References of "Bernard, Florian 50016032"
     in
Bookmark and Share    
Full Text
Peer Reviewed
See detailDistributed methods for synchronization of orthogonal matrices over graphs
Thunberg, Johan UL; Bernard, Florian UL; Goncalves, Jorge UL

in Automatica (2017), 80

This paper addresses the problem of synchronizing orthogonal matrices over directed graphs. For synchronized transformations (or matrices), composite transformations over loops equal the identity. We ... [more ▼]

This paper addresses the problem of synchronizing orthogonal matrices over directed graphs. For synchronized transformations (or matrices), composite transformations over loops equal the identity. We formulate the synchronization problem as a least-squares optimization problem with nonlinear constraints. The synchronization problem appears as one of the key components in applications ranging from 3D-localization to image registration. The main contributions of this work can be summarized as the introduction of two novel algorithms; one for symmetric graphs and one for graphs that are possibly asymmetric. Under general conditions, the former has guaranteed convergence to the solution of a spectral relaxation to the synchronization problem. The latter is stable for small step sizes when the graph is quasi-strongly connected. The proposed methods are verified in numerical simulations. [less ▲]

Detailed reference viewed: 102 (3 UL)
Full Text
Peer Reviewed
See detailShape-aware surface reconstruction from sparse 3D point-clouds
Bernard, Florian UL; Salamanca Mino, Luis UL; Thunberg, Johan UL et al

in Medical Image Analysis (2017), 38

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 ... [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 ▲]

Detailed reference viewed: 160 (21 UL)
Full Text
Peer Reviewed
See detailA Combinatorial Solution to Non-Rigid 3D Shape-to-Image Matching
Bernard, Florian UL; Schmidt, Frank R.; Thunberg, Johan UL et al

in The proceedings of the IEEE Conference on Computer Vision and Pattern Recognition (CVPR) (2017)

We propose a combinatorial solution for the problem of non-rigidly matching a 3D shape to 3D image data. To this end, we model the shape as a triangular mesh and allow each triangle of this mesh to be ... [more ▼]

We propose a combinatorial solution for the problem of non-rigidly matching a 3D shape to 3D image data. To this end, we model the shape as a triangular mesh and allow each triangle of this mesh to be rigidly transformed to achieve a suitable matching to the image. By penalising the distance and the relative rotation between neighbouring triangles our matching compromises between the image and the shape information. In this paper, we resolve two major challenges: Firstly, we address the resulting large and NP-hard combinatorial problem with a suitable graph-theoretic approach. Secondly, we propose an efficient discretisation of the unbounded 6-dimensional Lie group SE(3). To our knowledge this is the first combinatorial formulation for non-rigid 3D shape-to-image matching. In contrast to existing local (gradient descent) optimisation methods, we obtain solutions that do not require a good initialisation and that are within a bound of the optimal solution. We evaluate the proposed combinatorial method on the two problems of non-rigid 3D shape-to-shape and non-rigid 3D shape-to-image registration and demonstrate that it provides promising results. [less ▲]

Detailed reference viewed: 96 (6 UL)
Full Text
See detailNovel Methods for Multi-Shape Analysis
Bernard, Florian UL

Doctoral thesis (2016)

Multi-shape analysis has the objective to recognise, classify, or quantify morphological patterns or regularities within a set of shapes of a particular object class in order to better understand the ... [more ▼]

Multi-shape analysis has the objective to recognise, classify, or quantify morphological patterns or regularities within a set of shapes of a particular object class in order to better understand the object class of interest. One important aspect of multi-shape analysis are Statistical Shape Models (SSMs), where a collection of shapes is analysed and modelled within a statistical framework. SSMs can be used as (statistical) prior that describes which shapes are more likely and which shapes are less likely to be plausible instances of the object class of interest. Assuming that the object class of interest is known, such a prior can for example be used in order to reconstruct a three-dimensional surface from only a few known surface points. One relevant application of this surface reconstruction is 3D image segmentation in medical imaging, where the anatomical structure of interest is known a-priori and the surface points are obtained (either automatically or manually) from images. Frequently, Point Distribution Models (PDMs) are used to represent the distribution of shapes, where each shape is discretised and represented as labelled point set. With that, a shape can be interpreted as an element of a vector space, the so-called shape space, and the shape distribution in shape space can be estimated from a collection of given shape samples. One crucial aspect for the creation of PDMs that is tackled in this thesis is how to establish (bijective) correspondences across the collection of training shapes. Evaluated on brain shapes, the proposed method results in an improved model quality compared to existing approaches whilst at the same time being superior with respect to runtime. The second aspect considered in this work is how to learn a low-dimensional subspace of the shape space that is close to the training shapes, where all factors spanning this subspace have local support. Compared to previous work, the proposed method models the local support regions implicitly, such that no initialisation of the size and location of these regions is necessary, which is advantageous in scenarios where this information is not available. The third topic covered in this thesis is how to use an SSM in order to reconstruct a surface from only few surface points. By using a Gaussian Mixture Model (GMM) with anisotropic covariance matrices, which are oriented according to the surface normals, a more surface-oriented fitting is achieved compared to a purely point-based fitting when using the common Iterative Closest Point (ICP) algorithm. In comparison to ICP we find that the GMM-based approach gives superior accuracy and robustness on sparse data. Furthermore, this work covers the transformation synchronisation method, which is a procedure for removing noise that accounts for transitive inconsistency in the set of pairwise linear transformations. One interesting application of this methodology that is relevant in the context of multi-shape analysis is to solve the multi-alignment problem in an unbiased/reference-free manner. Moreover, by introducing an improvement of the numerical stability, the methodology can be used to solve the (affine) multi-image registration problem from pairwise registrations. Compared to reference-based multi-image registration, the proposed approach leads to an improved registration accuracy and is unbiased/reference-free, which makes it ideal for statistical analyses. [less ▲]

Detailed reference viewed: 118 (16 UL)
Full Text
Peer Reviewed
See detailFast Correspondences for Statistical Shape Models of Brain Structures
Bernard, Florian UL; Vlassis, Nikos UL; Gemmar, Peter et al

in SPIE Medical Imaging (2016, March)

Detailed reference viewed: 200 (17 UL)
Full Text
Peer Reviewed
See detailLinear Shape Deformation Models with Local Support using Graph-based Structured Matrix Factorisation
Bernard, Florian UL; Gemmar, Peter; Hertel, Frank UL et al

in Linear Shape Deformation Models with Local Support using Graph-based Structured Matrix Factorisation (2016)

Representing 3D shape deformations by linear models in high-dimensional space has many applications in computer vision and medical imaging, such as shape-based interpolation or segmentation. Commonly ... [more ▼]

Representing 3D shape deformations by linear models in high-dimensional space has many applications in computer vision and medical imaging, such as shape-based interpolation or segmentation. Commonly, using Principal Components Analysis a low-dimensional (affine) subspace of the high-dimensional shape space is determined. However, the resulting factors (the most dominant eigenvectors of the covariance matrix) have global support, i.e. changing the coefficient of a single factor deforms the entire shape. In this paper, a method to obtain deformation factors with local support is presented. The benefits of such models include better flexibility and interpretability as well as the possibility of interactively deforming shapes locally. For that, based on a well-grounded theoretical motivation, we formulate a matrix factorisation problem employing sparsity and graph-based regularisation terms. We demonstrate that for brain shapes our method outperforms the state of the art in local support models with respect to generalisation ability and sparse shape reconstruction, whereas for human body shapes our method gives more realistic deformations. [less ▲]

Detailed reference viewed: 127 (14 UL)
Full Text
Peer Reviewed
See detailShape-aware 3D Interpolation using Statistical Shape Models
Bernard, Florian UL; Salamanca Mino, Luis UL; Thunberg, Johan UL et al

in Symposium on Statistical Shape Models and Applications, Delemont, Switzerland, October 2015 (2015, October)

Detailed reference viewed: 146 (34 UL)
Full Text
Peer Reviewed
See detailImproved Parkinson’s disease classification from diffusion MRI data by Fisher vector descriptors
Salamanca Mino, Luis UL; Vlassis, Nikos UL; Diederich, Nico UL et al

in Improved Parkinson’s disease classification from diffusion MRI data by Fisher vector descriptors (2015, October)

Due to the complex clinical picture of Parkinson’s disease (PD), the reliable diagnosis of patients is still challenging. A promising approach is the structural characterization of brain areas affected in ... [more ▼]

Due to the complex clinical picture of Parkinson’s disease (PD), the reliable diagnosis of patients is still challenging. A promising approach is the structural characterization of brain areas affected in PD by diffusion magnetic resonance imaging (dMRI). Standard classification methods depend on an accurate non-linear alignment of all images to a common reference template, and are challenged by the resulting huge dimensionality of the extracted feature space. Here, we propose a novel diagnosis pipeline based on the Fisher vector algorithm. This technique allows for a precise encoding into a high-level descriptor of standard diffusion measures like the fractional anisotropy and the mean diffusivity, extracted from the regions of interest (ROIs) typically involved in PD. The obtained low dimensional, fixed-length descriptors are independent of the image alignment and boost the linear separability of the problem in the description space, leading to more efficient and accurate diagnosis. In a test cohort of 50 PD patients and 50 controls, the implemented methodology outperforms previous methods when using a logistic linear regressor for classification of each ROI independently, which are subsequently combined into a single classification decision. [less ▲]

Detailed reference viewed: 211 (10 UL)
Full Text
Peer Reviewed
See detailTransitively Consistent and Unbiased Multi-Image Registration Using Numerically Stable Transformation Synchronisation
Bernard, Florian UL; Thunberg, Johan UL; Salamanca Mino, Luis UL et al

in MIDAS Journal (2015)

Abstract. Transitive consistency of pairwise transformations is a desir- able property of groupwise image registration procedures. The transfor- mation synchronisation method [4] is able to retrieve ... [more ▼]

Abstract. Transitive consistency of pairwise transformations is a desir- able property of groupwise image registration procedures. The transfor- mation synchronisation method [4] is able to retrieve transitively con- sistent pairwise transformations from pairwise transformations that are initially not transitively consistent. In the present paper, we present a numerically stable implementation of the transformation synchronisa- tion method for a ne transformations, which can deal with very large translations, such as those occurring in medical images where the coor- dinate origins may be far away from each other. By using this method in conjunction with any pairwise (a ne) image registration algorithm, a transitively consistent and unbiased groupwise image registration can be achieved. Experiments involving the average template generation from 3D brain images demonstrate that the method is more robust with re- spect to outliers and achieves higher registration accuracy compared to reference-based registration. [less ▲]

Detailed reference viewed: 143 (21 UL)
Full Text
Peer Reviewed
See detailAssessment of Electrode Displacement and Deformation with Respect to Pre-Operative Planning in Deep Brain Stimulation
Husch, Andreas UL; Gemmar, Peter; Lohscheller, Jörg et al

in Handels, Heinz; Deserno, Thomas Martin; Meinzer, Hans-Peter (Eds.) et al Bildverarbeitung für die Medizin 2015 (2015)

The post-operative validation of deep brain stimulation electrode displacement and deformation is an important task towards improved DBS targeting. In this paper a method is proposed to align models of ... [more ▼]

The post-operative validation of deep brain stimulation electrode displacement and deformation is an important task towards improved DBS targeting. In this paper a method is proposed to align models of deep brain stimulation electrodes that are automatically extracted from post-operative CT imaging in a common coordinate system utilizing the planning data as reference. This enables the assessment of electrode displacement and deformation over the whole length of the trajectory with respect to the pre-operative planning. Accordingly, it enables the estimation of plan deviations in the surgical process as well as cross-patient statistics on electrode deformation, e.g. the bending induced by brain-shift. [less ▲]

Detailed reference viewed: 211 (14 UL)
Full Text
Peer Reviewed
See detailA solution for Multi-Alignment by Transformation Synchronisation
Bernard, Florian UL; Thunberg, Johan UL; Gemmar, Peter et al

in The proceedings of the IEEE Conference on Computer Vision and Pattern Recognition (CVPR) (2015)

The alignment of a set of objects by means of transformations plays an important role in computer vision. Whilst the case for only two objects can be solved globally, when multiple objects are considered ... [more ▼]

The alignment of a set of objects by means of transformations plays an important role in computer vision. Whilst the case for only two objects can be solved globally, when multiple objects are considered usually iterative methods are used. In practice the iterative methods perform well if the relative transformations between any pair of objects are free of noise. However, if only noisy relative transformations are available (e.g. due to missing data or wrong correspondences) the iterative methods may fail. Based on the observation that the underlying noise-free transformations lie in the null space of a matrix that can directly be obtained from pairwise alignments, this paper presents a novel method for the synchronisation of pairwise transformations such that they are globally consistent. Simulations demonstrate that for a high amount of noise, a large proportion of missing data and even for wrong correspondence assignments the method delivers encouraging results. [less ▲]

Detailed reference viewed: 193 (38 UL)
Full Text
Peer Reviewed
See detailSusceptibility-Weighted MRI for Deep Brain Stimulation: Potentials in Trajectory Planning
Hertel, Frank UL; Husch, Andreas UL; Dooms, Georges et al

in Stereotactic & Functional Neurosurgery (2015), 93(5), 303-308

Background: Deep brain stimulation (DBS) trajectory plan- ning is mostly based on standard 3-D T1-weighted gado- linium-enhanced MRI sequences (T1-Gd). Susceptibility- weighted MRI sequences (SWI) show ... [more ▼]

Background: Deep brain stimulation (DBS) trajectory plan- ning is mostly based on standard 3-D T1-weighted gado- linium-enhanced MRI sequences (T1-Gd). Susceptibility- weighted MRI sequences (SWI) show neurovascular struc- tures without the use of contrast agents. The aim of this study was to investigate whether SWI might be useful in DBS trajectory planning. Methods: We performed bilateral DBS planning using conventional T1-Gd images of 10 patients with different kinds of movement disorders. Afterwards, we matched SWI sequences and compared the visibility of vas- cular structures in both imaging modalities. Results: By ana- lyzing 100 possible trajectories, we found a potential vascu- lar conflict in 13 trajectories based on T1-Gd in contrast to 53 in SWI. Remarkably, all vessels visible in T1-Gd were also de- picted in SWI, whereas SWI showed many additional vascular structures which could not be identified in T1-Gd. Conclu- sion/Discussion: The sensitivity for detecting neurovascular structures for DBS planning seems to be significantly higher in SWI. As SWI does not require a contrast agent, we suggest that SWI may be a valuable alternative to T1-Gd MRI for DBS trajectory planning. Furthermore, the data analysis suggests that vascular interactions of DBS trajectories might be more frequent than expected from the very low incidence of symptomatic bleedings. The explanation for this is currently the subject of debate and merits further studies. [less ▲]

Detailed reference viewed: 121 (12 UL)
Full Text
Peer Reviewed
See detailAn Extensible Development Environment for 3D Segmentations based on Active Shape Models
Bernard, Florian UL; Gemmar, Peter; Husch, Andreas UL et al

in Shape Symposium (2014)

Detailed reference viewed: 38 (6 UL)