Artificial intelligence-based 3D angiography for visualization of complex cerebrovascular pathologies
Lang S, Hölter P, Schmidt M, Strother C, Kaethner C, Kowarschik M, Dörfler A (2021)
Publication Type: Journal article
Publication year: 2021
Journal
Book Volume: 42
Pages Range: 1722-1768
Journal Issue: 10
DOI: 10.3174/ajnr.A7252
Abstract
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 (nCA ¼ 10), AVMs (nAVM ¼ 10), and dural arteriovenous fistulas (dAVFs) (ndAVF ¼ 10) were reconstructed using both conventional and prototype software. Corresponding reconstructions have been analyzed by 2 neuroradiologists in a consensus reading in terms of image quality, injection vessel diameters (vessel diameter [VD] 1/2), vessel geometry index (VGI ¼ VD1/VD2), and specific qualitative/quantitative parameters of AVMs (eg, location, nidus size, feeder, associated aneurysms, drainage, Spetzler-Martin score), dAVFs (eg, fistulous point, main feeder, diameter of the main feeder, drainage), and cerebral aneurysms (location, neck, size). 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 size3D angiography/3D-DSA¼ 19.9 [SD, 10.9]/20.2 [SD, 11.2] mm; r ¼ 0.9, P ¼.001), dAVFs (eg, mean diameter of the main feeder3D angiography/3D-DSA¼ 2.04 [SD, 0.65]/2.05 [SD, 0.63] mm; r ¼ 0.9, P ¼.001), and cerebral aneurysms (eg, mean size3D angiography/3D-DSA¼ 5.17 [SD, 3.4]/5.12 [SD, 3.3] mm; r ¼ 0.9, P ¼.001). Assessment of the geometry of the injection vessel in 3D angiography data sets did not differ significantly from that of 3D-DSA (vessel geometry indexAVM: r ¼ 0.84, P ¼.003; vessel geometry indexdAVF: r ¼ 0.82, P ¼.003; vessel geometry indexCA: r ¼ 0.84, P,.001). 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.
Authors with CRIS profile
Philip Hölter
Department of Neuroradiology
Manuel Schmidt
Department of Neuroradiology
Arnd Dörfler
Department of Neuroradiology
Involved external institutions
United States (USA) (US)How to cite
APA:
Lang, S., Hölter, P., Schmidt, M., Strother, C., Kaethner, C., Kowarschik, M., & Dörfler, A. (2021). Artificial intelligence-based 3D angiography for visualization of complex cerebrovascular pathologies. American Journal of Neuroradiology, 42(10), 1722-1768. https://dx.doi.org/10.3174/ajnr.A7252
MLA:
Lang, Sabine, et al. "Artificial intelligence-based 3D angiography for visualization of complex cerebrovascular pathologies." American Journal of Neuroradiology 42.10 (2021): 1722-1768.
BibTeX: Download