Matches in SemOpenAlex for { <https://semopenalex.org/work/W317170363> ?p ?o ?g. }
Showing items 1 to 91 of
91
with 100 items per page.
- W317170363 endingPage "527" @default.
- W317170363 startingPage "520" @default.
- W317170363 abstract "Automated Lymph Node (LN) detection is an important clinical diagnostic task but very challenging due to the low contrast of surrounding structures in Computed Tomography (CT) and to their varying sizes, poses, shapes and sparsely distributed locations. State-of-the-art studies show the performance range of 52.9% sensitivity at 3.1 false-positives per volume (FP/vol.), or 60.9% at 6.1 FP/vol. for mediastinal LN, by one-shot boosting on 3D HAAR features. In this paper, we first operate a preliminary candidate generation stage, towards 100% sensitivity at the cost of high FP levels (40 per patient), to harvest volumes of interest (VOI). Our 2.5D approach consequently decomposes any 3D VOI by resampling 2D reformatted orthogonal views N times, via scale, random translations, and rotations with respect to the VOI centroid coordinates. These random views are then used to train a deep Convolutional Neural Network (CNN) classifier. In testing, the CNN is employed to assign LN probabilities for all N random views that can be simply averaged (as a set) to compute the final classification probability per VOI. We validate the approach on two datasets: 90 CT volumes with 388 mediastinal LNs and 86 patients with 595 abdominal LNs. We achieve sensitivities of 70%/83% at 3 FP/vol. and 84%/90% at 6 FP/vol. in mediastinum and abdomen respectively, which drastically improves over the previous state-of-the-art work." @default.
- W317170363 created "2016-06-24" @default.
- W317170363 creator A5001789641 @default.
- W317170363 creator A5013946815 @default.
- W317170363 creator A5016047550 @default.
- W317170363 creator A5026506226 @default.
- W317170363 creator A5043710204 @default.
- W317170363 creator A5045227579 @default.
- W317170363 creator A5050610534 @default.
- W317170363 creator A5058741321 @default.
- W317170363 creator A5059415607 @default.
- W317170363 date "2014-01-01" @default.
- W317170363 modified "2023-10-14" @default.
- W317170363 title "A New 2.5D Representation for Lymph Node Detection Using Random Sets of Deep Convolutional Neural Network Observations" @default.
- W317170363 cites W1915761309 @default.
- W317170363 cites W1969094840 @default.
- W317170363 cites W2003644909 @default.
- W317170363 cites W2008120479 @default.
- W317170363 cites W2034987181 @default.
- W317170363 cites W2038631899 @default.
- W317170363 cites W2062606839 @default.
- W317170363 cites W2135917749 @default.
- W317170363 cites W2139248078 @default.
- W317170363 cites W2169805405 @default.
- W317170363 cites W22040386 @default.
- W317170363 doi "https://doi.org/10.1007/978-3-319-10404-1_65" @default.
- W317170363 hasPubMedId "https://pubmed.ncbi.nlm.nih.gov/25333158" @default.
- W317170363 hasPublicationYear "2014" @default.
- W317170363 type Work @default.
- W317170363 sameAs 317170363 @default.
- W317170363 citedByCount "279" @default.
- W317170363 countsByYear W3171703632014 @default.
- W317170363 countsByYear W3171703632015 @default.
- W317170363 countsByYear W3171703632016 @default.
- W317170363 countsByYear W3171703632017 @default.
- W317170363 countsByYear W3171703632018 @default.
- W317170363 countsByYear W3171703632019 @default.
- W317170363 countsByYear W3171703632020 @default.
- W317170363 countsByYear W3171703632021 @default.
- W317170363 countsByYear W3171703632022 @default.
- W317170363 countsByYear W3171703632023 @default.
- W317170363 crossrefType "book-chapter" @default.
- W317170363 hasAuthorship W317170363A5001789641 @default.
- W317170363 hasAuthorship W317170363A5013946815 @default.
- W317170363 hasAuthorship W317170363A5016047550 @default.
- W317170363 hasAuthorship W317170363A5026506226 @default.
- W317170363 hasAuthorship W317170363A5043710204 @default.
- W317170363 hasAuthorship W317170363A5045227579 @default.
- W317170363 hasAuthorship W317170363A5050610534 @default.
- W317170363 hasAuthorship W317170363A5058741321 @default.
- W317170363 hasAuthorship W317170363A5059415607 @default.
- W317170363 hasBestOaLocation W3171703632 @default.
- W317170363 hasConcept C108583219 @default.
- W317170363 hasConcept C146599234 @default.
- W317170363 hasConcept C153180895 @default.
- W317170363 hasConcept C154945302 @default.
- W317170363 hasConcept C41008148 @default.
- W317170363 hasConcept C64869954 @default.
- W317170363 hasConcept C81363708 @default.
- W317170363 hasConcept C95623464 @default.
- W317170363 hasConceptScore W317170363C108583219 @default.
- W317170363 hasConceptScore W317170363C146599234 @default.
- W317170363 hasConceptScore W317170363C153180895 @default.
- W317170363 hasConceptScore W317170363C154945302 @default.
- W317170363 hasConceptScore W317170363C41008148 @default.
- W317170363 hasConceptScore W317170363C64869954 @default.
- W317170363 hasConceptScore W317170363C81363708 @default.
- W317170363 hasConceptScore W317170363C95623464 @default.
- W317170363 hasLocation W3171703631 @default.
- W317170363 hasLocation W3171703632 @default.
- W317170363 hasLocation W3171703633 @default.
- W317170363 hasLocation W3171703634 @default.
- W317170363 hasLocation W3171703635 @default.
- W317170363 hasOpenAccess W317170363 @default.
- W317170363 hasPrimaryLocation W3171703631 @default.
- W317170363 hasRelatedWork W2732542196 @default.
- W317170363 hasRelatedWork W2738221750 @default.
- W317170363 hasRelatedWork W2964383635 @default.
- W317170363 hasRelatedWork W2986507176 @default.
- W317170363 hasRelatedWork W2995914718 @default.
- W317170363 hasRelatedWork W3012978760 @default.
- W317170363 hasRelatedWork W3086857729 @default.
- W317170363 hasRelatedWork W3156786002 @default.
- W317170363 hasRelatedWork W3208028783 @default.
- W317170363 hasRelatedWork W564581980 @default.
- W317170363 isParatext "false" @default.
- W317170363 isRetracted "false" @default.
- W317170363 magId "317170363" @default.
- W317170363 workType "book-chapter" @default.