Divergence prior and vessel-tree reconstruction
| Autor: | Marc Moreno Maza, Zhongwen Zhang, Maria Drangova, Egor Chesakov, Yuri Boykov, Dmitrii Marin |
|---|---|
| Rok vydání: | 2019 |
| Předmět: |
Computer science
business.industry Quantitative Biology::Tissues and Organs Physics::Medical Physics Optimization Methods 02 engineering and technology Curvature Regularization (mathematics) Biological and Cell Microscopy 03 medical and health sciences 0302 clinical medicine Medical 0202 electrical engineering electronic engineering information engineering Medicine and Health Sciences 020201 artificial intelligence & image processing Vector field Artificial intelligence business Algorithm 030217 neurology & neurosurgery |
| Zdroj: | Bone and Joint Institute CVPR Medical Biophysics Publications |
| Popis: | © 2019 IEEE. We propose a new geometric regularization principle for reconstructing vector fields based on prior knowledge about their divergence. As one important example of this general idea, we focus on vector fields modelling blood flow pattern that should be divergent in arteries and convergent in veins. We show that this previously ignored regularization constraint can significantly improve the quality of vessel tree reconstruction particularly around bifurcations where non-zero divergence is concentrated. Our divergence prior is critical for resolving (binary) sign ambiguity in flow orientations produced by standard vessel filters, eg Frangi. Our vessel tree centerline reconstruction combines divergence constraints with robust curvature regularization. Our unsupervised method can reconstruct complete vessel trees with near-capillary details on synthetic and real 3D volumes. |
| Databáze: | OpenAIRE |
| Externí odkaz: |
|