Matches in SemOpenAlex for { <https://semopenalex.org/work/W3129091465> ?p ?o ?g. }
Showing items 1 to 79 of
79
with 100 items per page.
- W3129091465 abstract "Carotid ultrasound is a screening modality used by physicians to direct treatment in the prevention of ischemic stroke in high-risk patients. It is a time intensive process that requires highly trained technicians and physicians. Evaluation of a carotid ultrasound requires segmentation of the vessel wall, lumen, and plaque of the carotid artery. Convolutional neural networks are state of the art in image segmentation yet there are no previous methods to solve this problem on carotid ultrasounds. We evaluate here a U-net convolutional neural network for lumen segmentation from ultrasound images of the entire carotid system. We obtained de-identified images under IRB approval from 226 patients. We isolated the internal, external, and common carotid artery ultrasound images for these patients giving us a total of 2156 images. We manually segmented the vessel lumen in each image that we then use as ground truth. With our convolutional U-Net we obtained a 10-fold cross-validation accuracy of 94.3%. We see that the U-Net correctly segments the lumen even in the presence of significant plaque, calcified wall, and ultrasound shadowing, all of which make it difficult to outline the vessel. We also see that the common carotid artery vessels are easiest to segment with a 96.6% cross-validation accuracy whereas internal and external carotid are harder both with 92.7% and 91.9% cross-validation accuracies respectively. Our work here represents a first successful step towards the automated segmentation of the vessel lumen in carotid artery ultrasound images and is an important first step in creating a system that can independently evaluate carotid ultrasounds." @default.
- W3129091465 created "2021-02-15" @default.
- W3129091465 creator A5005863073 @default.
- W3129091465 creator A5007413887 @default.
- W3129091465 creator A5036148022 @default.
- W3129091465 creator A5041489769 @default.
- W3129091465 creator A5076952766 @default.
- W3129091465 creator A5077516487 @default.
- W3129091465 creator A5083898401 @default.
- W3129091465 creator A5087990990 @default.
- W3129091465 date "2020-12-16" @default.
- W3129091465 modified "2023-09-23" @default.
- W3129091465 title "Vessel lumen segmentation in carotid artery ultrasounds with the U-Net convolutional neural network" @default.
- W3129091465 cites W114517082 @default.
- W3129091465 cites W1901129140 @default.
- W3129091465 cites W2020745232 @default.
- W3129091465 cites W2112796928 @default.
- W3129091465 cites W2129837832 @default.
- W3129091465 cites W2132513126 @default.
- W3129091465 cites W2163605009 @default.
- W3129091465 cites W2167510172 @default.
- W3129091465 cites W2196906371 @default.
- W3129091465 cites W2596094611 @default.
- W3129091465 cites W2794642825 @default.
- W3129091465 cites W2899771611 @default.
- W3129091465 cites W2944775438 @default.
- W3129091465 cites W3004527277 @default.
- W3129091465 cites W3104087655 @default.
- W3129091465 cites W3105282616 @default.
- W3129091465 doi "https://doi.org/10.1109/bibm49941.2020.9313434" @default.
- W3129091465 hasPublicationYear "2020" @default.
- W3129091465 type Work @default.
- W3129091465 sameAs 3129091465 @default.
- W3129091465 citedByCount "2" @default.
- W3129091465 countsByYear W31290914652023 @default.
- W3129091465 crossrefType "proceedings-article" @default.
- W3129091465 hasAuthorship W3129091465A5005863073 @default.
- W3129091465 hasAuthorship W3129091465A5007413887 @default.
- W3129091465 hasAuthorship W3129091465A5036148022 @default.
- W3129091465 hasAuthorship W3129091465A5041489769 @default.
- W3129091465 hasAuthorship W3129091465A5076952766 @default.
- W3129091465 hasAuthorship W3129091465A5077516487 @default.
- W3129091465 hasAuthorship W3129091465A5083898401 @default.
- W3129091465 hasAuthorship W3129091465A5087990990 @default.
- W3129091465 hasConcept C126322002 @default.
- W3129091465 hasConcept C131631996 @default.
- W3129091465 hasConcept C153180895 @default.
- W3129091465 hasConcept C154945302 @default.
- W3129091465 hasConcept C2987047532 @default.
- W3129091465 hasConcept C41008148 @default.
- W3129091465 hasConcept C71924100 @default.
- W3129091465 hasConcept C81363708 @default.
- W3129091465 hasConcept C89600930 @default.
- W3129091465 hasConceptScore W3129091465C126322002 @default.
- W3129091465 hasConceptScore W3129091465C131631996 @default.
- W3129091465 hasConceptScore W3129091465C153180895 @default.
- W3129091465 hasConceptScore W3129091465C154945302 @default.
- W3129091465 hasConceptScore W3129091465C2987047532 @default.
- W3129091465 hasConceptScore W3129091465C41008148 @default.
- W3129091465 hasConceptScore W3129091465C71924100 @default.
- W3129091465 hasConceptScore W3129091465C81363708 @default.
- W3129091465 hasConceptScore W3129091465C89600930 @default.
- W3129091465 hasLocation W31290914651 @default.
- W3129091465 hasOpenAccess W3129091465 @default.
- W3129091465 hasPrimaryLocation W31290914651 @default.
- W3129091465 hasRelatedWork W2613736958 @default.
- W3129091465 hasRelatedWork W2769435486 @default.
- W3129091465 hasRelatedWork W2795329967 @default.
- W3129091465 hasRelatedWork W2994948129 @default.
- W3129091465 hasRelatedWork W3081496756 @default.
- W3129091465 hasRelatedWork W3093612317 @default.
- W3129091465 hasRelatedWork W3095523211 @default.
- W3129091465 hasRelatedWork W3102253946 @default.
- W3129091465 hasRelatedWork W3148584990 @default.
- W3129091465 hasRelatedWork W4200528772 @default.
- W3129091465 isParatext "false" @default.
- W3129091465 isRetracted "false" @default.
- W3129091465 magId "3129091465" @default.
- W3129091465 workType "article" @default.