Huang Y, Lu Y, Taubmann O, Lauritsch G, Maier A (2018)
Publication Language: English
Publication Type: Conference contribution, Original article
Publication year: 2018
Publisher: Springer
Edited Volumes: Informatik aktuell
City/Town: Springer
Pages Range: 222-227
Conference Proceedings Title: Bildverarbeitung für die Medizin 2018 Algorithmen - Systeme - Anwendungen
ISBN: 978-3-662-56537-7
URI: https://www5.informatik.uni-erlangen.de/Forschung/Publikationen/2018/Huang18-TML.pdf
DOI: 10.1007/978-3-662-56537-7
In this work, the application of traditional machine learning techniques, in the form of regression models based on conventional, “hand-crafted” features, to streak reduction in limited angle tomography is investigated. Specifically, linear regression (LR), multi-layer perceptron (MLP), and reduced-error pruning tree (REPTree) are investigated. When choosing the mean-variation-median (MVM), Laplacian, and Hessian features, REPTree learns streak artifacts best and reaches the smallest root-mean-square error (RMSE) of 29HU for the Shepp-Logan phantom. Further experiments demonstrate that the MVM and Hessian features complement each other, whereas the Laplacian feature is redundant in the presence of MVM. Preliminary experiments on clinical data suggests that further investigation of clinical applications using REPTree may be worthwhile.
APA:
Huang, Y., Lu, Y., Taubmann, O., Lauritsch, G., & Maier, A. (2018). Traditional Machine Learning Techniques for Streak Artifact Reduction in Limited Angle Tomography. In Andreas Maier,Thomas M. Deserno, Heinz Handels, Klaus Hermann Maier-Hein, Christoph Palm,Thomas Tolxdorff (Eds.), Bildverarbeitung für die Medizin 2018 Algorithmen - Systeme - Anwendungen (pp. 222-227). Erlangen, DE: Springer: Springer.
MLA:
Huang, Yixing, et al. "Traditional Machine Learning Techniques for Streak Artifact Reduction in Limited Angle Tomography." Proceedings of the Bildverarbeitung für die Medizin 2018, Erlangen Ed. Andreas Maier,Thomas M. Deserno, Heinz Handels, Klaus Hermann Maier-Hein, Christoph Palm,Thomas Tolxdorff, Springer: Springer, 2018. 222-227.
BibTeX: Download