Mean shift clustering is an excellent technique for clustering points when the number of clusters is not known. We present a implementation (vtkMeanShiftClustering) of the simplest version of the algorithm written in a VTK context.

The code is currently hosted at http://github.com/daviddoria/vtkMeanShiftClustering .

A Mean Shift Clustering Implementation for VTK

The Allen Brain Atlas (ABA) project aims to create a
cellular-resolution, genome-wide map of gene expression in the adult
mouse brain. The resulting in situ hybridization (ISH) image data
will be available free-of-charge to the public. Additionally, we are
developing an informatics pipeline to support searching of the data by
anatomic region and expression level and/or pattern. This paper
describes a robust, high-throughput registration scheme to
automatically annotate hierarchical brain structures in the ISH
imagery.

Automated high-throughput registration for localizing 3D mouse brain gene expression using ITK

Active contour segmentation and its robust implementation using level sets
have been studied thoroughly in the medical image analysis literature. Despite
the availability of these powerful methods, clinical research still largely
relies on manual slice-by-slice outlining for anatomical structure
segmentation. To bridge the gap between methodological advances and clinical
routine, we developed ITK-SNAP: an open source application intended to make
level set segmentation easily accessible to a wide range of users with various
levels of mathematical expertise. We briefly describe this new tool and report
the results of a validation study in which ITK-SNAP was compared to manual
segmentation of the caudate in the context of an ongoing child neuroimaging
autism study.

User-Guided Level Set Segmentation of Anatomical Structures with ITK-SNAP

A modification is made to Otsu thresholding method. It provides better results for ICV (Intracranial volume) segmentation on one kind of T2-weighted MRI data.

A Modification to Otsu Thresholding Method for ICV Segmentation

Methods for segmentation of skull infiltrated tumors in Computed
Tomography (CT) images using Insight Segmentation and Registration
Toolkit ITK (www.itk.org) are presented. Pipelines of filters and
algorithms from ITK are validated on the basis of different criteria: sensitivity,
specificity, dice similarity coefficient, Chi-squared, and Hausdorff
distance measure. The method to rate segmentation results in relation
to validation metrics is presented together with analysis of importance of
different goodness measures. Results for one simulated dataset and three
patient are presented.

Segmentation of Skull-infiltrated Tumors Using ITK: Methods and Validation

For over two decades, the National Library of Medicine (NLM)
has provided support for the collection of biomedical image data for use
throughout the biomedical image, visualization and analysis community.
Data collected during the Visible Human Project has been utilized to
advance development of medical image research, education, and other
ventures. One goal of our research has been to further diversify such
image data and make it openly available to the biomedical imaging community.
The approach is to provide open access to a diverse collection
of biomedical image data that can be used for the development and validation
of new image processing and analysis techniques. With support
from NLM, over 100 datasets were incorporated into the NLM-Mayo
data collection. There is variation in species, anatomy, pathology, scale,
and modality. In addition to providing linical qualitymedical image
data, the collection also includes newly acquired datasets of several animals,
including a whole mouse with both T and R data volumes.
This unique collection of data was categorized and organized into an intuitive
web-based browser which allows a user to rapidly access descriptive
information as well as the actual data volumes. The data collection
will be made available by the NLM for distribution, vis-a-vis its Visible
Human Project (VHP). Because the landscape of biomedical imaging
continues to change with new, advanced image acquisition systems and
techniques, continuously updating the VHP data collection seems prudent.
Additional new and varied image data will be incorporated into our
collection and disseminated to researchers in the medical image analysis
community.

The NLM-Mayo Image Collection: Common Access to Uncommon Data

Inactivation of the retinoblastoma gene in mouse embryos results
in morphological changes in the placenta, which has been shown to
affect fetal survivability. The construction of a 3D virtual
placenta aids in accurately quantifying structural changes using
image analysis. The placenta dataset consisted of 786 images
totaling 550 GB in size, which were registered into a volumetric
dataset using ITK's registration framework. The registration
process faces many challenges arising from the large image sizes,
damages during sectioning, staining gradients both within and
across sections, and background noise leading to local solutions.
In this work, we implement a rigorous ITK-based preprocessing
pipeline for removing noise and employ a novel 2-level
optimization strategy for enhanced registration in ITK. We provide
3D visualizations and numerical results to demonstrate our
improvements.

ITK-based Registration of Large Images from Light Microscopy: A Biomedical Application

Visualizing metabolic phenotypes, tracking phenotype dynamics, and screening molecular interventions all require comprehensive,
quantitative measures of micromolecular patterns across cell classes. In this project we develop an easy-to-use interface that permits the same sequence of operations as described in Marc and Jones [1] and is based on Cell Kit developed by Marc's lab. Work products for this project include: user application software (Matlab), user manual and if possible, a web portal interface to allow internet access and application of the system. The MORPHIAS system will be implemented by means of a Matlab function which creates a GUI which allows the user to import molecular signature images (in TIFF format), and then to perform classification using a clustering algorithm, and to then perform data analysis on the result.

MORPHIAS: Molecular Phenotyping Image Analysis System

Open source technologies are increasing in popularity for software development. Many open source projects rely on skilled development teams whose members are distributed throughout the world. Often, agile development methods are employed by these teams, as the focus is on concurrent development and fast production over requirements management and quality assurance. The image-guided surgery toolkit (IGSTK) is an open source development project that relies on the collaboration of a skilled and distributed development team, yet addresses a domain that demands managing requirements as well as implementing a high degree of robustness and addressing safety concerns. Due to this unique cross-section of open source technology and the surgical domain, the IGSTK team has developed a set of best practices and requirements techniques to augment commonly applied agile methods. This paper presents the lessons we have learned as we have engaged in the software development process.

IGSTK: Development Process and Project Management Best Practices for an Open Source Software Toolkit for Image-Guided Surgery Applications

The aim of this paper is to present the integration of new filters computing fuzzy mathematical morphology and spatial relationships into ITK and to share our experience with the Open source community. 
Our implementation architecture follows the essential system concepts of ITK. An illustrative application is provided to help ITK users and developers to evaluate the capabilities of these filters.