Shape-aware surface reconstruction from sparse 3D point-clouds
(2017) In Medical Image Analysis 38. p.77-89- Abstract
- The reconstruction of an object’s shape or surface from a set of 3D points plays an important role in medical image analysis, e.g. in anatomy reconstruction from tomographic measurements or in the process of aligning intra-operative navigation and preoperative planning data. In such scenarios, one usually has to deal with sparse data, which significantly aggravates the problem of reconstruction. However, medical applications often provide contextual information about the 3D point data that allow to incorporate prior knowledge about the shape that is to be reconstructed. To this end, we propose the use of a statistical shape model (SSM) as a prior for surface reconstruction. The SSM is represented by a point distribution model (PDM), which... (More)
- The reconstruction of an object’s shape or surface from a set of 3D points plays an important role in medical image analysis, e.g. in anatomy reconstruction from tomographic measurements or in the process of aligning intra-operative navigation and preoperative planning data. In such scenarios, one usually has to deal with sparse data, which significantly aggravates the problem of reconstruction. However, medical applications often provide contextual information about the 3D point data that allow to incorporate prior knowledge about the shape that is to be reconstructed. To this end, we propose the use of a statistical shape model (SSM) as a prior for surface reconstruction. The SSM is represented by a point distribution model (PDM), which is associated with a surface mesh. Using the shape distribution that is modelled by the PDM, we formulate the problem of surface reconstruction from a probabilistic perspective based on a Gaussian Mixture Model (GMM). In order to do so, the given points are interpreted as samples of the GMM. By using mixture components with anisotropic covariances that are “oriented” according to the surface normals at the PDM points, a surface-based fitting is accomplished. Estimating the parameters of the GMM in a maximum a posteriori manner yields the reconstruction of the surface from the given data points. We compare our method to the extensively used Iterative Closest Points method on several different anatomical datasets/SSMs (brain, femur, tibia, hip, liver) and demonstrate superior accuracy and robustness on sparse data. (Less)
Please use this url to cite or link to this publication:
https://lup.lub.lu.se/record/64f5a904-3b8b-47ca-a9ac-09621b2c72e2
- author
- Bernard, Florian ; Salamanca, Luis ; Thunberg, Johan LU ; Tack, Alexander ; Jentsch, Dennis ; Lamecker, Hans ; Zachow, Stefan ; Hertel, Frank ; Goncalves, Jorge and Gemmar, Peter
- publishing date
- 2017
- type
- Contribution to journal
- publication status
- published
- subject
- in
- Medical Image Analysis
- volume
- 38
- pages
- 13 pages
- publisher
- Elsevier
- external identifiers
-
- scopus:85014617098
- ISSN
- 1361-8415
- DOI
- 10.1016/j.media.2017.02.005
- language
- English
- LU publication?
- no
- id
- 64f5a904-3b8b-47ca-a9ac-09621b2c72e2
- date added to LUP
- 2024-09-05 13:59:42
- date last changed
- 2025-04-04 14:58:28
@article{64f5a904-3b8b-47ca-a9ac-09621b2c72e2,
abstract = {{The reconstruction of an object’s shape or surface from a set of 3D points plays an important role in medical image analysis, e.g. in anatomy reconstruction from tomographic measurements or in the process of aligning intra-operative navigation and preoperative planning data. In such scenarios, one usually has to deal with sparse data, which significantly aggravates the problem of reconstruction. However, medical applications often provide contextual information about the 3D point data that allow to incorporate prior knowledge about the shape that is to be reconstructed. To this end, we propose the use of a statistical shape model (SSM) as a prior for surface reconstruction. The SSM is represented by a point distribution model (PDM), which is associated with a surface mesh. Using the shape distribution that is modelled by the PDM, we formulate the problem of surface reconstruction from a probabilistic perspective based on a Gaussian Mixture Model (GMM). In order to do so, the given points are interpreted as samples of the GMM. By using mixture components with anisotropic covariances that are “oriented” according to the surface normals at the PDM points, a surface-based fitting is accomplished. Estimating the parameters of the GMM in a maximum a posteriori manner yields the reconstruction of the surface from the given data points. We compare our method to the extensively used Iterative Closest Points method on several different anatomical datasets/SSMs (brain, femur, tibia, hip, liver) and demonstrate superior accuracy and robustness on sparse data.}},
author = {{Bernard, Florian and Salamanca, Luis and Thunberg, Johan and Tack, Alexander and Jentsch, Dennis and Lamecker, Hans and Zachow, Stefan and Hertel, Frank and Goncalves, Jorge and Gemmar, Peter}},
issn = {{1361-8415}},
language = {{eng}},
pages = {{77--89}},
publisher = {{Elsevier}},
series = {{Medical Image Analysis}},
title = {{Shape-aware surface reconstruction from sparse 3D point-clouds}},
url = {{http://dx.doi.org/10.1016/j.media.2017.02.005}},
doi = {{10.1016/j.media.2017.02.005}},
volume = {{38}},
year = {{2017}},
}