Artificial Intelligence-Based 3D Angiography for Visualization of Complex Cerebrovascular Pathologies.
Journal
AJNR. American journal of neuroradiology
ISSN: 1936-959X
Titre abrégé: AJNR Am J Neuroradiol
Pays: United States
ID NLM: 8003708
Informations de publication
Date de publication:
10 2021
10 2021
Historique:
received:
25
05
2020
accepted:
27
05
2021
pubmed:
11
9
2021
medline:
25
11
2021
entrez:
10
9
2021
Statut:
ppublish
Résumé
By means of artificial intelligence, 3D angiography is a novel postprocessing method for 3D imaging of cerebral vessels. Because 3D angiography does not require a mask run like the current standard 3D-DSA, it potentially offers a considerable reduction of the patient radiation dose. Our aim was an assessment of the diagnostic value of 3D angiography for visualization of cerebrovascular pathologies. 3D-DSA data sets of cerebral aneurysms ( In total, 60 volumes have been successfully reconstructed with equivalent image quality. The specific qualitative/quantitative assessment of 3D angiography revealed nearly complete accordance with 3D-DSA in AVMs (eg, mean nidus size In this study, the artificial intelligence-based 3D angiography was a reliable method for visualization of complex cerebrovascular pathologies and showed results comparable with those of 3D-DSA. Thus, 3D angiography is a promising postprocessing method that provides a significant reduction of the patient radiation dose.
Sections du résumé
BACKGROUND AND PURPOSE
By means of artificial intelligence, 3D angiography is a novel postprocessing method for 3D imaging of cerebral vessels. Because 3D angiography does not require a mask run like the current standard 3D-DSA, it potentially offers a considerable reduction of the patient radiation dose. Our aim was an assessment of the diagnostic value of 3D angiography for visualization of cerebrovascular pathologies.
MATERIALS AND METHODS
3D-DSA data sets of cerebral aneurysms (
RESULTS
In total, 60 volumes have been successfully reconstructed with equivalent image quality. The specific qualitative/quantitative assessment of 3D angiography revealed nearly complete accordance with 3D-DSA in AVMs (eg, mean nidus size
CONCLUSIONS
In this study, the artificial intelligence-based 3D angiography was a reliable method for visualization of complex cerebrovascular pathologies and showed results comparable with those of 3D-DSA. Thus, 3D angiography is a promising postprocessing method that provides a significant reduction of the patient radiation dose.
Identifiants
pubmed: 34503946
pii: ajnr.A7252
doi: 10.3174/ajnr.A7252
pmc: PMC8562747
doi:
Types de publication
Journal Article
Langues
eng
Sous-ensembles de citation
IM
Pagination
1762-1768Informations de copyright
© 2021 by American Journal of Neuroradiology.
Références
Korean J Radiol. 2017 Jul-Aug;18(4):722-728
pubmed: 28670167
Comput Med Imaging Graph. 1999 Nov-Dec;23(6):311-21
pubmed: 10634143
Eur Radiol. 2014 Jun;24(6):1257-65
pubmed: 24691631
Stroke. 2001 Jun;32(6):1458-71
pubmed: 11387517
AJNR Am J Neuroradiol. 1999 Mar;20(3):475-81
pubmed: 10219415
AJNR Am J Neuroradiol. 2008 May;29(5):976-9
pubmed: 18258703
Rofo. 2006 Sep;178(9):880-5
pubmed: 16953480
J Neurosurg. 2006 Sep;105(3):406-11
pubmed: 16961135
Radiology. 2001 Mar;218(3):799-808
pubmed: 11230659
J Neurointerv Surg. 2014 Nov;6(9):672-6
pubmed: 24122004
Radiology. 1981 May;139(2):273-6
pubmed: 7012918
J Neurointerv Surg. 2015 May;7(5):386-90
pubmed: 24714612
AJNR Am J Neuroradiol. 2018 May;39(5):916-922
pubmed: 29567655
AJNR Am J Neuroradiol. 2002 Aug;23(7):1199-205
pubmed: 12169480
Clin Neuroradiol. 2020 Dec;30(4):705-712
pubmed: 31598760
Acad Radiol. 2012 Jun;19(6):701-7
pubmed: 22578227
Eur Radiol. 2000;10(4):564-8
pubmed: 10795532
AJNR Am J Neuroradiol. 2003 Jun-Jul;24(6):1067-74
pubmed: 12812928