This paper describes a new tutorial book titled "An Introduction to Programming for Medical Image Analysis with the Visualization Toolkit." This book derived from a set of class handouts used in a biomedical engineering graduate seminar at Yale University. The goal for the seminar was to
introduce the students to the Visualization Toolkit (VTK) and, to a lesser extent, the Insight Toolkit (ITK). A draft version of the complete book (including all the sample code) is available online at www.bioimagesuite.org/vtkbook.

Medical Image Analysis with VTK: A Tutorial

Phase Correlation Method (PCM or SPOMF - Symmetric Phase-Only Matched Filter) is a well known image registration method, that exploits Fourier Shift Theorem property of Fourier Transform. Even though it is limited to estimate only shifts between two images, it is very useful as it is robust to frequency-dependent noise and initial image overlap area. Furthermore, it evaluates very fast by way of two forward FFTs, one complex image division and one inverse FFT.

Phase Correlation Method for ITK

In an earlier submission, we considered 2-D and 3-D digital binary images topologically characterized by their well-composedness. Well-composed images exhibit important topological and geometrical properties not shared by their ill-composed counterparts. These properties have important implications for various algorithms used by the ITK community such as thinning algorithms and Marching Cubes. 

A natural follow-up inquiry to our original submission concerns the possible extension of the binary algorithm to accommodate images with multiple labels. In this paper, we describe such a generalization of our previous submission which also subsumes the binary approach. For completeness and clarity of exposition, we develop the idea of well-composedness within the binary image context and later generalize the discussion to include those images with multiple labels.

Well-Composedness and the Topological Repairing of 2-D and 3-D Digital Images

Certain classes of images find disparate use amongst members of the ITK community for such purposes as visualization, simulation, testing, etc. Currently there exists two derived classes from the ImageSource class used for generating specific images for various applications, viz. RandomImageSource and GaussianImageSource. We propose to add to this set with the class GridImageSource which, obviously enough, produces a grid image. Such images are useful for visualizing deformation when used in conjunction with the WarpImageFilter, simulating magnetic resonance tagging images, or creating optical illusions with which to amaze your friends.

Gridding Graphic Graticules

Logic operations such as $I > J$, where I and J are images are useful
when generating masks. This submission includes $==$, $>$, $>=$, $<$
and $<=$ filters based on the existing logic filters. This is a very
minor submission - there may already be easy ways of performing the
logic operations defined by these filters, but I couldn't find them.

Some extra image logical operations

Homogeneous transformations are widely used in computer vision and graphics. They commonly arise
when considering the transformation of an image of a planar object under arbitrary camera motion, or the
transformation of two images of the same scene due to camera motion holding the optical center fixed.
In this paper we describe the addition of a class of homogeneous transforms for the Insight Toolkit.

A Homogeneous Transform Class for the ITK

Kernel-based transforms such as the thin plate spline are frequently used to model deformations in medical
imaging. The existing implementation in ITK is capable of being used to warp images, but does not
work in the registration framework. The existing implementation is inefficient, requiring recomputation
of all cached values at every parameter change, and the Jacobian calculation is not implemented. By
reversing the roles of the fixed and moving parameters, the transform can be adapted for registration use.
We present modified classes which are more efficient, and calculate the Jacobian correctly.

Improvements to the itk::KernelTransform and Subclasses

Often times developers face the need to connect ITK and VTK pipelines to handle
image data. For this purpose, image data importer and exporter classes 
have been implemented both in ITK and VTK. However, as evident from frequent questions in 
the ITK and VTK users and developers mailing list, usage of these classes is not 
straight forward. Furthermore, the difficulty gets more challenging with the need to 
handle different pixel types. For these reasons, an effort was made to write Image IO classes that 
encapsulate all the intricacies and provide users with easy to use API. This article 
describes these Image IO classes and present an example to demonstrate how to use
these classes.

Seamless VTK-ITK pipeline connection for image data handling

This workshop features peer-reviewed submissions that describe the available data and software of MICCAI.

Open Source and Open Data for MICCAI - Announcement and Program

The subject of the paper is to introduce a new class of 4D filters to itk.While it is very easy to load a 3D volume stored as a series of DICOM images with ITK, some convenience functions that are already available for 3D volumes are not yet available for the 4D case. Especially for MR data (and to a certain limit also for CT data) it is very important to look at the full 4D series, since the radiologist usually does not make a diagnosis based on a single volume but on the full time series of volumes which shows the temporal flow of the contrast agent. As an example, for breast imaging the radiologist typically examines parameter maps like MIPt (maximum intensity over time), TTP (time to peak) or WI (Wash-In). These parameter maps are the 3D result of post-processing the entire 4D time series. The goal of proposing the denoted 4D filters is to provide ITK with functionality that enables a postprocessing job to handle the entire 4D series as one entity and not as a loose collection of 3D volumes.