Lang Stefan, Hoelter Philip, Schmidt Manuel Alexander, Mrochen Anne, Kuramatsu Joji, Kaethner Christian, Roser Philipp, Kowarschik Markus, Doerfler Arnd
Department of Neuroradiology, University Hospital of Erlangen-Nuremberg, 91054 Erlangen, Germany.
Department of Neurology, University Hospital of Erlangen-Nuremberg, 91054 Erlangen, Germany.
Diagnostics (Basel). 2023 Feb 14;13(4):712. doi: 10.3390/diagnostics13040712.
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.
3D-DSA datasets of IAS (n = 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), vessel-geometry index (VGI = VD/VD), and specific qualitative/quantitative parameters of IAS (e.g., location, visual IAS grading [low-/medium-/high-grade] and intra-/poststenotic diameters [d in mm]). Using the NASCET criteria, the percentual degree of luminal restriction was calculated.
In total, 20 angiographic 3D volumes (n = 10; n = 10) were successfully reconstructed with equivalent IQ. Assessment of the vessel geometry in 3DA datasets did not differ significantly from 3D-DSA (VD: = 0.994, = 0.0001; VD: = 0.994, = 0.0001; VGI: = 0.899, = 0.0001). Qualitative analysis of IAS location (3DA/3D-DSA:n = 1, n = 1, n = 4, n = 2, n = 2) and the visual IAS grading (3DA/3D-DSA:n = 3, n = 5, n = 2) revealed identical results for 3DA and 3D-DSA, respectively. Quantitative IAS assessment showed a strong correlation regarding intra-/poststenotic diameters (r = 0.995, p = 0.0001; r = 0.995, p = 0.0001) and the percentual degree of luminal restriction (r = 0.981; p = 0.0001).
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.
基于人工智能（AI）的三维血管造影（3DA）是一种用于脑血管系统“类数字减影血管造影（DSA）”三维成像的新型后处理算法。由于3DA既不需要像当前标准三维DSA那样进行蒙片采集，也不需要数字减法，因此有潜力将患者剂量降低50%。目的是评估与三维DSA相比，3DA在颅内动脉狭窄（IAS）可视化方面的诊断价值。
使用传统软件和原型软件（德国埃尔朗根西门子医疗有限公司）对IAS的三维DSA数据集（n = 10）进行后处理。由两名经验丰富的神经放射科医生通过一致性阅片评估匹配的重建图像，考虑图像质量（IQ）、血管直径（VD）、血管几何指数（VGI = VD/VD）以及IAS的特定定性/定量参数（例如位置、视觉IAS分级[低/中/高级]和狭窄内/后直径[d，单位为mm]）。使用北美症状性颈动脉内膜切除术（NASCET）标准计算管腔狭窄百分比程度。
总共成功重建了20个血管造影三维容积（n = 10；n = 10），图像质量相当。3DA数据集中血管几何形状的评估与三维DSA相比无显著差异（VD： = 0.994， = 0.0001；VD： = 0.994， = 0.0001；VGI： = 0.899， = 0.0001）。IAS位置的定性分析（3DA/三维DSA：n = 1，n = 1，n = 4，n = 2，n = 2）和视觉IAS分级（3DA/三维DSA：n = 3，n = 5，n = 2）分别显示3DA和三维DSA的结果相同。IAS的定量评估显示狭窄内/后直径（r = 0.995，p = 0.0001；r = 0.995，p = 0.0001）和管腔狭窄百分比程度（r = 0.981；p = 0.0001）之间有很强的相关性。
基于AI的3DA是一种用于IAS可视化的可靠算法，与三维DSA显示出可比的结果。因此，3DA是一种有前景的新方法，可大幅降低患者剂量，非常希望其能在临床中应用。
