A

Accuracy of fully automated iliac artery tortuosity measurements in patients with abdominal aortic aneurysm using deep learning

European Journal of Radiology, vol. 195, pp. 112609

Abstract

OBJECTIVE: To externally validate the accuracy of deep learning-based iliac artery tortuosity assessment (PRAEVAorta 2, Bordeaux, France) in computed tomography angiography of patients with abdominal aortic aneurysms. DESIGN: Retrospective, multi-center validation study. METHODS: Data from the ZEnith alPHa for aneurYsm Repair Registry (ZEPHYR) were used. Tortuosity measurements from PRAEVAorta 2 were benchmarked against manual reference measurements from an internationally recognized core laboratory (Syntactx, New York, USA). All PRAEVAorta 2 reports were visually inspected by two observers for plausibility of the segmentation of the iliac arteries. Scans with obvious segmentation errors were excluded. Qualitative and quantitative analysis of potential risk factors for segmentation failures were conducted. The core laboratory performed manual tortuosity measurements using standard multiplanar reconstructions. RESULTS: In total, 270 CTA scans from the ZEPHYR database fulfilled the inclusion criteria and were available for analysis. 21.1 % of scans demonstrated obvious segmentation errors upon initial review and were excluded from this analysis. Most common risk factors for segmentation failure were internal iliac artery occlusions and overlapping aneurysms in the distal infrarenal aorta and proximal common iliac arteries. In the remaining 213 scans, the median iliac tortuosity measured by the core laboratory was 1.34 (IQR 1.23-1.45) while PRAEVAorta 2 reported a median tortuosity of 1.25 (IQR 1.19-1.33). The analysis showed an excellent Pearson correlation of 0.95 (95 % CI: 0.94-0.96) with a moderate to good Intraclass Correlation (ICC) of 0.73 (95 % CI: 0.69-0.77) and a bias of -0.09 in Bland-Altman analysis. CONCLUSION: PRAEVAorta 2 successfully provided fully automated measurements of the iliac artery tortuosity in most cases, highlighting its potential as a valuable tool for both research and clinical applications. However, a critical review of automatically provided reports by an experienced observer remains essential.

Authors 28

  1. Alexandru Barb corresponding

    Heidelberg University · University Hospital Heidelberg

    Affiliation as printed

    Department of Vascular and Endovascular Surgery, University Hospital Heidelberg, Im Neuenheimer Feld 420, 69120 Heidelberg, Germany. Electronic address: Alexandru.Barb@med.uni-heidelberg.de

  2. RWTH Aachen University

    Affiliation as printed

    Department of Vascular Surgery, RWTH Aachen, Templergraben 55, 52062 Aachen, Germany. Electronic address: ChristianUhl@gmx.at

  3. Louisa Bornhak corresponding

    Heidelberg University · University Hospital Heidelberg

    Affiliation as printed

    Department of Vascular and Endovascular Surgery, University Hospital Heidelberg, Im Neuenheimer Feld 420, 69120 Heidelberg, Germany. Electronic address: Louisa.Bornhak@med.uni-heidelberg.de

  4. Edris El‐Sanosy corresponding

    Heidelberg University · University Hospital Heidelberg

    Affiliation as printed

    Department of Vascular and Endovascular Surgery, University Hospital Heidelberg, Im Neuenheimer Feld 420, 69120 Heidelberg, Germany. Electronic address: Edris.el-sanosy@gmx.de

  5. Matthias Fink corresponding

    Heidelberg University · University Hospital Heidelberg

    Affiliation as printed

    Clinic for Diagnostic and Interventional Radiology, University Hospital Heidelberg, Im Neuenheimer Feld 420, 69120 Heidelberg, Germany. Electronic address: Matthias.fink@uni-heidelberg.de

  6. Dittmar Böckler corresponding

    Heidelberg University · University Hospital Heidelberg

    Affiliation as printed

    Department of Vascular and Endovascular Surgery, University Hospital Heidelberg, Im Neuenheimer Feld 420, 69120 Heidelberg, Germany. Electronic address: Dittmar.Boeckler@med.uni-heidelberg.de

  7. Johannes Hatzl corresponding

    Heidelberg University · University Hospital Heidelberg

    Affiliation as printed

    Department of Vascular and Endovascular Surgery, University Hospital Heidelberg, Im Neuenheimer Feld 420, 69120 Heidelberg, Germany. Electronic address: Johannes.hatzl@med.uni-heidelberg.de

  8. Amsterdam University Medical Centers · Amsterdam Cardiovascular Sciences

    Affiliation as printed

    Department of Vascular Surgery, Amsterdam UMC, Location VU Medical Center, Amsterdam Cardiovascular Sciences, Amsterdam, Netherlands (the)

  9. Maasstad Ziekenhuis

    Affiliation as printed

    Department of Vascular Surgery, Maasstad Hospital, Rotterdam, Netherlands (the)

  10. Paracelsus Medizinische Privatuniversität

    Affiliation as printed

    Department of Vascular and Endovascular Surgery, Paracelsus Medical University, Nuremberg, Germany

  11. Ziekenhuis Oost-Limburg

    Affiliation as printed

    Department of Vascular and Thoracic Surgery, Ziekenhuis Oost-Limburg, Genk, Belgium

  12. University Medical Center Hamburg-Eppendorf

    Affiliation as printed

    German Aortic Center Hamburg, Department of Vascular Medicine, University Medical Center Eppendorf, Hamburg, Germany

  13. Haga Hospital

    Affiliation as printed

    Departments of Vascular Surgery and Interventional Radiology, Haga Hospital, The Hague, Netherlands (the)

  14. University Hospital Leipzig

    Affiliation as printed

    Department of Angiology, University Hospital Leipzig, Leipzig, Germany

  15. Imelda Hospital

    Affiliation as printed

    Department of Vascular and Thoracic Surgery, Imelda Hospital, Bonheiden, Belgium

  16. Maastricht University Medical Centre

    Affiliation as printed

    Department of Vascular Surgery, Maastricht University Medical Centre, Maastricht, Netherlands (the)

  17. Ghent University Hospital

    Affiliation as printed

    Department of Vascular Surgery, Ghent University Hospital, Ghent, Belgium

  18. Düsseldorf University Hospital · Heinrich Heine University Düsseldorf

    Affiliation as printed

    Department of Vascular and Endovascular Surgery, Heinrich-Heine-University Medical Center Düsseldorf, Düsseldorf, Germany

  19. Catharina Ziekenhuis

    Affiliation as printed

    Department of Vascular Surgery, Catharina Hospital, Eindhoven, Netherlands (the)

  20. Amsterdam University Medical Centers · Amsterdam Cardiovascular Sciences

    Affiliation as printed

    Department of Vascular Surgery, Amsterdam UMC, Location VU Medical Center, Amsterdam Cardiovascular Sciences, Amsterdam, Netherlands (the)

  21. Maasstad Ziekenhuis

    Affiliation as printed

    Department of Vascular Surgery, Maasstad Hospital, Rotterdam, Netherlands (the)

  22. Maasstad Ziekenhuis

    Affiliation as printed

    Department of Vascular Surgery, Maasstad Hospital, Rotterdam, Netherlands (the)

  23. Paracelsus Medizinische Privatuniversität

    Affiliation as printed

    Department of Vascular and Endovascular Surgery, Paracelsus Medical University, Nuremberg, Germany

  24. Paracelsus Medizinische Privatuniversität

    Affiliation as printed

    Department of Vascular and Endovascular Surgery, Paracelsus Medical University, Nuremberg, Germany

  25. Paracelsus Medizinische Privatuniversität

    Affiliation as printed

    Department of Vascular and Endovascular Surgery, Paracelsus Medical University, Nuremberg, Germany

  26. Paracelsus Medizinische Privatuniversität

    Affiliation as printed

    Department of Vascular and Endovascular Surgery, Paracelsus Medical University, Nuremberg, Germany

  27. University Medical Center Hamburg-Eppendorf

    Affiliation as printed

    German Aortic Center Hamburg, Department of Vascular Medicine, University Medical Center Eppendorf, Hamburg, Germany

  28. Klinikum Frankfurt Höchst

    Affiliation as printed

    Section of Vascular and Endovascular Surgery, Klinikum Frankfurt Höchst, Frankfurt, Germany

Cited by 2 stored of 2

2 results

No patents citing this paper on Lens.org (checked 2026-10-06).

References 24