CT angiography prior to TAVI procedure: can Artificial Intelligence improve reporting?

Abstract

Abstract CT angiography prior to transcatheter aortic valve implantation (TAVI) procedure is the standard non-invasive imaging method for pre-procedural evaluation of aortic root dimensions and access sites. A detailed report is crucial to a proper planning. We assessed Artificial Intelligence (AI)-algorithm accuracy to measure vessels diameters at CT prior to TAVI. CT scans of 50 patients were included. Two Radiologists with experience in vascular imaging together manually assessed diameters at nine landmark positions according to the American Heart Association guidelines: 450 values were obtained. Measurements were compared with diameters obtained from AI algorithm. Measurements performed by the radiologists were never significantly different from the values obtained from the AI algorithm (p ≥ 0.249). The more the aortic landmark was distal to the heart, the more accurate was the automatic software analysis (maximum p-value at diaphragmatic aorta, 0.995). P-values were lower close to the heart, with a minimum at sinotubular junction (0.249). The time for automatic evaluation (average 1 min 47 sec) was significantly lower compared with manual measurements (5 min 41 sec) (p < 0.01). In conclusion, our results indicate that AI-algorithms can measure aortic diameters at CT prior to TAVI with high accuracy. AI-assisted reporting promises high efficiency, reduced inter-reader variabilities and time saving. In order to perform optimal procedure planning aortic root analysis could be improved, including annulus dimensions.