W28901733162020 @default.
- W2890173316 countsByYear W28901733162022 @default.
- W2890173316 countsByYear W28901733162023 @default.
- W2890173316 crossrefType "book-chapter" @default.
- W2890173316 hasAuthorship W2890173316A5023095072 @default.
- W2890173316 hasAuthorship W2890173316A5028375560 @default.
- W2890173316 hasAuthorship W2890173316A5037044795 @default.
- W2890173316 hasAuthorship W2890173316A5049261765 @default.
- W2890173316 hasAuthorship W2890173316A5049350816 @default.
- W2890173316 hasAuthorship W2890173316A5058091444 @default.
- W2890173316 hasAuthorship W2890173316A5063201022 @default.
- W2890173316 hasAuthorship W2890173316A5076562643 @default.
- W2890173316 hasConcept C101738243 @default.
- W2890173316 hasConcept C108583219 @default.
- W2890173316 hasConcept C124504099 @default.
- W2890173316 hasConcept C126322002 @default.
- W2890173316 hasConcept C153180895 @default.
- W2890173316 hasConcept C154945302 @default.
- W2890173316 hasConcept C2777416452 @default.
- W2890173316 hasConcept C2778648096 @default.
- W2890173316 hasConcept C31972630 @default.
- W2890173316 hasConcept C32834561 @default.
- W2890173316 hasConcept C41008148 @default.
- W2890173316 hasConcept C509974204 @default.
- W2890173316 hasConcept C71924100 @default.
- W2890173316 hasConcept C73555534 @default.
- W2890173316 hasConcept C81363708 @default.
- W2890173316 hasConcept C89600930 @default.
- W2890173316 hasConceptScore W2890173316C101738243 @default.
- W2890173316 hasConceptScore W2890173316C108583219 @default.
- W2890173316 hasConceptScore W2890173316C124504099 @default.
- W2890173316 hasConceptScore W2890173316C126322002 @default.
- W2890173316 hasConceptScore W2890173316C153180895 @default.
- W2890173316 hasConceptScore W2890173316C154945302 @default.
- W2890173316 hasConceptScore W2890173316C2777416452 @default.
- W2890173316 hasConceptScore W2890173316C2778648096 @default.
- W2890173316 hasConceptScore W2890173316C31972630 @default.
- W2890173316 hasConceptScore W2890173316C32834561 @default.
- W2890173316 hasConceptScore W2890173316C41008148 @default.
- W2890173316 hasConceptScore W2890173316C509974204 @default.
- W2890173316 hasConceptScore W2890173316C71924100 @default.
- W2890173316 hasConceptScore W2890173316C73555534 @default.
- W2890173316 hasConceptScore W2890173316C81363708 @default.
- W2890173316 hasConceptScore W2890173316C89600930 @default.
- W2890173316 hasLocation W28901733161 @default.
- W2890173316 hasOpenAccess W2890173316 @default.
- W2890173316 hasPrimaryLocation W28901733161 @default.
- W2890173316 hasRelatedWork W2669956259 @default.
- W2890173316 hasRelatedWork W2731899572 @default.
- W2890173316 hasRelatedWork W2960184797 @default.
- W2890173316 hasRelatedWork W3116150086 @default.
- W2890173316 hasRelatedWork W3133861977 @default.
- W2890173316 hasRelatedWork W4200173597 @default.
- W2890173316 hasRelatedWork W4285827401 @default.
- W2890173316 hasRelatedWork W4287995534 @default.
- W2890173316 hasRelatedWork W4312417841 @default.
- W2890173316 hasRelatedWork W4321369474 @default.
- W2890173316 isParatext "false" @default.
- W2890173316 isRetracted "false" @default.
- W2890173316 magId "2890173316" @default.
- W2890173316 workType "book-chapter" @default.