Reconstructing cerebrovascular networks under local physiological constraints by integer programming
- Technische Univ. Munchen (Germany); ETH Zurich (Switzerland)
- ETH Zurich (Switzerland); Univ. of Zurich (Switzerland)
- Univ. and ETH Zurich (Switzerland)
- Argonne National Lab. (ANL), Argonne, IL (United States)
- Northwestern Univ., Chicago, IL (United States)
- Computer Vision Lab., ETH Zurich (Switzerland)
- Max Planck Institute for Informatics, Saarbrucken (Germany)
- Technische Univ. Munchen (Germany)
We introduce a probabilistic approach to vessel network extraction that enforces physiological constraints on the vessel structure. The method accounts for both image evidence and geometric relationships between vessels by solving an integer program, which is shown to yield the maximum a posteriori (MAP) estimate to the probabilistic model. Starting from an over-connected network, it is pruning vessel stumps and spurious connections by evaluating the local geometry and the global connectivity of the graph. We utilize a high-resolution micro computed tomography (µCT) dataset of a cerebrovascular corrosion cast to obtain a reference network and learn the prior distributions of our probabilistic model. As a result, we perform experiments on micro magnetic resonance angiography (µMRA) images of mouse brains and discuss properties of the networks obtained under different tracking and pruning approaches.
- Research Organization:
- Argonne National Laboratory (ANL), Argonne, IL (United States)
- Sponsoring Organization:
- USDOE Office of Science (SC), Basic Energy Sciences (BES)
- Grant/Contract Number:
- AC02-06CH11357
- OSTI ID:
- 1245820
- Alternate ID(s):
- OSTI ID: 1251304
- Journal Information:
- Medical Image Analysis, Vol. 25, Issue 1; ISSN 1361-8415
- Publisher:
- ElsevierCopyright Statement
- Country of Publication:
- United States
- Language:
- English
Web of Science
Machine learning analysis of whole mouse brain vasculature
|
journal | March 2020 |
Learning Shape Representation on Sparse Point Clouds for Volumetric Image Segmentation
|
book | October 2019 |
Segmentation of Peripheral Nerves From Magnetic Resonance Neurography: A Fully-Automatic, Deep Learning-Based Approach
|
journal | September 2018 |
Similar Records
WE-DE-207A-01: Parallels in the Evolution of X-Ray Angiographic Systems and Devices Used for Minimally Invasive Endovascular Therapy
WE-DE-207A-02: Advances in Cone Beam CT Anatomical and Functional Imaging in Angio-Suite to Enable One-Stop-Shop Stroke Imaging Workflow