Introducing MIPAV and Introduction: Difference between pages

From MIPAV
(Difference between pages)
Jump to navigation Jump to search
m (1 revision imported)
 
MIPAV>Olga Vovk
mNo edit summary
 
Line 1: Line 1:
<div id="IntroducingMipav"></div>
'''In this section . . .<br />'''
== Introducing MIPAV ==
[[File:MipavSplash.gif|158px|thumb|right|MIPAV]]


[http://en.wikipedia.org/wiki/Medical_imaging Imaging] is essential to medical research and clinical practice. Biologists study cells and generate three-dimensional (3D) confocal microscopy datasets; virologists generate 3D reconstructions of viruses from micrographs. Radiologists identify and quantify tumors from [http://en.wikipedia.org/wiki/Magnetic_resonance_imaging Magnetic Resonance Imaging (MRI)] and [http://en.wikipedia.org/wiki/X-ray_computed_tomography Computed Tomography (CT)] scans.
== Introduction ==
Designed specifically for medical researchers, MIPAV concentrates on providing those researchers with the tools needed to do their work. It reads image files of many different formats and allows images to be displayed and measured using the most meaningful method to achieve research goals. MIPAV's flexibility becomes apparent when its capabilities are expanded and fine tuned through the development of plug-in programs that tailor solutions to meet specific requirements.<br />


Neuroscientists detect regional metabolic brain activity from [http://en.wikipedia.org/wiki/Positron_emission_tomography Positron Emission Tomography (PET)] and [http://en.wikipedia.org/wiki/Functional_magnetic_resonance_imaging functional MRI (fMRI)] scans. Analysis of these diverse image datasets require sophisticated quantification and visualization tools. Until recently, 3D visualization and quantitative analysis of an image dataset could only be performed on expensive [http://en.wikipedia.org/wiki/Unix UNIX workstations] with customized software.
Using MIPAV to display, label, and measure brain components in Talairach space demonstrates both: MIPAV's native ability to display and measure brain images in Talairach space and the tailoring provided through the Talairach Transformation wizard and the FANTASM (Fuzzy and Noise Tolerant Adaptive Segmentation Method) plug-in programs, developed by the Johns Hopkins University.


Because of technological advancements, medical image visualization and analysis can now be performed on an inexpensive desktop computer that is equipped with the appropriate software applications.
== Background ==
In 1988 Jean Talairach and Pierre Tournoux developed a three-dimensional proportional grid system that can be used to identify and measure brains from any number of patients despite the variability of brain sizes and proportions. The premise of the system is that brain components that cannot be seen or identified can be defined in relation to other anatomic cerebral structures. In the Talairach system, the anterior commissure (AC) and posterior commissure (PC) are the structures from which the system of reference is developed.<br />


This [[Introducing MIPAV | Getting Started guide]] explains how to use one of these software applications: [http://mipav.cit.nih.gov/index.php|Medical Image Processing, Analysis, and Visualization] (MIPAV). Researchers use MIPAV to extract quantitative information from image datasets of various medical image modalities. The MIPAV application can run on virtually any platform, including [http://windows.microsoft.com/en-US/windows/home Microsoft Windows], [http://en.wikipedia.org/wiki/Solaris_%28operating_system%29 Solaris], and the [http://en.wikipedia.org/wiki/Mac_OS Macintosh Operating System (Mac OS)]. <br />
The Talairach system establishes the maximal dimensions of the brain in three planes of space: <span style="font-weight: normal; text-decoration: none; text-transform: none; vertical-align: baseline">''<font color="#000000">x, y</font>''</span> and <span style="font-weight: normal; text-decoration: none; text-transform: none; vertical-align: baseline">''<font color="#000000">z</font>''</span><nowiki>: </nowiki>


MIPAV installation program can be downloaded from MIPAV web site - <span style="font-style: normal; text-transform: none; vertical-align: baseline"><u>'''<font color="#000000">http://mipav.cit.nih.gov</font>'''</u></span>
<div style="font-style: normal; font-weight: normal; margin-bottom: 0pt; margin-left: 24pt; margin-right: 0pt; margin-top: 5pt; text-align: left; text-decoration: none; text-indent: -24pt; text-transform: none; vertical-align: baseline"><font color="#000000">  <span style="font-weight: normal; text-decoration: none; text-transform: none; vertical-align: baseline">''<font color="#000000">AC-PC line (X axis)</font>''</span>-A horizontal line running through the anterior and posterior commissures. <br /></font></div><div style="font-style: normal; font-weight: normal; margin-bottom: 0pt; margin-left: 24pt; margin-right: 0pt; margin-top: 5pt; text-align: left; text-decoration: none; text-indent: -24pt; text-transform: none; vertical-align: baseline"><font color="#000000">  <span style="font-weight: normal; text-decoration: none; text-transform: none; vertical-align: baseline">''<font color="#000000">VCA line (verticofrontal line, or Y axis)</font>''</span>-A vertical line passing through the anterior commissure<br /></font></div><div style="font-style: normal; font-weight: normal; margin-bottom: 0pt; margin-left: 24pt; margin-right: 0pt; margin-top: 5pt; text-align: left; text-decoration: none; text-indent: -24pt; text-transform: none; vertical-align: baseline"><font color="#000000">  <span style="font-weight: normal; text-decoration: none; text-transform: none; vertical-align: baseline">''<font color="#000000">Midline (Z axis)</font>''</span>-A line forming the interhemispheric sagittal plane<br /></font></div>


<div id="MipavPlatformIndependence"></div>
Often referred to as the "origin," the anterior commissure is commonly used to describe structures. For example, a structure is described as "AC 13 mm" for the frontal lobe or "AC - 35 mm" for the occipital pole. These descriptions assume that the anterior commissure is in the positive direction. However, the Talairach system does not use positive and negative directions. Instead, it labels quadrants according to number and letters (Figure 1). The AC-PC line defines the horizontal plane, the VCA line defines the vertical plane, and the midline defines the depth plane. Because the anterior commissure and posterior commissure do not occur in the same axial slice, reslicing is necessary to put the brain into Talairach space.


== Platform independence ==
Much research at NIH requires the segmentation, quantification, and visualization of 2D, 3D, and 4D image datasets. Researchers analyze images of varied imaging modalities, such as microscopy, microarray data, X-ray, CT, MRI, fMRI, and PET. Factors such as personal preference, data requirements, software limitations, and precedent have led to a heterogeneous distribution of computer platforms, among which are personal computers executing Windows or Linux, Macintoshes, and workstations by SGI, Sun Microsystems, or Hewlett-Packard. To analyze an image dataset, researchers may use several software applications. If each software application is platform specific, researchers may need access to several platforms to analyze a single image dataset. This often reduces efficiency while simultaneously increasing lab costs. MIPAV has been designed to help researchers increase efficiency and reduce costs by providing them with a flexible tool that can operate on virtually any platform. Researchers can use MIPAV by itself or in concert with other image processing and visualization tools.


'''This technical guide explains how to install and use two MIPAV plug-in programs-the Talairach Transformation wizard and FANTASM to:'''


The MIPAV application is platform independent because it is written in [http://www.java.com/en/ Java], which is an object-oriented, interpreted, programming language that was developed by [http://en.wikipedia.org/wiki/Sun_Microsystems Sun Microsystems]. Java source code is compiled into the bytecode, which is machine-level code that is compiled specifically for the [http://en.wikipedia.org/wiki/Java_virtual_machine Java Virtual Machine (JVM)]. There are versions of the Java VM for different platforms. The same program (bytecode) can run on any of those versions. If researchers run a Java program on a Windows platform, the bytecode is interpreted by the Java VM that has been specifically designed for the particular Windows platform. If the same program is run on a Solaris platform; the bytecode is then interpreted by the Java VM that was specifically designed for the Solaris platform.
<div style="font-style: normal; font-weight: normal; margin-bottom: 0pt; margin-left: 24pt; margin-right: 0pt; margin-top: 5pt; text-align: left; text-decoration: none; text-indent: -24pt; text-transform: none; vertical-align: baseline"><font color="#000000">  Create the <span style="font-weight: normal; text-decoration: none; text-transform: none; vertical-align: baseline">''<font color="#000000">x, y,</font>''</span> and <span style="font-weight: normal; text-decoration: none; text-transform: none; vertical-align: baseline">''<font color="#000000">z</font>''</span> planes of space in an image of a brain<br /></font></div><div style="font-style: normal; font-weight: normal; margin-bottom: 0pt; margin-left: 24pt; margin-right: 0pt; margin-top: 5pt; text-align: left; text-decoration: none; text-indent: -24pt; text-transform: none; vertical-align: baseline"><font color="#000000">  Transfer Talairach labels to an image of a brain<br /></font></div><div style="font-style: normal; font-weight: normal; margin-bottom: 0pt; margin-left: 24pt; margin-right: 0pt; margin-top: 5pt; text-align: left; text-decoration: none; text-indent: -24pt; text-transform: none; vertical-align: baseline"><font color="#000000">  Measure brain components in Talairach space<br /></font></div><div style="font-style: normal; font-weight: normal; margin-bottom: 0pt; margin-left: 0pt; margin-right: 0pt; margin-top: 0pt; text-align: left; text-decoration: none; text-indent: 0pt; text-transform: none; vertical-align: baseline"><font color="#000000"> <br /></font></div><div style="font-style: normal; font-weight: normal; margin-bottom: 0pt; margin-left: 0pt; margin-right: 0pt; margin-top: 0pt; text-align: left; text-decoration: none; text-indent: 0pt; text-transform: none; vertical-align: baseline"><font color="#000000">


'''Note:''' The correct version of the Java VM can be downloaded from the MIPAV web site <span style="font-style: normal; text-transform: none; vertical-align: baseline"><u>'''<font color="#000000">http://mipav.cit.nih.gov</font>'''</u></span> along with the MIPAV installation program.
{| border="1" cellpadding="5"
|+ '''Figure 1. Talairach space: (A) Quadrants labeled by number and letters and (B) horizontal, vertical, and depth planes'''<br />
|-
|
[[Image:exampleTalairachCubeBrain.gif]]
|}
=== Talairach Transformation wizard ===
The Talairach Transformation wizard is a plug-in program for MIPAV that performs a semimanual transformation of image datasets of the brain to Talairach (stereotaxic) coordinates, providing atlas-based labeling. The Talairach coordinates allow researchers to easily identify subregions of the brain and measure their volume. It includes labels for 148 different substructures of the brain at various scales, obtained from the <span style="font-style: normal; font-weight: normal; text-transform: none; vertical-align: baseline"><u><font color="#000000">[ http://ric.uthscsa.edu/projects/talairachdaemon.html ]</font></u></span><span style="font-style: normal; font-weight: normal; text-decoration: none; text-transform: none; vertical-align: baseline"><font color="#000000">Talairach Daemon database</font></span>, along with a set of volumetric images of the labels.<br /></font></div>


<div id="MipavCapabilities"></div>
=== FANTASM ===
The FANTASM plug-in program<span style="font-style: normal; font-weight: normal; text-decoration: none; text-transform: none; vertical-align: baseline"><font color="#000000"> is a different version of the Fuzzy C-mean algorithm for segmenting 2D and 3D images. It incorporates a spatial constraint that requires neighboring pixels to be similar and reduces the noise effect obtained with the Fuzzy C-mean algorithm. It can deal with outliers. Plans for a future version of FANTASM incorporates inhomogeneity correction. </font></span><br />


== Understanding MIPAV capabilities ==
== References ==
ICBM atlas created by the International Consortium on Brain Mapping (ICBM), automatic <br />(<span style="font-style: normal; font-weight: normal; text-transform: none; vertical-align: baseline"><u><font color="#000000">http://www.loni.ucla.edu/ICBM/ICBM_BrainTemplate.html</font></u></span>).<br />
<div style="font-style: normal; font-weight: normal; margin-bottom: 4pt; margin-left: 0pt; margin-right: 0pt; margin-top: 11pt; text-align: left; text-decoration: none; text-indent: 0pt; text-transform: none; vertical-align: baseline"><font color="#000000"> Jean Talairach and Pierre Tournoux, <span style="font-weight: normal; text-decoration: none; text-transform: none; vertical-align: baseline">''<font color="#000000">Co-Planar Stereotaxic Atlas of the Human Brain</font>''</span>, Thieme Medical Publishers, New York, 1988. <br /></font></div><div style="font-style: normal; font-weight: normal; margin-bottom: 4pt; margin-left: 0pt; margin-right: 0pt; margin-top: 11pt; text-align: left; text-decoration: none; text-indent: 0pt; text-transform: none; vertical-align: baseline"><font color="#000000"> Neva Chernizasky, <span style="font-weight: normal; text-decoration: none; text-transform: none; vertical-align: baseline">''<font color="#000000">Medical Imaging: Orientation</font>''</span>, Paper prepared for Matthew McAuliiffe, Ph.D. Center for Information Technology, National Institutes of Health, August 31, 2001.<br /></font></div><div style="font-style: normal; font-weight: normal; margin-bottom: 4pt; margin-left: 0pt; margin-right: 0pt; margin-top: 11pt; text-align: left; text-decoration: none; text-indent: 0pt; text-transform: none; vertical-align: baseline"><font color="#000000"> Dzung L. Pham, "Spatial Models for Fuzzy Clustering," <span style="font-weight: normal; text-decoration: none; text-transform: none; vertical-align: baseline">''<font color="#000000">Computer Vision and Image Understanding</font>''</span>, vol. 84, pp. 285-297, 2001.<br /></font></div><div style="font-style: normal; font-weight: normal; margin-bottom: 4pt; margin-left: 0pt; margin-right: 0pt; margin-top: 11pt; text-align: left; text-decoration: none; text-indent: 0pt; text-transform: none; vertical-align: baseline"><font color="#000000"> Pierre-Louis Bazin, Dzung L. Pham, William Gandler, and Matthew McAuliffe. "Free Software Tools for Atlas-based Volumetric Neuroimage Analysis," to be published in the <span style="font-weight: normal; text-decoration: none; text-transform: none; vertical-align: baseline">''<font color="#000000">Proceedings of the SPIE Medical Image 2005 Conference</font>''</span>, The International Society for Optical Engineering (SPIE), Bellingham, Washington, 2005.<br /></font></div>


<div id="SupportedImagetypes"></div>
[[Installing]]
=== Supported image types ===
 
Before image dataset analysis and quantification can be performed, an application must be able to read and write image datasets in industry-standard formats. Conformance to accepted standards, such as DICOM, ensures compatibility with present and future applications and medical equipment. This protects researchers' investment in hardware and provides flexibility in reaching their goals.<br />
 
MIPAV supports over 20 different industry-standard image formats including: DICOM, TIFF, Analyze, and RAW (a complete list appears in [[Supported Formats#SupportedFormats|Supported formats]]). MIPAV reads and writes images in both big and little endian formats.
 
See also: [[Supported Formats]].
 
=== Visualization of images ===
 
The visualization of datasets with two or more dimensions is an important aspect of image dataset analysis and research. The ability to visualize the orientation, locality, or progression (time) of structures in clinical and nonclinical datasets can be vital to researchers. Confocal microscopy, CT, and MRI are examples of imaging modalities that are comprised of multiple adjacent cross-sectional image datasets that can be combined to form a 3D volume dataset. MIPAV allows researchers to visualize datasets using a variety of presentation formats, including lightbox, triplanar, cine, and animate. Once researchers display the image dataset, they can adjust the lookup table (LUT), apply prepackaged pseudo-color LUTs to highlight structures of interest, control the magnification level, adjust the transfer function, and more. <br />
 
=== Volume of interest (VOI) segmentation and analysis ===
 
Another significant research activity is the quantification of data from image datasets. Although the visualization of image data is important, the actual quantification of the data is typically required to evaluate the researchers' hypothesis. Researchers must be able to identify regions-of-interest (ROIs) and  [[Delineating volumes of interest (VOIs)| volumes of interest (VOIs)]].
 
'''Note:''' An ROI is used in the context of 2D image datasets. VOI usually describes the analysis of volume data for datasets with more than two dimensions. This document uses the term VOI to represent both ROI and VOI.
 
'''[[Delineating volumes of interest (VOIs)| Image segmentation]]''' is the process of identifying connected regions of images as members of a common group. In the medical field, physicians must routinely identify (i.e., segment) structures in medical image datasets to facilitate the treatment of patients. For example, many researchers who study the brain are interested in the segmentation of gray matter, white matter, and cerebrospinal fluid in MR images. The quantification of important attributes, such as volume, of various tissue types enables researchers to better understand, diagnose, monitor, and treat neurobehavioral disorders.
 
There is a multitude of image dataset segmentation methods; the choice of segmentation algorithm depends on the image data type and task. Automatic segmentation methods are desirable because they require little user interaction, which is subject to operator error and subjectivity. However, in practice automatic methods sometimes fail and require manual VOI correction (adjustment of the boundary that identifies the region). In MIPAV, researchers have the choice to segment VOIs automatically, semi-automatically, and manually. [[Delineating volumes of interest (VOIs)| Contours]] can be manually edited, grouped, and copied to other slices in the dataset. MIPAV also offers a variety of [[Segmenting Images Using Contours and Masks| mask-generation methods]]. Researchers can manually [[Segmenting Images Using Contours and Masks: Advanced paint and Power Paint tools|paint a mask]] or use one or a combination of [[Using MIPAV Algorithms#MipavAlgorithms|segmentation algorithms]].
 
MIPAV also allows researchers to perform [[Calculating VOI statistics | statistical calculations on masked and contoured VOIs]]. Statistical results can be saved to an ASCII text file and imported to another program, as needed.
 
<div id="JavaPlugIns"></div>
=== Extensibility with Java plug-ins ===
 
A typical analysis and visualization application can be designed to meet a broad range of researcher requirements. Many components of image dataset processing, analysis, and visualization techniques are general and can be applied to many types of data. However, many datasets also require unique functionality to meet special requirements. MIPAV allows researchers, who have the programming resources, to add a customized Java plug-in to the application. To program a plug-in, researchers must have a strong understanding of the underlying structure of the application's software design.
 
The [[Developing Plugin Programs]] chapter offers the information on how to add and remove plug-ins from the MIPAV application. It also indicates the statements that must be included in the source code to allow the plug-in to interface properly with MIPAV. However, in-depth information is not included in this guide. If you need more information, check the MIPAV web site <span style="font-style: normal; text-transform: none; vertical-align: baseline"><u>'''<font color="#000000">http://mipav.cit.nih.gov</font>'''</u></span> for the e-mail address for technical support.
 
See also: [[Developing new tools using the API]].
 
<div id="MipavFeatures"></div>
 
=== Sampling of MIPAV's features ===
MIPAV provides ready-made, general-purpose tools that meet the majority of requirements of many researchers. Researchers can use MIPAV to perform a variety of tasks. The following list shows a sampling of the tasks that researchers can performed with the program. For more information, refer to the MIPAV web site: [http://mipav.cit.nih.gov/documentation.php http://mipav.cit.nih.gov/documentation.php].
 
*[[Displaying images | Visualize files]] and [[Creating new images |create new image dataset files]]
*[[Displaying images | View and modify the attributes of image datasets]], including [[Working with DICOM Images | DICOM]] and [[Delineating volumes of interest (VOIs)| volumes of interest (VOI) information]]
*Adjust the [[Displaying images | display of an image dataset file]] and [[Displaying images#AdjustingMagnification|adjust magnification]] settings
*[[Working with DICOM Images | View DICOM overlays]] and protect patient privacy using the [[Protecting patient privacy using Anonymize| anonymize feature]]
*[[Sending and retrieving DICOM images| Send and receive image dataset files to and from databases via DICOM-compliant servers]] 
*[[Delineating volumes of interest (VOIs)|Contour VOIs]] using manual, semi-automatic, and automatic methods
*[[Reviewing VOI statistics|Generate graphs and calculate statistics on VOIs]]
*[[Changing Image Contrast#PredefinedLut| Generate and adjust histograms and Look up tables (LUT)]] using customized or preset options
*Run sophisticated, predefined [http://mipav.cit.nih.gov/documentation/userguide/Vol2Algorithms.pdf algorithms] and [[Customizing MIPAV | generate logs]]
*[[Changing Image Contrast#ComparingImages | Blend two image datasets and adjust opacity levels of the alpha channels so overlapping areas can be studied]]
*[[Developing Plugin Programs | Create new plug-ins]] to further customize the analysis of data
*[[Saving and printing images | Save transformation]], [[Changing Image Contrast | LUT]], and [[Delineating volumes of interest (VOIs)|VOI data]], and apply them to other image datasets
*[[Saving and printing images | Print image dataset files]], [[Reviewing VOI statistics| intensity profiles]], statistical data, algorithmic logs, and [[Customizing MIPAV | debugging log data]]
 
== See also: ==
*[http://mipav.cit.nih.gov MIPAV web site]
*[http://mipav.cit.nih.gov/wiki/index.php/Main_Page MIPAV WIKI]
*[[Getting Started Quickly with MIPAV]]
*[[Installing mipav|Installing MIPAV]]
*[[MIPAV system requirements]]
*[[Installing mipav|Installing MIPAV]]
*[[Installing mipav#MipavUpgrade|Upgrading MIPAV]]
*[[Installing mipav#MipavUninstall|Uninstalling MIPAV]]
*[[Quitting MIPAV]]
*[[MIPAV mailing list]]
*[[Technical Support]]
*[[Installing mipav#MipavNews|Viewing MIPAV News and Updates]]
*[[Developing new tools using the API]]
*[[Supported Formats]]
 
 
[[Category:Help]]
[[Category: Getting started]]

Revision as of 15:48, 15 June 2012

In this section . . .

Introduction

Designed specifically for medical researchers, MIPAV concentrates on providing those researchers with the tools needed to do their work. It reads image files of many different formats and allows images to be displayed and measured using the most meaningful method to achieve research goals. MIPAV's flexibility becomes apparent when its capabilities are expanded and fine tuned through the development of plug-in programs that tailor solutions to meet specific requirements.

Using MIPAV to display, label, and measure brain components in Talairach space demonstrates both: MIPAV's native ability to display and measure brain images in Talairach space and the tailoring provided through the Talairach Transformation wizard and the FANTASM (Fuzzy and Noise Tolerant Adaptive Segmentation Method) plug-in programs, developed by the Johns Hopkins University.

Background

In 1988 Jean Talairach and Pierre Tournoux developed a three-dimensional proportional grid system that can be used to identify and measure brains from any number of patients despite the variability of brain sizes and proportions. The premise of the system is that brain components that cannot be seen or identified can be defined in relation to other anatomic cerebral structures. In the Talairach system, the anterior commissure (AC) and posterior commissure (PC) are the structures from which the system of reference is developed.

The Talairach system establishes the maximal dimensions of the brain in three planes of space: x, y and z:

AC-PC line (X axis)-A horizontal line running through the anterior and posterior commissures.
VCA line (verticofrontal line, or Y axis)-A vertical line passing through the anterior commissure
Midline (Z axis)-A line forming the interhemispheric sagittal plane

Often referred to as the "origin," the anterior commissure is commonly used to describe structures. For example, a structure is described as "AC 13 mm" for the frontal lobe or "AC - 35 mm" for the occipital pole. These descriptions assume that the anterior commissure is in the positive direction. However, the Talairach system does not use positive and negative directions. Instead, it labels quadrants according to number and letters (Figure 1). The AC-PC line defines the horizontal plane, the VCA line defines the vertical plane, and the midline defines the depth plane. Because the anterior commissure and posterior commissure do not occur in the same axial slice, reslicing is necessary to put the brain into Talairach space.


This technical guide explains how to install and use two MIPAV plug-in programs-the Talairach Transformation wizard and FANTASM to:

Create the x, y, and z planes of space in an image of a brain
Transfer Talairach labels to an image of a brain
Measure brain components in Talairach space

Figure 1. Talairach space: (A) Quadrants labeled by number and letters and (B) horizontal, vertical, and depth planes

ExampleTalairachCubeBrain.gif

Talairach Transformation wizard

The Talairach Transformation wizard is a plug-in program for MIPAV that performs a semimanual transformation of image datasets of the brain to Talairach (stereotaxic) coordinates, providing atlas-based labeling. The Talairach coordinates allow researchers to easily identify subregions of the brain and measure their volume. It includes labels for 148 different substructures of the brain at various scales, obtained from the [ http://ric.uthscsa.edu/projects/talairachdaemon.html ]Talairach Daemon database, along with a set of volumetric images of the labels.

FANTASM

The FANTASM plug-in program is a different version of the Fuzzy C-mean algorithm for segmenting 2D and 3D images. It incorporates a spatial constraint that requires neighboring pixels to be similar and reduces the noise effect obtained with the Fuzzy C-mean algorithm. It can deal with outliers. Plans for a future version of FANTASM incorporates inhomogeneity correction.

References

ICBM atlas created by the International Consortium on Brain Mapping (ICBM), automatic
(http://www.loni.ucla.edu/ICBM/ICBM_BrainTemplate.html).

Jean Talairach and Pierre Tournoux, Co-Planar Stereotaxic Atlas of the Human Brain, Thieme Medical Publishers, New York, 1988.
Neva Chernizasky, Medical Imaging: Orientation, Paper prepared for Matthew McAuliiffe, Ph.D. Center for Information Technology, National Institutes of Health, August 31, 2001.
Dzung L. Pham, "Spatial Models for Fuzzy Clustering," Computer Vision and Image Understanding, vol. 84, pp. 285-297, 2001.
Pierre-Louis Bazin, Dzung L. Pham, William Gandler, and Matthew McAuliffe. "Free Software Tools for Atlas-based Volumetric Neuroimage Analysis," to be published in the Proceedings of the SPIE Medical Image 2005 Conference, The International Society for Optical Engineering (SPIE), Bellingham, Washington, 2005.

Installing