Jeroen Hermans

A comparison of methods for non-rigid 3D shape retrieval

Non-rigid 3D shape retrieval has become an active and important research topic in content-based 3D object retrieval. The aim of this paper is to measure and compare the performance of state-of-the-art methods for non-rigid 3D shape retrieval. The paper develops a new benchmark consisting of 600 non-rigid 3D watertight meshes, which are equally classified into 30 categories, to carry out experiments for 11 different algorithms, whose retrieval accuracies are evaluated using six commonly utilized measures. Models and evaluation tools of the new benchmark are publicly available on our web site [1].

SHREC'11 track: shape retrieval on non-rigid 3D watertight meshes

Non-rigid 3D shape retrieval has become an important research topic in content-based 3D object retrieval. The aim of this track is to measure and compare the performance of non-rigid 3D shape retrieval methods implemented by different participants around the world. The track is based on a new non-rigid 3D shape benchmark, which contains 600 watertight triangle meshes that are equally classified into 30 categories. In this track, 25 runs have been submitted by 9 groups and their retrieval accuracies were evaluated using 6 commonly-utilized measures.

A Comparative Study of 3-D Face Recognition Under Expression Variations

Research in face recognition has continuously been challenged by extrinsic (head pose, lighting conditions) and intrinsic (facial expression, aging) sources of variability. While many survey papers on face recognition exist, in this paper, we focus on a comparative study of 3-D face recognition under expression variations. As a first contribution, 3-D face databases with expressions are listed, and the most important ones are briefly presented and their complexity is quantified using the iterative closest point (ICP) baseline recognition algorithm. This allows to rank the databases according to their inherent difficulty for face-recognition tasks. This analysis reveals that the FRGC v2 database can be considered as the most challenging because of its size, the presence of expressions and outliers, and the time lapse between the recordings. Therefore, we recommend to use this database as a reference database to evaluate (expression-invariant) 3-D face-recognition algorithms. We also determine and quantify the most important factors that influence the performance. It appears that performance decreases 1) with the degree of nonfrontal pose, 2) for certain expression types, 3) with the magnitude of the expressions, 4) with an increasing number of expressions, and 5) for a higher number of gallery subjects. Future 3-D face-recognition algorithms should be evaluated on the basis of all these factors. As the second contribution, a survey of published 3-D face-recognition methods that deal with expression variations is given. These methods are subdivided into three classes depending on the way the expressions are handled. Region-based methods use expression-stable regions only, while other methods model the expressions either using an isometric or a statistical model. Isometric models assume the deformation because of expression variation to be (locally) isometric, meaning that the deformation preserves lengths along the surface. Statistical models learn how the facial soft tissue deforms during expressions based on a training database with expression labels. Algorithmic performances are evaluated by the comparison of recognition rates for identification and verification. No statistical significant differences in class performance are found between any pair of classes.

Isometric Deformation Modelling for Object Recognition

We present two methods for isometrically deformable object recognition. The methods are built upon the use of geodesic distance matrices (GDM) as an object representation. The first method compares these matrices by using histogram comparisons. The second method is a modal approach. The largest singular values or eigenvalues appear to be an excellent shape descriptor, based on the comparison with other methods also using the isometric deformation model and a general baseline algorithm. The methods are validated using the TOSCA database of non-rigid objects and a rank 1 recognition rate of 100% is reported for the modal representation method using the 50 largest eigenvalues. This is clearly higher than other methods using an isometric deformation model.

Intrafractional prostate motion during online image guided intensity-modulated radiotherapy for prostate cancer

INTRODUCTION Intrafractional motion consists of two components: (1) the movement between the on-line repositioning procedure and the treatment start and (2) the movement during the treatment delivery. The goal of this study is to estimate this intrafractional movement of the prostate during prostate cancer radiotherapy. MATERIAL AND METHODS Twenty-seven patients with prostate cancer and implanted fiducials underwent a marker match procedure before a five-field IMRT treatment. For all fields, in-treatment images were obtained and then processed to enable automatic marker detection. Combining the subsequent projection images, five positions of each marker were determined using the shortest path approach. The residual set-up error (RSE) after kV-MV based prostate localization, the prostate position as a function of time during a radiotherapy session and the required margins to account for intrafractional motion were determined. RESULTS The mean RSE and standard deviation in the antero-posterior, cranio-caudal and left-right direction were 2.3±1.5 mm, 0.2±1.1 mm and -0.1±1.1 mm, respectively. Almost all motions occurred in the posterior direction before the first treatment beam as the percentage of excursions>5 mm was reduced significantly when the RSE was not accounted for. The required margins for intrafractional motion increased with prolongation of the treatment. Application of a repositioning protocol after every beam could decrease the 1cm margin from CTV to PTV by 2 mm. CONCLUSIONS The RSE is the main contributor to intrafractional motion. This RSE after on-line prostate localization and patient repositioning in the posterior direction emphasizes the need to speed up the marker match procedure. Also, a prostate IMRT treatment should be administered as fast as possible, to ensure that the pre-treatment repositioning efforts are not erased by intrafractional prostate motion. This warrants an optimized workflow with the use of faster treatment techniques.

Isometric deformation invariant 3D shape recognition

Intra-shape deformations complicate 3D shape recognition and therefore need proper modeling. Thereto, an isometric deformation model is used in this paper. The method proposed does not need explicit point correspondences for the comparison of 3D shapes. The geodesic distance matrix is used as an isometry-invariant shape representation. Two approaches are described to arrive at a sampling order invariant shape descriptor: the histogram of geodesic distance matrix values and the set of largest singular values of the geodesic distance matrix. Shape comparison is performed by comparison of the shape descriptors using the @g^2-distance as dissimilarity measure. For object recognition, the results obtained demonstrate the singular value approach to outperform the histogram-based approach, as well as the state-of-the-art multidimensional scaling technique, the ICP baseline algorithm and other isometric deformation modeling methods found in literature. Using the TOSCA database, a rank-1 recognition rate of 100% is obtained for the identification scenario, while the verification experiments are characterized by a 1.58% equal error rate. External validation demonstrates that the singular value approach outperforms all other participants for the non-rigid object retrieval contests in SHREC 2010 as well as SHREC 2011. For 3D face recognition, the rank-1 recognition rate is 61.9% and the equal error rate is 11.8% on the BU-3DFE database. This decreased performance is attributed to the fact that the isometric deformation assumption only holds to a limited extent for facial expressions. This is also demonstrated in this paper.

Automatic 3-D Breath-Hold Related Motion Correction of Dynamic Multislice MRI

Magnetic resonance (MR) cine images are often used to clinically assess left ventricular cardiac function. In a typical study, multiple 2-D long axis (LA) and short axis (SA) cine images are acquired, each in a different breath-hold. Differences in lung volume during breath-hold and overall patient motion distort spatial alignment of the images thus complicating spatial integration of all image data in three dimensions. We present a fully automatic postprocessing approach to correct these slice misalignments. The approach is based on the constrained optimization of the intensity similarity of intersecting image lines after the automatic definition of a region of interest. It uses all views and all time frames simultaneously. Our method models both in-plane and out-of-plane translations and full 3-D rotations, can be applied retrospectively and does not require a cardiac wall segmentation. The method was validated on both healthy volunteer and patient data with simulated misalignments, as well as on clinical multibreath-hold patient data. For the simulated data, subpixel accuracy could be obtained using translational correction. The possibilities and limitations of rotational correction were investigated and discussed. For the clinical multibreath-hold patient data sets, the median discrepancy between manual SA and LA contours was reduced from 2.83 to 1.33 mm using the proposed correction method. We have also shown the usefulness of the correction method for functional analysis on clinical image data. The same clinical multibreath-hold data sets were resegmented after positional correction, taking newly available complementary information of intersecting slices into account, further reducing the median discrepancy to 0.43 mm. This is due to the integration of the 2-D slice information into 3-D space.

Robust point set registration using EM-ICP with information-theoretically optimal outlier handling

In this paper the problem of pairwise model-to-scene point set registration is considered. Three contributions are made. Firstly, the relations between correspondence-based and some information-theoretic point cloud registration algorithms are formalized. Starting from the observation that the outlier handling of existing methods relies on heuristically determined models, a second contribution is made exploiting aforementioned relations to derive a new robust point set registration algorithm. Representing model and scene point clouds by mixtures of Gaus-sians, the method minimizes their Kullback-Leibler divergence both w.r.t. the registration transformation parameters and w.r.t. the scenes mixture coefficients. This results in an Expectation-Maximization Iterative Closest Point (EM-ICP) approach with a parameter-free outlier model that is optimal in information-theoretical sense. While the current (CUDA) implementation is limited to the rigid registration case, the underlying theory applies to both rigid and non-rigid point set registration. As a by-product of the registration algorithms theory, a third contribution is made by suggesting a new point cloud Kernel Density Estimation approach which relies on maximizing the resulting distributions entropy w.r.t. the kernel weights. The rigid registration algorithm is applied to align different patches of the publicly available Stanford Dragon and Stanford Happy Budha range data. The results show good performance regarding accuracy, robustness and convergence range.

Unsupervised Segmentation, Clustering, and Groupwise Registration of Heterogeneous Populations of Brain MR Images

Population analysis of brain morphology from magnetic resonance images contributes to the study and understanding of neurological diseases. Such analysis typically involves segmentation of a large set of images and comparisons of these segmentations between relevant subgroups of images (e.g., “normal” versus “diseased”). The images of each subgroup are usually selected in advance in a supervised way based on clinical knowledge. Their segmentations are typically guided by one or more available atlases, assumed to be suitable for the images at hand. We present a data-driven probabilistic framework that simultaneously performs atlas-guided segmentation of a heterogeneous set of brain MR images and clusters the images in homogeneous subgroups, while constructing separate probabilistic atlases for each cluster to guide the segmentation. The main benefits of integrating segmentation, clustering and atlas construction in a single framework are that: 1) our method can handle images of a heterogeneous group of subjects and automatically identifies homogeneous subgroups in an unsupervised way with minimal prior knowledge, 2) the subgroups are formed by automatical detection of the relevant morphological features based on the segmentation, 3) the atlases used by our method are constructed from the images themselves and optimally adapted for guiding the segmentation of each subgroup, and 4) the probabilistic atlases represent the morphological pattern that is specific for each subgroup and expose the groupwise differences between different subgroups. We demonstrate the feasibility of the proposed framework and evaluate its performance with respect to image segmentation, clustering and atlas construction on simulated and real data sets including the publicly available BrainWeb and ADNI data. It is shown that combined segmentation and atlas construction leads to improved segmentation accuracy. Furthermore, it is demonstrated that the clusters generated by our unsupervised framework largely coincide with the clinically determined subgroups in case of disease-specific differences in brain morphology and that the differences between the cluster-specific atlases are in agreement with the expected disease-specific patterns, indicating that our method is capable of detecting the different modes in a population. Our method can thus be seen as a comprehensive image-driven population analysis framework that can contribute to the detection of novel subgroups and distinctive image features, potentially leading to new insights in the brain development and disease.

A semi-automated 2D/3D marker-based registration algorithm modelling prostate shrinkage during radiotherapy for prostate cancer

BACKGROUND AND PURPOSE Currently, most available patient alignment tools based on implanted markers use manual marker matching and rigid registration transformations to measure the needed translational shifts. To quantify the particular effect of prostate gland shrinkage, implanted gold markers were tracked during a course of radiotherapy including an isotropic scaling factor to model prostate shrinkage. MATERIALS AND METHODS Eight patients with prostate cancer had gold markers implanted transrectally and seven were treated with (neo) adjuvant androgen deprivation therapy. After patient alignment to skin tattoos, orthogonal electronic portal images (EPIs) were taken. A semi-automated 2D/3D marker-based registration was performed to calculate the necessary couch shifts. The registration consists of a rigid transformation combined with an isotropic scaling to model prostate shrinkage. RESULTS The inclusion of an isotropic shrinkage model in the registration algorithm cancelled the corresponding increase in registration error. The mean scaling factor was 0.89+/-0.09. For all but two patients, a decrease of the isotropic scaling factor during treatment was observed. However, there was almost no difference in the translation offset between the manual matching of the EPIs to the digitally reconstructed radiographs and the semi-automated 2D/3D registration. A decrease in the intermarker distance was found correlating with prostate shrinkage rather than with random marker migration. CONCLUSIONS Inclusion of shrinkage in the registration process reduces registration errors during a course of radiotherapy. Nevertheless, this did not lead to a clinically significant change in the proposed table translations when compared to translations obtained with manual marker matching without a scaling correction.