Combining some labeled images is a quite common and useful task in image analysis.
That's something we may want to do to prepare the markers for a watershed from
markers for example, or to write the output of several segmentations in a single
file.
This article comes with three new filters to make the combination
of labeled images easier with ITK.
This contribution also try to provide an implementation better integrated with the
ITK pipeline model than the itkMultipleUnlabeledImagesToLabeledImageFilter contribution.

Combining labeled images with ITK

Although Gabor filtering is quite prevalent in the computer vision community for such tasks as 
texture segmentation and motion analysis, such capabilities are conspicuously absent from the 
Insight Toolkit. The contribution described in this paper attempts to remedy this deficiency by 
introducing two new classes: itkGaborKernelFunction and itkGaborImageSource.

Go-Go Gabor Gadgetry

ManagedITK generates wrappers around ITK for .NET languages. These wrappers can be used with any CLR language, including C#, VB.NET, IronPython, and others. ManagedITK is useful for a number of reasons, including the ability to rapidly create graphical user interfaces using Windows Forms (also known as System.Windows.Forms). Full source code and many in-depth examples accompany this article. Pre-compiled .NET assemblies can also be downloaded for easy integration into standalone C# applications.

ManagedITK: .NET Wrappers for ITK

This article presents the itk::ComposeRGBAImageFilter.

ComposeRGBA

This article provides an implementation of our non-parametric diffeomorphic image registration algorithm generalizing Thirion's demons algorithm. Within the Insight Toolkit (ITK), the demons algorithm is implemented as part of the finite difference solver framework. We show that this framework can be extended to handle diffeomorphic transformations. The source code is composed of a set of reusable ITK filters and classes. In addition to an overview of our implementation, we provide a small example program that allows the user to compare the different variants of the demons algorithm.

Diffeomorphic Demons Using ITK's Finite Difference Solver Hierarchy

This paper describes the Insight Toolkit (ITK) Spherical Wavelet object: itkSWaveletSource. This
ITK object is an implementation of a paper by Schr¨oder and W. Sweldens, “Spherical Wavelets: Effi-
ciently Representing Functions on the Sphere” [8], with pseudo-code given in their paper entitled “Spherical
wavelets: Texture processing” [7]. In these papers, Swelden et. al. show how to do decompose a
scalar signal defined on a spherical mesh into spherical wavelet coefficients (analysis step, also called
forward transform), and vice-versa (synthesis step, also called inverse transform). We have implemented
the spherical wavelet transform in ITK entitled itkSWaveletSource object, which will take the scalar
function defined on a spherical mesh as input and apply spherical wavelet analysis and synthesis on it.
In this paper, we describe our code and provide the user with enough details to reproduce the results
which we present in this paper. This filter has a variety of applications including shape representation
and shape analysis of brain surfaces, which was the initial motivation for this work.
This paper is accompanied with the source code, input data, parameters and output data that the
authors used for validating the spherical wavelet transform described in this paper.

Spherical Wavelet ITK Filter

This paper describes the implementation of a multidimensional block-matching nonrigid registration
algorithm. The main features of the algorithm are its simplicity, its free form nature, the modularity of
the similarity measure, which makes it possible using local entropy-based similarity measures and the
avoidance of the optimization module. The algorithm implementation described in this paper is based
on the method by Suarez et al. This paper, which has already been submitted to the Insight
Journal, is accompanied with the source code, input data, parameters and output data used for validating
the algorithm described in it.

Fast BlockMatching Registration with Entropy-based Similarity

In this paper, we describe a database of cine-MR (3D+t) images of the
left ventricle. This database contains the voxel data, one automated
and two manual segmentations for each sequence of images. The
segmentations are validated from a clinical point of view. We detail
how the images were obtained, as well as how the associated
segmentations were performed. We also provide the data clinical
validation process.

This database, including tools to compute quantitative measures and
the software package used to obtain the automated segmentation, is
freely available for research purposes.

An open, clinically-validated database of 3D+t cine-MR images of the left ventricle with associated manual and automated segmentation

Volumetric layers often encountered in medical image analysis are characterized by double and nested bounding surfaces. The thickness of a volumetric layer at a point on the bounding surface is the distance from that point to the opposite surface. There exist several definitions for the layer thickness. A newly proposed thickness definition is the radial thickness, which is defined as the distance between each pair of corresponding points on the two surfaces with the same polar coordinate. The thickness values calculated by the radial thickness definition are unique and does not depend on the starting surface. In this paper, we describe a class for calculating the radial thickness of one volumetric layer represented as coupled and nested triangle meshes. 

The class, vtkRadialThicknessCalculate, is implemented using the Visualization Toolkit (VTK). In this document, we describe the radial thickness calculation algorithm and provide the user with the source code and the input data to reproduce the results. The radial thickness calculation described in this paper has a variety of applications including the thickness calculation for the skull vault, which is the original motivation for this work.

Radial Thickness Calculation and Visualization for Volumetric Layers

At the Johns Hopkins University’s Engineering Research Center for Computer-Integrated Surgical Systems and Technology (ERC-CISST) laboratory, we have designed and developed a platformindependent C++ software package, called the nArray library, that provides a unified framework for efficiently working with multidimensional data sets. In this paper, we present and discuss the core elements of the library, including its intuitive and uniform API, efficient arithmetic engine algorithm, and efficient sub-volume algorithm. We then compare the performance of the nArray library with that of an existing multidimensional array toolkit, ITK. We conclude that the nArray library is more efficient than ITK in many situations, especially in operations on sub-arrays, and that the two packages have comparable performance in many other scenarios. The underlying algorithms, if incorporated in ITK, can help improve its performance.