Jon Sporring

Evaluation of Registration Methods on Thoracic CT: The EMPIRE10 Challenge

EMPIRE10 (Evaluation of Methods for Pulmonary Image REgistration 2010) is a public platform for fair and meaningful comparison of registration algorithms which are applied to a database of intra patient thoracic CT image pairs. Evaluation of nonrigid registration techniques is a nontrivial task. This is compounded by the fact that researchers typically test only on their own data, which varies widely. For this reason, reliable assessment and comparison of different registration algorithms has been virtually impossible in the past. In this work we present the results of the launch phase of EMPIRE10, which comprised the comprehensive evaluation and comparison of 20 individual algorithms from leading academic and industrial research groups. All algorithms are applied to the same set of 30 thoracic CT pairs. Algorithm settings and parameters are chosen by researchers expert in the con figuration of their own method and the evaluation is independent, using the same criteria for all participants. All results are published on the EMPIRE10 website (http://empire10.isi.uu.nl). The challenge remains ongoing and open to new participants. Full results from 24 algorithms have been published at the time of writing. This paper details the organization of the challenge, the data and evaluation methods and the outcome of the initial launch with 20 algorithms. The gain in knowledge and future work are discussed.

Gaussian Scale-Space Theory

Preface. Scale in Perspective J.J. Koenderink. I: Applications. 1. Applications of Scale-Space Theory B. ter Haar Romeny. 2. Enhancement of Fingerprint Images Using Shape-Adapted Scale-Space Operators A. Almansa, T. Lindeberg. 3. Optic Flow and Stereo W.J. Niessen, R. Maas. II: The Foundation. 4. On The History of Gaussian Scale-Space Axiomatics J. Weickert, et al. 5. Scale-Space and Measurement Duality L. Florack. 6. On The Axiomatic Foundations of Linear Scale-Space T. Lindeberg. 7. Scale-Space Generators and Functionals M. Nielsen. 8. Invariance Theory A. Salden. 9. Stochastic Analysis of Image Acquisition and Scale-Space Smoothing K. Astrom, A. Heyden. III: The Structure. 10. Local Analysis of Image Scale Space P. Johansen. 11. Local Morse Theory for Gaussian Blurred Functions J. Damon. 12. Critical Point Events in Affine Scale-Space L. Griffin. 13. Topological Numbers and Singularities S. Kalitzin. 14. Multi-Scale Watershed Segmentation O.F. Olsen. IV: Non-Linear Extensions. 15. The Morphological Equivalent of Gaussian Scale-Space R. van den Boomgaard, L. Dorst. 16. Nonlinear Diffusion Scale-Spaces J. Weickert. Bibliography. Index.

Vessel-guided airway tree segmentation: A voxel classification approach

This paper presents a method for airway tree segmentation that uses a combination of a trained airway appearance model, vessel and airway orientation information, and region growing. We propose a voxel classification approach for the appearance model, which uses a classifier that is trained to differentiate between airway and non-airway voxels. This is in contrast to previous works that use either intensity alone or hand crafted models of airway appearance. We show that the appearance model can be trained with a set of easily acquired, incomplete, airway tree segmentations. A vessel orientation similarity measure is introduced, which indicates how similar the orientation of an airway candidate is to the orientation of the neighboring vessel. We use this vessel orientation similarity measure to overcome regions in the airway tree that have a low response from the appearance model. The proposed method is evaluated on 250 low dose computed tomography images from a lung cancer screening trial. Our experiments showed that applying the region growing algorithm on the airway appearance model produces more complete airway segmentations, leading to on average 20% longer trees, and 50% less leakage. When combining the airway appearance model with vessel orientation similarity, the improvement is even more significant (p<0.01) than only using the airway appearance model, with on average 7% increase in the total length of branches extracted correctly.

Information measures in scale-spaces

This article investigates Renyis (1976) generalized entropies under linear and nonlinear scale-space evolutions of images. Scale-spaces are useful computer vision concepts for both scale analysis and image restoration. We regard images as densities and prove monotony and smoothness properties for the generalized entropies. The scale-space extended generalized entropies are applied to global scale selection and size estimations. Finally, we introduce an entropy-based fingerprint description for textures.

Virtual trackballs revisited

Rotation of three-dimensional objects by a two-dimensional mouse is a typical task in computer-aided design, operation simulations, and desktop virtual reality. The most commonly used rotation technique is a virtual trackball surrounding the object and operated by the mouse pointer. We review and provide a mathematical foundation for virtual trackballs. The first, but still popular, virtual trackball was described by Chen et al. (1998). We show that the virtual trackball by Chen et al. does not rotate the object along the intended great circular arc on the virtual trackball and we give a correction. Another popular virtual trackball is Shoemakes quaternion implementation (1992), which we show to be a special case of the virtual trackball by Chen et al.. Shoemake extends the scope of the virtual trackball to the full screen. Unfortunately, Shoemakes virtual trackball is inhomogeneous and discontinuous with consequences for usability. Finally, we review Bells virtual trackball (1998) and discuss studies of the usability of virtual trackballs.

Mass preserving image registration for lung CT

This paper presents a mass preserving image registration algorithm for lung CT images. To account for the local change in lung tissue intensity during the breathing cycle, a tissue appearance model based on the principle of preservation of total lung mass is proposed. This model is incorporated into a standard image registration framework with a composition of a global affine and several free-form B-Spline transformations with increasing grid resolution. The proposed mass preserving registration method is compared to registration using the sum of squared intensity differences as a similarity function on four groups of data: 44 pairs of longitudinal inspiratory chest CT scans with small difference in lung volume; 44 pairs of longitudinal inspiratory chest CT scans with large difference in lung volume; 16 pairs of expiratory and inspiratory CT scans; and 5 pairs of images extracted at end exhale and end inhale phases of 4D-CT images. Registration errors, measured as the average distance between vessel tree centerlines in the matched images, are significantly lower for the proposed mass preserving image registration method in the second, third and fourth group, while there is no statistically significant difference between the two methods in the first group. Target registration error, assessed via a set of manually annotated landmarks in the last group, was significantly smaller for the proposed registration method.

Diffeomorphic spectral matching of cortical surfaces

Accurate matching of cortical surfaces is necessary in many neuroscience applications. In this context diffeomorphisms are often sought, because they facilitate further statistical analysis and atlas building. Present methods for computing diffeomorphisms are based on optimizing flows or on inflating surfaces to a common template, but they are often computationally expensive. It typically takes several hours on a conventional desktop computer to match a single pair of cortical surfaces having a few hundred thousand vertices. We propose a very fast alternative based on an application of spectral graph theory on a novel association graph. Our symmetric approach can generate a diffeomorphic correspondence map within a few minutes on high-resolution meshes while avoiding the sign and multiplicity ambiguities of conventional spectral matching methods. The eigenfunctions are shared between surfaces and provide a smooth parameterization of surfaces. These properties are exploited to compute differentials on highly folded cortical surfaces. Diffeomorphisms can thus be verified and invalid surface folding detected. Our method is demonstrated to attain a vertex accuracy that is at least as good as that of FreeSurfer and Spherical Demons but in only a fraction of their processing time. As a practical experiment, we construct an unbiased atlas of cortical surfaces with a speed several orders of magnitude faster than current methods.

The visible ear: A digital image library of the temporal bone

High-fidelity computer-based modeling, simulation and visualization systems for the study of temporal bone anatomy and training for middle ear surgery are based on a sequence of digital anatomical images, which must cover a large tissue volume and yet display details in high resolution and with high fidelity. However, the use of existing image libraries by independent developers of virtual models of the ear is limited by copyright protection and low image resolution. A fresh frozen human temporal bone was CT-scanned and serially sectioned at 25 µm and digital images of the block surface were recorded at 50- to 100-µm increments with a Light PhaseTM single-shot camera back attachment. A total of 605 images were recorded in 24-bit RGB resolution. After color correction and elimination of image size variation by differential cropping to 15.4 cm × 9.7 cm, all images were resampled to 3,078 × 1,942 pixels at a final resolution of 50 µm/pixel and stored as 605 one-Mb JPEG files together with a three-dimensional viewer. The resulting complete set of image data provides: (1) a source material suitable for generating computer models of the human ear; (2) a resource of high-quality digital images of anatomical cross sections from the human ear, and (3) a PC-based viewer of the temporal bone in three perpendicular planes of section.

Photon differentials

A number of popular global illumination algorithms uses density estimation to approximate indirect illumination. The density estimate is performed on finite points -- particles -- generated by a stochastic sampling of the scene. In the course of the sampling, particles, representing light, are stochastically emitted from the light sources and reflected around the scene. The sampling induces noise, which in turn is handled by the density estimate during the illumination reconstruction. Unfortunately, this noise reduction imposes a systematic error (bias), which is seen as a blurring of prominent illumination features. This is often not desirable as these may lose clarity or vanish altogether. We present an accurate method for reconstruction of indirect illumination with photon mapping. Instead of reconstructing illumination using classic density estimation on finite points, we use the correlation of light footprints, created by using Ray Differentials during the light pass. This procedure gives a high illumination accuracy, improving the trade-off between bias and variance considerable as compared to traditional particle tracing algorithms. In this way we preserve structures in indirect illumination.

Airway Tree Extraction with Locally Optimal Paths

This paper proposes a method to extract the airway tree from CT images by continually extending the tree with locally optimal paths. This is in contrast to commonly used region growing based approaches that only search the space of the immediate neighbors. The result is a much more robust method for tree extraction that can overcome local occlusions. The cost function for obtaining the optimal paths takes into account of an airway probability map as well as measures of airway shape and orientation derived from multi-scale Hessian eigen analysis on the airway probability. Significant improvements were achieved compared to a region growing based method, with up to 36% longer trees at a slight increase of false positive rate.