Abstract
Background In the active shape model framework, principal component analysis (PCA) based statistical shape models (SSMs) are widely employed to incorporate high-level a priori shape knowledge of the structure to be segmented to achieve robustness. A crucial component of building SSMs is to establish shape correspondence between all training shapes, which is a very challenging task, especially in three dimensions.Methods We propose a novel mesh-to-volume registration based shape correspondence establishment method to improve the accuracy and reduce the computational cost. Specifically, we present a greedy algorithm based deformable simplex mesh that uses vector field convolution as the external energy. Furthermore, we develop an automatic shape initialization method by using a Gaussian mixture model based registration algorithm, to derive an initial shape that has high overlap with the object of interest, such that the deformable models can then evolve more locally. We apply the proposed deformable surface model to the application of femur statistical shape model construction to illustrate its accuracy and efficiency.ResultsExtensive experiments on ten femur CT scans show that the quality of the constructed femur shape models via the proposed method is much better than that of the classical spherical harmonics (SPHARM) method. Moreover, the proposed method achieves much higher computational efficiency than the SPHARM method.ConclusionsThe experimental results suggest that our method can be employed for effective statistical shape model construction.
Highlights
Medical image segmentation is a prerequisite for various clinical applications, such as medical diagnosis, treatment planning and image-guided surgery
This paper significantly extends our preliminary conference paper on gradient vector flow (GVF)-based deformable simplex meshes [21] by (1) introducing a new vector field convolution (VFC) external energy, (2) developing an automatic shape initialization method, and (3) applying our method to establish shape correspondence and construct statistical shape models
Background we briefly show the main geometry of simplex meshes [21], the reader is referred to [15] for the detailed definition
Summary
We describe the details of the proposed deformable surface model based statistical shape models construction method It adopts a greedy algorithm which allows simplex meshes to converge on the object of interest under the constraints of both internal energy and VFC external energy. Considering that no noise is presented in our binary input images, we propose to normalize the edge map f(x, y, z) to [0, 1] before the computation of VFC energy, in order to alleviate the leakage problem and preserve the weak yet important edges. Statistical shape model construction Using our proposed greedy algorithm-based deformable simplex meshes, we obtain a set of K corresponding femur training shapes {Mi | i = 1, 2, . I=√1 t > 0.98}, and bm is the shape parameter constrained to the interval bm ∈ −3 m, 3 m
Sign-in/Register to view highlights & summary Talk to us
Join us for a 30 min session where you can share your feedback and ask us any queries you have
Schedule a callDisclaimer: All third-party content on this website/platform is and will remain the property of their respective owners and is provided on "as is" basis without any warranties, express or implied. Use of third-party content does not indicate any affiliation, sponsorship with or endorsement by them. Any references to third-party content is to identify the corresponding services and shall be considered fair use under The CopyrightLaw.
