Significant Radiation Reduction Using Cloud-Based AI Imaging in Manually Matched Cohort of Complex Aneurysm Repair.
Academic Article
Overview
abstract
OBJECTIVE: Cloud-based, surgical augmented intelligence (Cydar Medical, Cambridge, UK) can be used for surgical planning and intraoperative imaging guidance during complex endovascular aortic procedures. We aim to evaluate radiation exposure, operative safety metrics, and post-operative renal outcomes following implementation of Cydar imaging guidance using a manually matched cohort of aortic procedures. METHODS: We retrospectively reviewed our prospectively maintained database of endovascular aortic cases. Patients repaired using Cydar imaging were matched to patients who underwent a similar procedure without using Cydar. Matching was performed manually on a 1:1 basis using anatomy, device configuration, number of branches/fenestrations, and adjunctive procedures including in-situ laser fenestration. Radiation, contrast use, and other operative metrics were compared. Pre- and post-operative maximum creatinine was compared to assess for acute kidney injury (AKI) based on RIFLE Criteria. RESULTS: 100 patients from 2012-2023 were identified: 50 cases (38 FEVAR, 2 TEVAR, 3 octopus-type TAAA repair, 7 EVAR) where Cydar imaging was used, with suitable matches to 50 non-Cydar cases. Baseline characteristics including BMI did not differ significantly between the two groups (27.8 ± 5.6 vs. 26.7 ± 6.1; P=0.31). Radiation dose was significantly lower in the Cydar group (2529 ± 2256 vs 3676 ± 2976 mGy; P<0.03 Figure 1), despite there being no difference in fluoroscopy time (51 ± 29.4 vs 58 ± 37.2 min; P = 0.37). Contrast volume (94 ± 37.4 vs 93 ± 43.9 mL; P = 0.73), estimated blood loss (169 ± 223 vs 193 ± 222 mL; P = 0.97), and procedure time (154 ± 78 vs 165 ± 89.1 min) did not differ significantly. Additionally, Cydar vs non-Cydar patients did not show a significant difference between pre- and post-creatinine changes (0.13 +/- 0.08 vs 0.05 +/- 0.07; P=0.34). Only one patient in the non-Cydar group met RIFLE criteria for AKI post-operatively. CONCLUSIONS: The use of cloud-based augmented intelligence imaging was associated with a significant reduction in radiation dose in a cohort of matched aortic procedures but did not appear to affect other parameters or renal function. Even with advanced imaging, surgeons should remain conscientious about radiation safety and administration of nephrotoxic contrast agents.