MINC2.0 IO support REVISED!
This revision has direction cosines and various other issues addressed.

MINC2.0 IO Support for ITK

This document describes the implementation of an algorithm that computes a generalization of the distance transform with the squared euclidean metric.

The generalization allows for interesting image operators, e.g. a morphologic dilation with euclidean ball structure elements that can vary in size across the image. Voronoi maps and the standard distance transform can be computed as well.

The algorithm is provided as an image processing filter for ITK. Several example programs demonstrate its applications.

A Generalized Squared Euclidean Distance Transform with Voronoi Maps

The current ITK release 2.6 does not contain a way to combine transforms in a structural way. This document describes a contribution to the Insight Toolkit ITK \url{www.itk.org}, which implements what we call an \doxygen{CombinationTransform}. Two ways to combine transforms are implemented, by addition and by composition. Depending on this selection, different implementations of the \code{TransformPoint()} are provided. Also the expressions for the Jacobian and the inverse transform depend on the way transforms are combined. By using function pointers expensive \code{if}-statements are avoided. This paper is accompanied with the
source code.

Combining Transforms in ITK

This report discusses various definitions and implementations of the watershed transform as well as providing an introduction to some well known techniques for applying the watershed transform to practical problems. The discussion will be focused on new and existing ITK classes.

The watershed transform in ITK - discussion and new developments

Classes to provide IO capabilities for the ITK Neural Networks library.

ITK Neural Networks IO Classes

This work describes the implementation of computational geometry algorithms developed within the Insight Toolkit (ITK): Distance Transform (DT), Voronoi diagrams, k Nearest Neighbor (kNN) transform, and finally a K Nearest Neighbor classifier for multichannel data, that is used for supervised segmentation. We have tested this algorithm for 2D and 3D medical datasets, and the results are excellent in terms of accuracy and performance. One of the strongest points of the algorithms described here is that they can be used for many other applications, because they are based on the ordered propagation paradigm. This idea consists in actually not raster scan the image but rather in start from the image objects and propagate them until the image is totally filled. This has been demonstrated to be a good approach in many algorithms as for example, computation of Distance Transforms, Voronoi Diagrams, Fast Marching, skeletons computation, etc. We show here that these algorithms have low computational complexity and it provides excellent results for clinical applications as the segmentation of brain MRI.

Computational Geometry Computation and KNN Segmentation in ITK

BioImage Suite is an NIH-supported medical image analysis software suite developed at Yale. It
leverages both the Visualization Toolkit (VTK) and the Insight Toolkit (ITK) and it includes many additional
algorithms for image analysis especially in the areas of segmentation, registration, diffusion
weighted image processing and fMRI analysis. BioImage Suite has a user-friendly user interface developed
in the Tcl scripting language. A final beta version is freely available for download.

BioImage Suite: An integrated medical image analysis suite: An update

This paper describes the Datatree module of BioImage Suite, that allows for rapid and flexible reslicing
of images based on a user-defined tree structure that organizes image and transformation data as well as
electrode localizations, image landmarks, and surface objects. This Datatree tool provides abstracted file
loading, allowing for interface with databases, as well as multisubject capabilities, other plugins designed
for specific image modalities, and an incr Tcl based API, allowing users to extend its functionality with
their own plugins.

The BioImage Suite Datatree Tool: Enabling Flexible Realtime Surgical Visualizations

The software requirements for computer-aided navigation tools in image-guided therapy are becoming increasingly complex as a result of new possibilities in imaging and tracking hardware, novel application areas and regulatory restrictions.
A new software framework has been developed to meet the needs of emerging image-guided procedures and therapies that require multi-modal imaging and tracking. This framework accommodates dynamic data-structures, dynamic input and output interfaces for interventional devices, and dynamic visualization of data. Arbitrary, yet meaningful, connections can be established between these entities in order to implement customized applications that target specific clinical procedures. A series of demonstration applications have been developed in order to emphasize different aspects of the framework, and are presented here.

The SIGN: A dynamic and extensible software framework for Image-Guided Therapy

ImageLib is a free object-oriented development environment destined to biomedical image processing. The software package contains a programming library (C++ language) and an MDI user interface (kernel). The major interest is to allow the creation of fully modular applications. Both user processing functions and image read/write facilities are separately compiled as DLLs, and the resulting plugin objects are dynamically imported into the kernel. The library provides all the required wrapping material to incorporate all find of image processing functions into user-written components. A rapid prototyping application is provided to communicate with the kernel communication interface. No graphics programming skills is required to manage advanced user interactions, image display (e.g. OpenGL), and generic image processing functions based on C++ templates. The component-oriented software architecture makes it possible to share image processing and handling resources for light Windows processing applications.