| Autor: |
Kuckertz, Sven, Papenberg, Nils, Honegger, Jonas, Morgas, Tomasz, Haas, Benjamin, Heldmann, Stefan |
| Jazyk: |
angličtina |
| Rok vydání: |
2020 |
| Předmět: |
|
| Zdroj: |
Biomedical Image Registration |
| Popis: |
Accurate registration of CT and CBCT images is key for adaptive radiotherapy. A particular challenge is the alignment of flexible organs, such as bladder or rectum, that often yield extreme deformations. In this work we analyze the impact of so-called structure guidance for learning based registration when additional segmentation information is provided to a neural network. We present a novel weakly supervised deep learning based method for multi-modal 3D deformable CT-CBCT registration with structure guidance constraints. Our method is not supervised by ground-truth deformations and we use the energy functional of a variational registration approach as loss for training. Incorporating structure guidance constraints in our learning based approach results in an average Dice score of \documentclass[12pt]{minimal} \usepackage{amsmath} \usepackage{wasysym} \usepackage{amsfonts} \usepackage{amssymb} \usepackage{amsbsy} \usepackage{mathrsfs} \usepackage{upgreek} \setlength{\oddsidemargin}{-69pt} \begin{document}$$0.91\pm 0.08$$\end{document} compared to a score of \documentclass[12pt]{minimal} \usepackage{amsmath} \usepackage{wasysym} \usepackage{amsfonts} \usepackage{amssymb} \usepackage{amsbsy} \usepackage{mathrsfs} \usepackage{upgreek} \setlength{\oddsidemargin}{-69pt} \begin{document}$$0.76\pm 0.15$$\end{document} for the same method without constraints. An iterative registration approach with structure guidance results in a comparable average Dice score of \documentclass[12pt]{minimal} \usepackage{amsmath} \usepackage{wasysym} \usepackage{amsfonts} \usepackage{amssymb} \usepackage{amsbsy} \usepackage{mathrsfs} \usepackage{upgreek} \setlength{\oddsidemargin}{-69pt} \begin{document}$$0.91\pm 0.09$$\end{document}. However, learning based registration requires only a single pass through the network, yielding computation of a deformation fields in less than 0.1 s which is more than 100 times faster than the runtime of iterative registration. |
| Databáze: |
OpenAIRE |
| Externí odkaz: |
|
