Back to the list
Congress: ECR25
Poster Number: C-12553
Type: Poster: EPOS Radiologist (scientific)
Authorblock: D. Ravanelli, E. Robbi, I. Raunig, S. Allevi, A. Passerini, S. Bonvini, A. Trianni; Trent/IT
Disclosures:
Daniele Ravanelli: Nothing to disclose
Erich Robbi: Nothing to disclose
Igor Raunig: Nothing to disclose
Sara Allevi: Nothing to disclose
Andrea Passerini: Nothing to disclose
Stefano Bonvini: Nothing to disclose
Annalisa Trianni: Nothing to disclose
Keywords: Computer applications, Interventional vascular, Radiation physics, CT-Angiography, Computer Applications-General, Segmentation, Aneurysms
Purpose The purpose of this study is to evaluate the accuracy of a novel, fully automatic artificial intelligence (AI)-based 3D tool designed to extract morphological features from pre-operative computed tomography angiography (CTA) images. These features are crucial for the planning of endovascular aneurysm repair (EVAR) procedures in patients suffering from abdominal aortic aneurysms (AAA). Pre-operative analysis of CTA images is a critical component in ensuring the success of EVAR procedures, as it directly influences the planning of stent graft sizing. Inaccurate...
Read more Methods and materials Pre-operative CTA images are an essential part of EVAR planning, offering detailed insights into the morphology of the aneurysm and its surrounding structures. These images are used to measure parameters such as the diameter of the aneurysmal sac, the aortic-iliac diameters, and the presence of critical features like wall thrombus and calcifications. Accurately measuring these features is vital for selecting the correct stent graft size, which directly impacts the procedure’s success. Inaccurate measurements, whether due to human error or variability...
Read more Results The results of the Bland-Altman analysis showed no significant mean bias between the manual and automatic measurements of aortic diameters, with limits of agreement of ± 3 mm, which is clinically acceptable. These findings suggest that the AI tool performs at a comparable level of accuracy to manual measurements performed by experienced surgeons. This is a promising outcome, as it demonstrates the potential of AI to provide reliable, automated measurements that could be used in clinical practice.Additionally, the Cohen’s Kappa...
Read more Conclusion The results of this study demonstrate that the newly developed AI-based 3D tool is a highly accurate and efficient method for extracting morphological features from pre-operative CTA images for EVAR planning in AAA patients. The AI tool showed good agreement with manually extracted measurements, adhering to the European Society for Vascular Surgery (ESVS) 2024 guidelines for EVAR, and significantly reduced the time required for data extraction. The implementation of this AI tool in clinical practice could lead to more standardized...
Read more References Wanhainen, A., Van Herzeele, I., Bastos Goncalves, F., Bellmunt Montoya, S., Berard, X., Boyle, J. R., D'Oria, M., Prendes, C. F., Karkos, C. D., Kazimierczak, A., Koelemay, M. J. W., Kölbel, T., Mani, K., Melissano, G., Powell, J. T., Trimarchi, S., Tsilimparis, N., ESVS Guidelines Committee, Antoniou, G. A., Björck, M., … Yeung, K. K. (2024). Editor's Choice -- European Society for Vascular Surgery (ESVS) 2024 Clinical Practice Guidelines on the Management of Abdominal Aorto-Iliac Artery Aneurysms. European journal of vascular...
Read more
GALLERY