SemOpenAlex |

SemOpenAlex

Matches in SemOpenAlex for { <https://semopenalex.org/work/W3204455671> ?p ?o ?g. }

Showing items 1 to 92 of 92 with 100 items per page.

W3204455671 endingPage "234" @default.
W3204455671 startingPage "226" @default.
W3204455671 abstract "The detection of intracranial aneurysms from Magnetic Resonance Angiography images is a problem of rapidly growing clinical importance. In the last 3 years, the raise of deep convolutional neural networks has instigated a streak of methods that have shown promising performance. The major issue to address is the very severe class imbalance. Previous authors have focused their efforts on the network architecture and loss function. This paper tackles the data. A rough but fast annotation is considered: each aneurysm is approximated by a sphere defined by two points. Second, a small patch approach is taken so as to increase the number of samples. Third, samples are generated by a combination of data selection (negative patches are centered half on blood vessels and half on parenchyma) and data synthesis (patches containing an aneurysm are duplicated and deformed by a 3D spline transform). This strategy is applied to train a 3D U-net model, with a binary cross entropy loss, on a data set of 111 patients (155 aneurysms, mean size 3.86 mm ± 2.39 mm, min 1.23 mm, max 19.63 mm). A 5-fold cross-validation evaluation provides state of the art results (sensitivity 0.72, false positive count 0.14, as per ADAM challenge criteria). The study also reports a comparison with the focal loss, and Cohen’s Kappa coefficient is shown to be a better metric than Dice for this highly unbalanced detection problem." @default.
W3204455671 created "2021-10-11" @default.
W3204455671 creator A5003471678 @default.
W3204455671 creator A5025565467 @default.
W3204455671 creator A5073632869 @default.
W3204455671 creator A5080003178 @default.
W3204455671 creator A5084222659 @default.
W3204455671 date "2021-01-01" @default.
W3204455671 modified "2023-10-11" @default.
W3204455671 title "An Efficient Data Strategy for the Detection of Brain Aneurysms from MRA with Deep Learning" @default.
W3204455671 cites W1909740415 @default.
W3204455671 cites W2026616100 @default.
W3204455671 cites W2043478908 @default.
W3204455671 cites W2053154970 @default.
W3204455671 cites W2464708700 @default.
W3204455671 cites W2746587344 @default.
W3204455671 cites W2895926594 @default.
W3204455671 cites W2904807675 @default.
W3204455671 cites W2936503027 @default.
W3204455671 cites W2951762285 @default.
W3204455671 cites W2963351448 @default.
W3204455671 cites W3012280898 @default.
W3204455671 cites W3035665735 @default.
W3204455671 cites W3083713818 @default.
W3204455671 doi "https://doi.org/10.1007/978-3-030-88210-5_22" @default.
W3204455671 hasPublicationYear "2021" @default.
W3204455671 type Work @default.
W3204455671 sameAs 3204455671 @default.
W3204455671 citedByCount "2" @default.
W3204455671 countsByYear W32044556712022 @default.
W3204455671 crossrefType "book-chapter" @default.
W3204455671 hasAuthorship W3204455671A5003471678 @default.
W3204455671 hasAuthorship W3204455671A5025565467 @default.
W3204455671 hasAuthorship W3204455671A5073632869 @default.
W3204455671 hasAuthorship W3204455671A5080003178 @default.
W3204455671 hasAuthorship W3204455671A5084222659 @default.
W3204455671 hasBestOaLocation W32044556712 @default.
W3204455671 hasConcept C108583219 @default.
W3204455671 hasConcept C12267149 @default.
W3204455671 hasConcept C124504099 @default.
W3204455671 hasConcept C153180895 @default.
W3204455671 hasConcept C154945302 @default.
W3204455671 hasConcept C162324750 @default.
W3204455671 hasConcept C163892561 @default.
W3204455671 hasConcept C167981619 @default.
W3204455671 hasConcept C176217482 @default.
W3204455671 hasConcept C21547014 @default.
W3204455671 hasConcept C27181475 @default.
W3204455671 hasConcept C41008148 @default.
W3204455671 hasConcept C50644808 @default.
W3204455671 hasConcept C58489278 @default.
W3204455671 hasConcept C66905080 @default.
W3204455671 hasConcept C81363708 @default.
W3204455671 hasConcept C89600930 @default.
W3204455671 hasConceptScore W3204455671C108583219 @default.
W3204455671 hasConceptScore W3204455671C12267149 @default.
W3204455671 hasConceptScore W3204455671C124504099 @default.
W3204455671 hasConceptScore W3204455671C153180895 @default.
W3204455671 hasConceptScore W3204455671C154945302 @default.
W3204455671 hasConceptScore W3204455671C162324750 @default.
W3204455671 hasConceptScore W3204455671C163892561 @default.
W3204455671 hasConceptScore W3204455671C167981619 @default.
W3204455671 hasConceptScore W3204455671C176217482 @default.
W3204455671 hasConceptScore W3204455671C21547014 @default.
W3204455671 hasConceptScore W3204455671C27181475 @default.
W3204455671 hasConceptScore W3204455671C41008148 @default.
W3204455671 hasConceptScore W3204455671C50644808 @default.
W3204455671 hasConceptScore W3204455671C58489278 @default.
W3204455671 hasConceptScore W3204455671C66905080 @default.
W3204455671 hasConceptScore W3204455671C81363708 @default.
W3204455671 hasConceptScore W3204455671C89600930 @default.
W3204455671 hasLocation W32044556711 @default.
W3204455671 hasLocation W32044556712 @default.
W3204455671 hasLocation W32044556713 @default.
W3204455671 hasOpenAccess W3204455671 @default.
W3204455671 hasPrimaryLocation W32044556711 @default.
W3204455671 hasRelatedWork W2607836359 @default.
W3204455671 hasRelatedWork W3037097571 @default.
W3204455671 hasRelatedWork W3080935557 @default.
W3204455671 hasRelatedWork W3121296535 @default.
W3204455671 hasRelatedWork W3124102327 @default.
W3204455671 hasRelatedWork W4200334192 @default.
W3204455671 hasRelatedWork W4281645058 @default.
W3204455671 hasRelatedWork W4286545890 @default.
W3204455671 hasRelatedWork W4312877132 @default.
W3204455671 hasRelatedWork W4319993456 @default.
W3204455671 isParatext "false" @default.
W3204455671 isRetracted "false" @default.
W3204455671 magId "3204455671" @default.
W3204455671 workType "book-chapter" @default.