Automatic CTA analysis for blood vessels and aneurysm features extraction in EVAR planning

Area of Science:

• Medical Imaging
• Artificial Intelligence in Medicine
• Vascular Surgery

Background:

• Pre-operative planning for Endovascular Aneurysm Repair (EVAR) is critical for treating abdominal aortic aneurysms (AAA).
• Current manual measurement methods are time-consuming and error-prone.
• Existing AI solutions for AAA analysis are often incomplete, focusing only on basic measurements.

Purpose of the Study:

• To present BRAVE (Blood Vessels Recognition and Aneurysms Visualization Enhancement), a comprehensive AI-driven solution for automated vascular segmentation and AAA analysis.
• To provide a fully automated pre-operative analysis pipeline for EVAR planning.
• To improve the efficiency and precision of AAA assessment.

Main Methods:

• Developed BRAVE, an AI pipeline for comprehensive vascular segmentation of the aorta and secondary vessels from pre-operative CTA scans.
• Implemented advanced volumetric analysis, including quantification of thrombotic tissue and calcifications.
• Automated identification of proximal and distal sealing zones essential for EVAR.

Main Results:

• BRAVE provides exhaustive segmentation, capturing the complete vascular structure.
• The system performs advanced volumetric analysis and identifies critical EVAR sealing zones.
• Demonstrated generalizability across multi-center datasets, diverse CTA protocols, and patient populations.

Conclusions:

• BRAVE offers the first comprehensive, fully automated AI solution for vascular segmentation and AAA analysis.
• This tool significantly reduces manual intervention, saving time and improving precision in pre-operative planning.
• BRAVE enhances clinical workflow efficiency and supports vascular surgeons' decision-making for EVAR procedures.