Use of surgical augmented intelligence maps can reduce radiation and improve safety in the endovascular treatment of complex aortic aneurysms

Abstract

Objective: The introduction of endovascular procedures has revolutionized the management of complex aortic aneurysms. Although repair has traditionally required longer operative times and increased radiation exposure compared with simple endovascular aneurysm repair, the recent introduction of three-dimensional technology has become an invaluable operative adjunct. Surgical augmented intelligence (AI) is a rapidly evolving tool initiated at our institution in June 2019. In our study, we sought to determine whether this technology improved patient and operator safety.

Methods: A retrospective review of patients who had undergone endovascular repair of complex aortic aneurysms (pararenal, juxtarenal, or thoracoabdominal), type B dissection, or infrarenal (endoleak, coil placement, or renal angiography with or without intervention) at a tertiary care center from August 2015 to November 2021 was performed. Patients were stratified according to the findings from intelligent maps, which are patient-specific AI tools used in the operating room in conjunction with real-time fluoroscopic images. The primary outcomes included operative time, radiation exposure, fluoroscopy time, and contrast use. The secondary outcomes included 30-day postoperative complications and long-term follow-up. Linear regression models were used to evaluate the association between AI use and the main outcomes.

Results: During the 6-year period, 116 patients were included in the present study, with no significant differences in the baseline characteristics. Of the 116 patients, 76 (65.5%) had undergone procedures using AI and 40 (34.5%) had undergone procedures without AI software. The intraoperative outcomes revealed a significant decrease in radiation exposure (AI group, 1955 mGy; vs non-AI group, 3755 mGy; P = .004), a significant decrease in the fluoroscopy time (AI group, 55.6 minutes; vs non-AI group, 86.9 minutes; P = .007), a decrease in the operative time (AI group, 255 minutes; vs non-AI group, 284 minutes; P = .294), and a significant decrease in contrast use (AI group, 123 mL; vs non-AI group, 199 mL; P < .0001). No differences were found in the 30-day and long-term outcomes.

Conclusions: The results from the present study have demonstrated that the use of AI technology combined with intraoperative imaging can significantly facilitate complex endovascular aneurysm repair by decreasing the operative time, radiation exposure, fluoroscopy time, and contrast use. Overall, evolving technology such as AI has improved radiation safety for both the patient and the entire operating room team.

Keywords: Aortic aneurysm; Artificial intelligence; Radiation.

Fig.

Cydar EV map showing preadjustment rings showing incorrect graft position (A), adjustment for deformation (B), after adjustment (C), right renal and celiac artery cannulation (D), and completion angiogram (E).