Fully automatic volume segmentation using deep learning approaches to assess aneurysmal sac evolution after infrarenal endovascular aortic repair.

OBJECTIVE: Endovascular aortic repair (EVAR) surveillance relies on serial measurements of the maximal diameter despite significant inter- and intraobserver variability. Volumetric measurements are more sensitive; however, their general use has been hampered by the time required for their implementation. An innovative, fully automated software (PRAEVAorta; Nurea, Bordeaux, France), using artificial intelligence, had previously demonstrated fast and robust detection of the characteristics of infrarenal abdominal aortic aneurysms on preoperative imaging studies. In the present study, we assessed the robustness of these data on post-EVAR computed tomography (CT) scans. METHODS: We compared fully automatic and semiautomatic segmentation manually corrected by a senior surgeon (E.D.) using a dataset of 48 patients (48 early post-EVAR CT scans with 6466 slices and 101 follow-up CT scans with 13,708 slices). RESULTS: The analyses confirmed the excellent correlation of the post-EVAR volumes and surfaces and the proximal neck and maximum aneurysm diameters measured using the fully automatic and manually corrected segmentation methods (Pearson's coefficient correlation, >0.99; P < .0001). A comparison between the fully automatic and manually corrected segmentation methods revealed a mean Dice similarity coefficient of 0.950 ± 0.015, Jaccard index of 0.906 ± 0.028, sensitivity of 0.929 ± 0.028, specificity of 0.965 ± 0.016, volumetric similarity of 0.973 ± 0.018, and mean Hausdorff distance/slice of 8.7 ± 10.8 mm. The mean volumetric similarity reached 0.873 ± 0.100 for the lumen and 0.903 ± 0.091 for the thrombus. The segmentation time was nine times faster with the fully automatic method (2.5 minutes vs 22 minutes per patient with the manually corrected method; P < .0001). A preliminary analysis also demonstrated that a diameter increase of 2 mm can actually represent a >5% volume increase. CONCLUSIONS: PRAEVAorta enabled a fast, reproducible, and fully automated analysis of post-EVAR abdominal aortic aneurysm sac and neck characteristics, with a comparison between different time points. It could become a crucial adjunct for EVAR follow-up through the early detection of sac evolution, which might reduce the risk of secondary rupture.

Contemporary Results with the Biosynthetic Glutaraldehyde Denatured Ovine Collagen Graft (Omniflow II) in Lower Extremity Arterial Revascularization in a Septic Context.

BACKGROUND: Peripheral vascular graft infections are poorly-evaluated, despite high mortality and amputation rates. The vascular substitute of choice remains controversial when veins are unavailable. This study aims to evaluate the results of a biosynthetic collagen graft (Omniflow II®) in an infected field when autologous veins are unavailable. METHODS: This retrospective, multicentric study included all consecutive patients in whom an Omniflow II graft was used for infra-inguinal revascularization in a septic context from January 2015 to January 2020. The primary end-point was freedom from major amputation; secondary end-points were 30-day mortality, survival, patency, and freedom from reinfection estimated using the Kaplan-Meier method. RESULTS: Twenty-nine patients (27 men, median age of 69 years interquartile range IQR:60; 76) were included. Fever was present in 58.6%, a septic rupture in 17.9%, a pseudo-aneurysm in 25.0%. The 30-day mortality rate was 3.4%. Median follow-up reached 49 months. At 1 and 3 years, estimated freedom from major amputation was 88.4% and 83.9%, survival: 96%, primary patency: 74.6% and 65.8%, and reinfection free-survival: 85.6%. There were 7 occlusions (1 iliofemoral, 1 below-knee, and 5 above-knee bypasses), 3 explantations for persistent sepsis, 4 reinfections (all within 6 months which led to 1 death and 3 out of 4 major amputations). The risk of major amputation increased with bypass reinfection (P = 0.004), occlusion (P = 0.005), and polymicrobial infection (P = 0.05). CONCLUSIONS: In a septic context, the Omniflow II graft shows acceptable freedom from major amputation and reinfection. This usage remains outside the instructions of use, it is, therefore, is essential to pursue longer-term studies in larger cohorts.