Automatic Measurement of Vascular Calcifications in Patients with Aorto-Iliac Occlusive Disease to Predict the Risk of Re-intervention After Endovascular Repair

Abstract

There is currently a lack of consensus and tools to easily measure vascular calcification using computed tomography angiography (CTA). The aim of this study was to develop a fully automatic software to measure calcifications and to evaluate the interest as predictive factor in patients with aorto-iliac occlusive disease. This study retrospectively included 171 patients who had endovascular repair of an aorto-iliac occlusive lesion at the University Hospital of Nice between January 2011 and December 2019. Calcifications volumes were measured from CTA using an automatic method consisting in three sequential steps: image pre-processing, lumen segmentation using expert system, and deep learning algorithms and segmentation of calcifications. Calcification volumes were measured in the infrarenal abdominal aorta and the iliac arterial segments, corresponding to the common and the external iliac arteries. Among 171 patients included with a mean age of 65years, the revascularization was performed on the native external and internal iliac arteries in, respectively: 83 patients (48.5%), 107 (62.3%), and 7 (4.1%). The mean volumes of calcifications were 2,759mm3 in the infrarenal abdominal aorta, 1,821mm3 and 1,795mm3 in the right and left iliac arteries, respectively. For a mean follow-up of 39months, target lesion re-intervention was performed in 55 patients (32.2%). These patients had higher volume of calcifications in the right and left iliac arteries, compared with patients who did not have a re-intervention (2,274mm3 vs. 1,606mm3, P=0.0319 and 2,278 vs. 1,567mm3, P=0.0213). The development of a fully automatic software would be useful to facilitate the measurement of vascular calcifications and possibly better inform the prognosis of patients.