Registration of vascular structures using a hybrid mixture model

Bayer, Siming; Zhai, Zhiwei; Strumia, Maddalena; Tong, Xiaoguang; Gao, Ying; Staring, Marius; Stoel, Berend C.; Fahrig, Rebecca; Nabavi, Arya; Maier, Andreas; Ravikumar, Nishant

doi:10.1007/s11548-019-02007-y

Cited by 4 publications

(6 citation statements)

References 32 publications

Supporting

Mentioning

Contrasting

Order By: Relevance

“…1. The vessel centerline of the synthetic data and phantom data are extracted and aligned using the framework proposed in [2]. The catheters in the clinical data are registered as described in [8].…”

Section: Resultsmentioning

confidence: 99%

“…One of the state-of-the-art interpolation technique is B-Spline interpolation [1]. It has been widely employed for various clinical applications such as registration of breast MR images [1] or intraoperative brain shift compensation [2]. Thin-Plate-Splines (TPS) proposed in [3] are another common choice for deformable image warping, and has been applied e. g. for 3D-3D [4] registration of vasculature.…”

Section: Introductionmentioning

confidence: 99%

“…We present a first investigation of the performance of GP for feature-based deformable registration, including comparison with B-Spline interpolation and analysis of hyperparameter setting. To this end, correspondence of selected features are established using the method proposed in [2] and [8]. Subsequently, GP with squared exponential kernel is employed to interpolate the sparse deformation field to a dense one and to estimate an associated uncertainty map.…”

Section: Introductionmentioning

confidence: 99%

See 2 more Smart Citations

Investigation of Feature-Based Nonrigid Image Registration Using Gaussian Process

et al. 2020

Self Cite

View full text Add to dashboard Cite

For a wide range of clinical applications, such as adaptive treatment planning or intraoperative image update, feature-based deformable registration (FDR) approaches are widely employed because of their simplicity and low computational complexity. FDR algorithms estimate a dense displacement field by interpolating a sparse field, which is given by the established correspondence between selected features. In this paper, we consider the deformation field as a Gaussian Process (GP), whereas the selected features are regarded as prior information on the valid deformations. Using GP, we are able to estimate the both dense displacement field and a corresponding uncertainty map at once. Furthermore, we evaluated the performance of different hyperparameter settings for squared exponential kernels with synthetic, phantom and clinical data respectively. The quantitative comparison shows, GP-based interpolation has performance on par with state-of-the-art B-spline interpolation. The greatest clinical benefit of GP-based interpolation is that it gives a reliable estimate of the mathematical uncertainty of the calculated dense displacement map.

show abstract

Section: Resultsmentioning

confidence: 99%

Section: Introductionmentioning

confidence: 99%

Section: Introductionmentioning

confidence: 99%

See 1 more Smart Citation

Investigation of Feature-Based Nonrigid Image Registration Using Gaussian Process

et al. 2020

Self Cite

View full text Add to dashboard Cite

show abstract

“…The non-rigid registration with the hybrid mixture models (HMMs) have been proposed by researchers [47]- [49]. The Student t distribution models are used to model the positional error while the uncertainties with the normal vectors are modelled with Fisher mixture models (FMMs) [47], [48]. In [47], Ravikumar et al have formulated and solved the group-wise registration problem with normal vectors for both rigid and non-rigid registration problems.…”

Section: A Probabilistic Registration Methodsmentioning

confidence: 99%

Joint Rigid Registration of Multiple Generalized Point Sets With Anisotropic Positional Uncertainties in Image-Guided Surgery

Min

Wang

Meng

2022

IEEE Trans. Automat. Sci. Eng.

View full text Add to dashboard Cite

In medical image analysis (MIA) and computerassisted surgery (CAS), aligning two multiple point sets (PSs) together is an essential but also a challenging problem. For example, rigidly aligning multiple point sets into one common coordinate frame is a prerequisite for statistical shape modelling (SSM). Accurately aligning the pre-operative space with the intraoperative space in CAS is very crucial to successful interventions. In this article, we formally formulate the multiple generalized point set registration problem (MGPSR) in a probabilistic manner, where both the positional and the normal vectors are used. The six-dimensional vectors consisting of both positional and normal vectors are called as generalized points. In the formulated model, all the generalized PSs to be registered are considered to be the realizations of underlying unknown hybrid mixture models (HMMs). By assuming the independence of the positional and orientational vectors (i.e., the normal vectors), the probability density function (PDF) of an observed generalized point is computed as the product of Gaussian and Fisher distributions. Furthermore, to consider the anisotropic noise in surgical navigation, the positional error is assumed to obey a multi-variate Gaussian distribution. Finally, registering PSs is formulated as a maximum likelihood (ML) problem, and solved under the expectation maximization (EM) technique. By using more enriched information (i.e., the normal vectors), our algorithm is more robust to outliers. By treating all PSs equally, our algorithm does not bias towards any PS. To validate the Manuscript

show abstract

“…Under the iterative closest point (ICP) framework, the NICP [24] and G-IMOP [25], [26] methods incorporate the estimated surface normal vectors into both correspondence and registration stages of their algorithms. In both orthopedic and cardiac surgeries, both position vectors and normal vectors are utilized to enable intra-operative guidance in both pair-wise [27]- [29] and group-wise generalized PSR problems [30]- [32], and in both rigid [33] and non-rigid PSR problems [27], [28], [30]- [32], [34]. In neurosurgery, the extracted features from the multi-modal brain images could be utilized to screen the outliers [14], [35].…”

mentioning

confidence: 99%

Aligning 3D Curve With Surface Using Tangent and Normal Vectors for Computer-Assisted Orthopedic Surgery

Min

Zhu

Liu

et al. 2021

IEEE Trans. Med. Robot. Bionics

View full text Add to dashboard Cite

Registration that aligns different views of one interested organ together is an essential technique and outstanding problem in medical robotics and image-guided surgery (IGS). This work introduces a novel rigid point set registration (PSR) approach that aims to accurately map the pre-operative space with the intra-operative space to enable successful image guidance for computer-assisted orthopaedic surgery (CAOS). The normal vectors and tangent vectors are first extracted from the pre-operative and intra-operative point sets (PSs) respectively, and are further utilized to enhance the registration accuracy and robustness. The contributions of this article are threefolds. First, we propose and formulate a novel distribution that describes the error between one normal vector and the corresponding tangent vector based on the von-Mises Fisher (vMF) distribution. Second, by modelling the anisotropic position localization error with the multi-variate Gaussian distribution, we formulate the PSR considering anisotropic localization error as a maximum likelihood estimation (MLE) problem and then solve it under the expectation maximization (EM) framework. Third, to facilitate the optimization process, the gradients of the objective function with respect to the desired parameters are computed and presented. Extensive experimental results on the human femur and pelvis models verify that the proposed approach outperforms the state-of-the-art methods, and demonstrate potential clinical values for relevant surgical navigation applications.

show abstract

Registration of vascular structures using a hybrid mixture model

Abstract: This is a repository copy of Registration of vascular structures using a hybrid mixture model.

Cited by 4 publications

References 32 publications

Investigation of Feature-Based Nonrigid Image Registration Using Gaussian Process

Investigation of Feature-Based Nonrigid Image Registration Using Gaussian Process

Joint Rigid Registration of Multiple Generalized Point Sets With Anisotropic Positional Uncertainties in Image-Guided Surgery

Aligning 3D Curve With Surface Using Tangent and Normal Vectors for Computer-Assisted Orthopedic Surgery

Contact Info

Product

Resources

About