Accuracy of Dose-Saving Artificial-Intelligence-Based 3D Angiography (3DA) for Grading of Intracranial Artery Stenoses: Preliminary Findings
oleh: Stefan Lang, Philip Hoelter, Manuel Alexander Schmidt, Anne Mrochen, Joji Kuramatsu, Christian Kaethner, Philipp Roser, Markus Kowarschik, Arnd Doerfler
| Format: | Article |
|---|---|
| Diterbitkan: | MDPI AG 2023-02-01 |
Deskripsi
Background and purpose: Based on artificial intelligence (AI), 3D angiography (3DA) is a novel postprocessing algorithm for “DSA-like” 3D imaging of cerebral vasculature. Because 3DA requires neither mask runs nor digital subtraction as the current standard 3D-DSA does, it has the potential to cut the patient dose by 50%. The object was to evaluate 3DA’s diagnostic value for visualization of intracranial artery stenoses (IAS) compared to 3D-DSA. Materials and methods: 3D-DSA datasets of IAS (n<sub>IAS</sub> = 10) were postprocessed using conventional and prototype software (Siemens Healthineers AG, Erlangen, Germany). Matching reconstructions were assessed by two experienced neuroradiologists in consensus reading, considering image quality (IQ), vessel diameters (VD<sub>1/2</sub>), vessel-geometry index (VGI = VD<sub>1</sub>/VD<sub>2</sub>), and specific qualitative/quantitative parameters of IAS (e.g., location, visual IAS grading [low-/medium-/high-grade] and intra-/poststenotic diameters [d<sub>intra-/poststenotic</sub> in mm]). Using the NASCET criteria, the percentual degree of luminal restriction was calculated. Results: In total, 20 angiographic 3D volumes (n<sub>3DA</sub> = 10; n<sub>3D-DSA</sub> = 10) were successfully reconstructed with equivalent IQ. Assessment of the vessel geometry in 3DA datasets did not differ significantly from 3D-DSA (VD<sub>1</sub>: <i>r</i> = 0.994, <i>p</i> = 0.0001; VD<sub>2</sub>:<i>r</i> = 0.994, <i>p</i> = 0.0001; VGI: <i>r</i> = 0.899, <i>p</i> = 0.0001). Qualitative analysis of IAS location (3DA/3D-DSA:n<sub>ICA/C4</sub> = 1, n<sub>ICA/C7</sub> = 1, n<sub>MCA/M1</sub> = 4, n<sub>VA/V4</sub> = 2, n<sub>BA</sub> = 2) and the visual IAS grading (3DA/3D-DSA:n<sub>low-grade</sub> = 3, n<sub>medium-grade</sub> = 5, n<sub>high-grade</sub> = 2) revealed identical results for 3DA and 3D-DSA, respectively. Quantitative IAS assessment showed a strong correlation regarding intra-/poststenotic diameters (r<sub>dintrastenotic</sub> = 0.995, p<sub>dintrastenotic</sub> = 0.0001; r<sub>dpoststenotic</sub> = 0.995, p<sub>dpoststenotic</sub> = 0.0001) and the percentual degree of luminal restriction (r<sub>NASCET 3DA</sub> = 0.981; p<sub>NASCET 3DA</sub> = 0.0001). Conclusions: The AI-based 3DA is a resilient algorithm for the visualization of IAS and shows comparable results to 3D-DSA. Hence, 3DA is a promising new method that allows a considerable patient-dose reduction, and its clinical implementation would be highly desirable.