Automated landmarking of bends in vascular structures: a comparative study with application to the internal carotid artery

BioMedical Engineering OnLine

Kristian Valen-Sendstad¹  Aslak W Bergersen¹  Henrik A Kjeldsberg¹ 

[1] Department of Computational Physiology, Simula Research Laboratory AS, Kristian Augusts gate 23, 0164, Oslo, Norway;

关键词: Geometric characterization;    Automated landmarking;    Internal carotid artery;    Computational geometry;    Landmark detection;    Geometric risk factor;   

DOI  :  10.1186/s12938-021-00957-6

来源: Springer

【 摘 要 】

Automated tools for landmarking the internal carotid artery (ICA) bends have the potential for efficient and objective medical image-based morphometric analysis. The two existing algorithms rely on numerical approximations of curvature and torsion of the centerline. However, input parameters, original source code, comparability, and robustness of the algorithms remain unknown. To address the former two, we have re-implemented the algorithms, followed by sensitivity analyses. Of the input parameters, the centerline smoothing had the least impact resulting in 6–7 bends, which is anatomically realistic. In contrast, centerline resolution showed to completely over- and underestimated the number of bends varying from 3 to 33. Applying the algorithms to the same cohort revealed a variability that makes comparison of results between previous studies questionable. Assessment of robustness revealed how one algorithm is vulnerable to model smoothness and noise, but conceptually independent of application. In contrast, the other algorithm is robust and consistent, but with limited general applicability. In conclusion, both algorithms are equally valid albeit they produce vastly different results. We have provided a well-documented open-source implementation of the algorithms. Finally, we have successfully performed this study on the ICA, but application to other vascular regions should be performed with caution.

【 授权许可】

CC BY