DOI | Resolve DOI: https://doi.org/10.1109/TBME.2013.2272657 |
---|
Author | Search for: Lecron, Fabian; Search for: Boisvert, Jonathan1; Search for: Mahmoudi, Saïd; Search for: Labelle, Hubert; Search for: Benjelloun, Mohammed |
---|
Affiliation | - National Research Council of Canada. Information and Communication Technologies
|
---|
Format | Text, Article |
---|
Subject | 3D reconstruction; Biomedical applications; One-class support vector machines (OCSVM); scoliosis; State-of-the-art methods; Statistical shape model; Gaussian distribution; Hospital data processing; Medical applications; Support vector machines; accuracy; algorithm; anatomic model; image reconstruction; sensitivity analysis; statistical shape model; validity |
---|
Abstract | Statistical shape models have become essential for medical image registration or segmentation and are used in many biomedical applications. These models are often based on Gaussian distributions learned from a training set. We propose in this paper a shape model which does not rely on the estimation of a Gaussian distribution, but on similarities computed with a kernel function. Our model takes advantage of the one-class support vector machine (OCSVM) to do so. In this context, we propose in this paper a method for reconstructing the spine of scoliotic patients using OCSVM regularization. Current state-of-the-art methods use conventional statistical shape models, and the reconstruction is commonly processed by minimizing a Mahalanobis distance. Nevertheless, when a shape differs significantly from the statistical model, the associated Mahalanobis distance often overstates the need for statistical regularization. We show that OCSVM regularization is more robust and is less sensitive to weak landmarks definition and is hardly influenced by the presence of outliers in the training data. The proposed OCSVM model applied to 3-D spine reconstruction was evaluated on real patient data, and results showed that our approach allows precise reconstruction. |
---|
Publication date | 2013-07-10 |
---|
In | |
---|
Language | English |
---|
Peer reviewed | Yes |
---|
NPARC number | 21270442 |
---|
Export citation | Export as RIS |
---|
Report a correction | Report a correction (opens in a new tab) |
---|
Record identifier | e3ad19b5-e670-4b90-b58c-817120035848 |
---|
Record created | 2014-02-11 |
---|
Record modified | 2020-04-22 |
---|