Affiliation:
1. Department of Simulation and Graphics , OvG-University , Magdeburg , Germany
2. Department of Radiology , Ameos Hospital Bernburg , Bernburg , Germany
Abstract
Abstract
In this study, we propose a method for marker detection in X-ray fluoroscopy sequences based on adaptive thresholding and classification. Adaptive thresholding yields multiple marker candidates. To remove non-marker areas, 24 specific features are extracted from each extracted patch and four supervised classifiers are trained to differentiate non-marker areas from marker areas. Quantitative evaluation was carried out to assess different classifier performance by calculating accuracy, sensitivity, specificity and precision. SVM outperforms other classifiers based on the mean value for accuracy, specificity and precision with 81.56, 91.94 and 84.21%, respectively.
Funder
German Research Foundation
Federal Ministry of Education and Research
European Structural and Investment Funds
Reference9 articles.
1. Reiml, S, Pfister, M, Toth, D, Maier, A, Hoffmann, M, Kowarschik, M, et al. Automatic detection of stent graft markers in 2d fluoroscopy images. In: Joint MICCAI workshops on CVII-STENT; 2015.
2. Movassaghi, B, Schaefer, D, Grass, M, Rasche, V, Wink, O, Garcia, JA, et al. 3d reconstruction of coronary stents in vivo based on motion compensated x-ray angiograms. In: International conference on medical image computing and computer-assisted intervention: Springer; 2006:177–84 pp.
3. Bismuth, V, Vaillant, R, Funck, F, Guillard, N, Najman, L. A comprehensive study of stent visualization enhancement in x-ray images by image processing means. Med Image Anal 2011;15:565–76. https://doi.org/10.1016/j.media.2011.03.002.
4. Wang, Y, Chen, T, Wang, P, Rohkohl, C, Comaniciu, D. Automatic localization of balloon markers and guidewire in rotational fluoroscopy with application to 3d stent reconstruction. In: European conference on computer vision: Springer; 2012:428–41 pp.
5. Schoonenberg, G, Lelong, P, Florent, R, Wink, O, ter Haar Romeny, B. The effect of automated marker detection on in vivo volumetric stent reconstruction. In: International conference on medical image computing and computer-assisted intervention: Springer; 2008:87–94 pp.
Cited by
3 articles.
订阅此论文施引文献
订阅此论文施引文献，注册后可以免费订阅5篇论文的施引文献，订阅后可以查看论文全部施引文献