Matches in SemOpenAlex for { <https://semopenalex.org/work/W2793152034> ?p ?o ?g. }
Showing items 1 to 88 of
88
with 100 items per page.
- W2793152034 abstract "Current clinical 3D-DSA requires the acquisition of two image volumes, before and after the injection of contrast media (i.e. mask and fill scans). Deep learning angiography (DLA) is a recently developed technique that enables the generation of mask-free 3D angiography using convolutional neural networks (CNN). In this work, the quantitative performance of DLA as a function of the number of layers in the deep neural network and the DLA inference computation time are investigated. Clinically indicated rotational angiography exams of 105 patients scanned with a C-arm conebeam CT system using a standard 3D-DSA imaging protocol for the assessment of cerebrovascular abnormalities were retrospectively collected. More than 185 million labeled voxels from contrast-enhanced images of 43 subjects were used as training and testing dataset. Multiple deep CNNs were trained to perform DLA. The trained DLA models were then applied in a validation cohort consisting of the remaining image volumes from 62 subjects and accuracy, sensitivity, precision and F1-scores were calculated for vasculature classification in relevant anatomy. The implementation of the best performing model was optimized for accelerated DLA inference and the computation time was measured under multiple hardware configurations. Vasculature classification accuracy and 95% CI in the validation dataset were 98.7% ([98.3, 99.1] %) for the best performing model. DLA inference user time was 17 seconds for a throughput of 23 images/s. In conclusion, a 30-layer DLA model outperformed shallower networks and DLA inference computation time was demonstrated not be a limiting factor for current clinical practice." @default.
- W2793152034 created "2018-03-29" @default.
- W2793152034 creator A5006071922 @default.
- W2793152034 creator A5038165514 @default.
- W2793152034 creator A5042252659 @default.
- W2793152034 creator A5055137353 @default.
- W2793152034 date "2018-03-09" @default.
- W2793152034 modified "2023-09-25" @default.
- W2793152034 title "Deep learning angiography (DLA): three-dimensional C-arm cone beam CT angiography generated from deep learning method using a convolutional neural network" @default.
- W2793152034 cites W1988115241 @default.
- W2793152034 cites W2035175661 @default.
- W2793152034 cites W2103496339 @default.
- W2793152034 cites W2117649227 @default.
- W2793152034 cites W2130616436 @default.
- W2793152034 cites W2141157125 @default.
- W2793152034 cites W2194775991 @default.
- W2793152034 cites W2302255633 @default.
- W2793152034 cites W2743501370 @default.
- W2793152034 cites W2919115771 @default.
- W2793152034 cites W3101156210 @default.
- W2793152034 doi "https://doi.org/10.1117/12.2293985" @default.
- W2793152034 hasPublicationYear "2018" @default.
- W2793152034 type Work @default.
- W2793152034 sameAs 2793152034 @default.
- W2793152034 citedByCount "2" @default.
- W2793152034 countsByYear W27931520342019 @default.
- W2793152034 crossrefType "proceedings-article" @default.
- W2793152034 hasAuthorship W2793152034A5006071922 @default.
- W2793152034 hasAuthorship W2793152034A5038165514 @default.
- W2793152034 hasAuthorship W2793152034A5042252659 @default.
- W2793152034 hasAuthorship W2793152034A5055137353 @default.
- W2793152034 hasConcept C108583219 @default.
- W2793152034 hasConcept C11413529 @default.
- W2793152034 hasConcept C126838900 @default.
- W2793152034 hasConcept C153180895 @default.
- W2793152034 hasConcept C154945302 @default.
- W2793152034 hasConcept C2776214188 @default.
- W2793152034 hasConcept C2776502983 @default.
- W2793152034 hasConcept C2780643987 @default.
- W2793152034 hasConcept C31972630 @default.
- W2793152034 hasConcept C41008148 @default.
- W2793152034 hasConcept C45374587 @default.
- W2793152034 hasConcept C50644808 @default.
- W2793152034 hasConcept C54170458 @default.
- W2793152034 hasConcept C71924100 @default.
- W2793152034 hasConcept C81363708 @default.
- W2793152034 hasConceptScore W2793152034C108583219 @default.
- W2793152034 hasConceptScore W2793152034C11413529 @default.
- W2793152034 hasConceptScore W2793152034C126838900 @default.
- W2793152034 hasConceptScore W2793152034C153180895 @default.
- W2793152034 hasConceptScore W2793152034C154945302 @default.
- W2793152034 hasConceptScore W2793152034C2776214188 @default.
- W2793152034 hasConceptScore W2793152034C2776502983 @default.
- W2793152034 hasConceptScore W2793152034C2780643987 @default.
- W2793152034 hasConceptScore W2793152034C31972630 @default.
- W2793152034 hasConceptScore W2793152034C41008148 @default.
- W2793152034 hasConceptScore W2793152034C45374587 @default.
- W2793152034 hasConceptScore W2793152034C50644808 @default.
- W2793152034 hasConceptScore W2793152034C54170458 @default.
- W2793152034 hasConceptScore W2793152034C71924100 @default.
- W2793152034 hasConceptScore W2793152034C81363708 @default.
- W2793152034 hasLocation W27931520341 @default.
- W2793152034 hasOpenAccess W2793152034 @default.
- W2793152034 hasPrimaryLocation W27931520341 @default.
- W2793152034 hasRelatedWork W2786758767 @default.
- W2793152034 hasRelatedWork W2896620274 @default.
- W2793152034 hasRelatedWork W2896909802 @default.
- W2793152034 hasRelatedWork W2922013307 @default.
- W2793152034 hasRelatedWork W2924878444 @default.
- W2793152034 hasRelatedWork W2929557486 @default.
- W2793152034 hasRelatedWork W2943739392 @default.
- W2793152034 hasRelatedWork W2946391413 @default.
- W2793152034 hasRelatedWork W2963446989 @default.
- W2793152034 hasRelatedWork W2964191491 @default.
- W2793152034 hasRelatedWork W2967609188 @default.
- W2793152034 hasRelatedWork W3099224939 @default.
- W2793152034 hasRelatedWork W3112113845 @default.
- W2793152034 hasRelatedWork W3116861932 @default.
- W2793152034 hasRelatedWork W3120915328 @default.
- W2793152034 hasRelatedWork W3151039536 @default.
- W2793152034 hasRelatedWork W3166710094 @default.
- W2793152034 hasRelatedWork W3185504789 @default.
- W2793152034 hasRelatedWork W3205086167 @default.
- W2793152034 hasRelatedWork W3209522247 @default.
- W2793152034 isParatext "false" @default.
- W2793152034 isRetracted "false" @default.
- W2793152034 magId "2793152034" @default.
- W2793152034 workType "article" @default.