Evaluation of an Artificial Intelligence-Based 3D-Angiography for Visualization of Cerebral Vasculature

• Published in: Clinical neuroradiology (Munich) Vol. 30; no. 4; pp. 705 - 712
• Main Authors: Lang, Stefan, Hoelter, Philip, Schmidt, Manuel, Eisenhut, Felix, Kaethner, Christian, Kowarschik, Markus, Lücking, Hannes, Doerfler, Arnd
• Format: Journal Article
• Language: English
• Published: Berlin/Heidelberg Springer Berlin Heidelberg 01.12.2020; Springer; Springer Nature B.V
• Subjects: Algorithms; Angiography; Artificial intelligence; Datasets; Medical imaging; Medicine; Medicine & Public Health; Neurology; Neuroradiology; Neurosurgery; Original Article; Radiation; Radiotherapy; Visualization; Deep learning; 3D angiography; Artificial intelligence; Flat-detector computed tomography; Dose reduction
• ISSN: 1869-1439; 1869-1447
• DOI: 10.1007/s00062-019-00836-7

Purpose The three-dimensional digital subtraction angiography (3D DSA) technique is the current standard and is based on both mask and fill runs to enable the subtraction technique. Artificial intelligence (AI)-based 3D angiography (3DA) was developed to reduce radiation dosage because only one contrast-enhanced run of the C‑arm system is required for reconstruction of DSA-like 3D volumes. The aim was the evaluation of this algorithm regarding its diagnostic information. Methods 3D DSA datasets without pathologic findings were reconstructed both with subtraction technique and with the AI-based algorithm. Corresponding reconstructions were evaluated by 2 neuroradiologists with respect to image quality (IQ), visualization of major segments of the circle of Willis (ICA = C4-C7; OphA; ACA = A1-A2, MCA = M1-M2; VA = V4; BA; AICA; SUCA; PCA = P1-P2), identifiability of perforators (lenticulostriate/thalamoperforating arteries) and vessel diameters (ICA = C4; MCA = M1; BA; PCA = P1). Results In total 15 datasets were successfully reconstructed as 3D DSA and 3DA with diagnostic image quality. All major segments of the circle of Willis and perforators were comparably visualized with 3DA. Quantitative analysis of vessel diameters in 3D DSA and 3DA datasets was equivalent and did not show relevant differences ( r ICA  = 0.901, p  = 0.001; r M1  = 0.951, p  = 0.001; r BA  = 0.906, p  = 0.001; r P1  = 0.991, p  = 0.001). Conclusions The use of 3DA demonstrated reliable visualization of cerebral vasculature with respect to quantitative and qualitative parameters. Therefore, 3DA is a promising method that might help to reduce patient radiation.