Debian Med Imaging development packages

The CImg Library is a C++ toolkit providing simple classes and functions to load, save, process and display images in your own C++ code. It consists only of a single header file CImg.h that must be included in your program source. It contains useful image processing algorithms for loading/saving, resizing/rotating, filtering, object drawing (text, lines, faces, ellipses, ...), etc.

Images are instantiated by a class able to represent images up to 4-dimension wide (from 1-D scalar signals to 3-D volumes of vector-valued pixels), with template pixel types. It depends on a minimal number of libraries : you can compile it with only standard C libraries. No need for exotic libraries and complex dependencies.

DICOM is the standard for image storage, annotation, and networking. It is used widely for medical imaging.

This package includes the header files and static library used for creating programs that use the CTN library.

G'MIC is an interpreter of image processing macros whose goal is to convert, manipulate and visualize generic 1D/2D/3D multi-spectral image files. This includes classical color images, but also more complex data as image sequences or 3D volumetric images.

This package contains the stand-alone gmic binary.

ActiViz provides a powerful interface to the Visualization Toolkit (VTK), an object-oriented software system encompassing thousands of algorithms that transform data into interactive 3D environments. ActiViz, which generates C# wrappers around VTK, enables developers to combine the power of VTK with the many .NET framework objects for web and database access. Available as source code or as a pre-built WinForms Control, ActiViz .NET includes examples, online documentation, and supports IntelliSense in the .NET Framework

BioSig is a library for accessing files in several biomedical data formats (including EDF, BDF, GDF, BrainVision, BCI2000, CFWB, HL7aECG, SCP_ECG (EN1064), MFER, ACQ, CNT(Neuroscan), DEMG, EGI, EEG1100, FAMOS, SigmaPLpro, TMS32). The complete list of supported file formats is available at http://pub.ist.ac.at/~schloegl/biosig/TESTED .

This package provides header files and static library.

Helps researchers and clinicians to easily and rapidly collaborate in order to prototype CAMI applications, that feature medical images, surgical navigation and biomechanical simulations.

This package contains development files needed to build CamiTK applications. This package also provides the CamiTK wizard to create new extensions.

This package provide files for translation from libcv-dev to subdivided packages.

This package contains the header files and static library needed to compile applications that use OpenCV (Open Computer Vision).

The Open Computer Vision Library is a collection of algorithms and sample code for various computer vision problems. The library is compatible with IPL (Intel's Image Processing Library) and, if available, can use IPP (Intel's Integrated Performance Primitives) for better performance.

OpenCV provides low level portable data types and operators, and a set of high level functionalities for video acquisition, image processing and analysis, structural analysis, motion analysis and object tracking, object recognition, camera calibration and 3D reconstruction.

GDF (General Dataformat for Biosignals) is intended to provide a generic storage for biosignals, such as EEG, ECG, MEG etc.

This package provides the header files and static library.

GIFTI is an XML-based file format for cortical surface data. This reference IO implementation is developed by the Neuroimaging Informatics Technology Initiative (NIfTI).

This package provides the header files and static library.

The Image-Guided Surgery Toolkit (IGstk: pronounced IGStick) is a high-level component-based framework providing common functionality for image-guided surgery applications.

This software framework consists of a set of high-level components integrated with other low-level open source software libraries and application programming interfaces (API) from hardware vendors.

The cornerstone of IGstk is robustness. IGstk provides the following high-level functionality: Ability to read and display medical images including CT and MRI in DICOM format. An interface to common tracking hardware (e.g. AURORA from Northern Digital Inc.). A graphical user interface and visualization capability including a four-quadrant view (axial, sagittal, coronal, and 3D) as well as a multi-slice axial view (from 1 by 1 to many by many such as 10 by 10).

Registration: point based registration and a means for selecting these points. Robust common internal software services for logging, exception-handling and problem resolution.

This package contains the development files needed to build your own IGSTK applications.

ITK is an open-source software toolkit for performing registration and segmentation. Segmentation is the process of identifying and classifying data found in a digitally sampled representation. Typically the sampled representation is an image acquired from such medical instrumentation as CT or MRI scanners. Registration is the task of aligning or developing correspondences between data. For example, in the medical environment, a CT scan may be aligned with a MRI scan in order to combine the information contained in both.

This package contains the development files needed to build your own ITK applications.

This project stands for Medical Image Conversion. Released under the (L)GPL, it comes with the full C-source code of the library, a flexible command line utility and a neat graphical front-end using the GTK+ toolkit. The currently supported formats are: Acr/Nema 2.0, Analyze (SPM), DICOM 3.0, InterFile 3.3 and PNG.

Static library, include files and documentation for developers.

libmia comprises a set of libraries and plug-ins for general purpose 2D and 3D gray scale image processing and basic handling of triangular meshes. The libraries provide a basic infrastructure and generic algorithms, that can be specialized by specifying the apropriate plug-ins. This package provides the development files for the library.

This package contains the library and headers for libminc2 and libvolume_io2.

The Minc file format is a highly flexible medical image file format. Minc version 1 is built on top of the NetCDF generalized data format. Minc version 2 is built on top of the HDF data format. This library handles both formats. In each case the format is simple, self-describing, extensible, portable and N-dimensional, with programming interfaces for both low-level data access and high-level volume manipulation. On top of the libraries is a suite of generic image-file manipulation tools. The format, libraries and tools are designed for use in a medical-imaging research environment : they are simple and powerful and make no attempt to provide a pretty interface to users.

Niftilib is a set of i/o libraries for reading and writing files in the NIfTI-1 data format. NIfTI-1 is a binary file format for storing medical image data, e.g. magnetic resonance image (MRI) and functional MRI (fMRI) brain images.

This package provides the header files and static libraries of libniftiio, znzlib and libnifticdf.

Open IGT Link is a simple network protocol intended for trackers, robots and other devices to send data to the main application. Some devices might also accept commands.

This package contains the development files needed to build your own IGT applications.

OpenMEEG consists of state-of-the art solvers for forward problems in the field of MEG and EEG. Solvers are based on the symmetric Boundary Element method [Kybic et al, 2005], providing excellent accuracy, particularly for superficial cortical sources. OpenMEEG can compute four types of lead fields (EEG, MEG, Internal Potential and Electrical Impedence Tomography).

This package provides static libraries and header files.

OpenSlide is a C library that provides a simple interface to read whole-slide images also known as virtual slides.

Whole-slide images, also known as virtual slides, are large, high resolution images used in digital pathology. Reading these images using standard image tools or libraries is a challenge because these tools are typically designed for images that can comfortably be uncompressed into RAM or a swap file. Whole-slide images routinely exceed RAM sizes, often occupying tens of gigabytes when uncompressed. Additionally, whole-slide images are typically multi-resolution, and only a small amount of image data might be needed at a particular resolution.

This library currently supports:

 -Trestle (.tif)
 -Hamamatsu (.vms, .vmu)
 -Aperio (.svs, .tif)
 -MIRAX (.mrxs)
 -Generic tiled TIFF (.tif)

This package contains development files needed to build OpenSlide applications.

Teem is a coordinated group of libraries for representing, processing, and visualizing scientific raster data. Teem includes command-line tools that permit the library functions to be quickly applied to files and streams, without having to write any code. The most important and useful libraries in Teem are:

• Nrrd (and the unu command-line tool on top of it) supports a range of operations for transforming N-dimensional raster data (resample, crop, slice, project, histogram, etc.), as well as the NRRD file format for storing arrays and their meta-information.
• Gage: fast convolution-based measurements at arbitrary point locations in volume datasets (scalar, vector, tensor, etc.)
• Mite: a multi-threaded ray-casting volume render with transfer functions based on any quantity Gage can measure
• Ten: for estimating, processing, and visualizing diffusion tensor fields, including fiber tractography methods.

This package provides the Teem header files required to compile C++ programs that use Teem to do 3D visualisation.

VIA is a volumetric image analysis suite. The included libraries provide about 70 image analysis functions.

This package provides the header files and static libraries of vialib, vxlib and viaio.

Vistaio is a library that handles loading and storing of data in a cross-platform manner. Its virtue is that the otherwise binary files provide an ascii header that makes it easy to get information about the contens of a file. It supports a variety of data types like images, vector fields and graphs. This is the development package containing the header files, and pkg-config script, and man pages.

VolPack is a software library for fast, high-quality volume rendering with this features:

• Renders data sampled on a regular, three-dimensional grid.
• Supports user-specified transfer functions for both opacity and color.
• Provides a shading model with directional light sources, multiple material types with different reflective properties, depth cueing, and shadows.
• Produces color (24 bits/pixel) or grayscale (8 bits/pixel) renderings, with or without an alpha channel.
• Supports arbitrary affine view transformations.
• Supports a flexible data format that allows an arbitrary C structure to be associated with each voxel.

This is the development package.

The Visualization Toolkit (VTK) is an object oriented, high level library that allows one to easily write C++ programs, Tcl, Python and Java scripts that do 3D visualization.

This package provides the VTK header files required to compile C++ programs that use VTK to do 3D visualisation.

VXL (the Vision-something-Libraries) is a collection of C++ libraries designed for computer vision research and implementation. It was created from TargetJr and the IUE with the aim of making a light, fast and consistent system. VXL is written in ANSI/ISO C++ and is designed to be portable over many platforms.

This package contains the development files needed to build your own VXL applications.

ODIN is a framework for magnetic resonance imaging (MRI). It covers the whole toolchain of MRI, from low-level data acquisition to image reconstruction. In particular, it aims at rapid prototyping of MRI sequences. The sequences can be programmed using a high-level, object oriented, C++ programming interface. It provides advanced sequence analysis tools, such as interactive plotting of k-space trajectories, a user interface for a fast compile-link-test cycle and a powerful MRI simulator which supports different virtual samples. For fast and flexible image reconstruction, ODIN contains a highly customizable, multi-threaded data-processing framework.

Smoothing algorithms allow to reduce artifacts from mesh generation, but often degrade accuracy. The method described in the paper "Context-aware mesh smoothing for biomedical applications" identifies staircase artifacts which result from image inhomogeneities and binary segmentation in medical image data for subsequent removal by adaptive mesh smoothing. Thus, context-aware smoothing enables to adaptively smooth artifact areas, while non-artifact features can be preserved. This is a implementation of this method in Cpp with Python bindings.

The Connectome File Format Library (cfflib) is a Python module for multi-modal neuroimaging connectome data and metadata management and integration.

It enables single subject and multi-subject data integration for a variety of modalities, such as networks, surfaces, volumes, fiber tracks, timeseries, scripts, arbitrary data objects such as homogeneous arrays or CSV/JSON files. It relies on existing Python modules and the standard library for basic data I/O, and adds a layer of metadata annotation as tags or with structured properties to individual data objects.

pydicom is a pure Python module for parsing DICOM files. DICOM is a standard (http://medical.nema.org) for communicating medical images and related information such as reports and radiotherapy objects.

pydicom makes it easy to read DICOM files into natural pythonic structures for easy manipulation. Modified datasets can be written again to DICOM format files.

Dipy is a toolbox for the analysis of diffusion magnetic resonance imaging data. It features:

• Reconstruction algorithms, e.g. GQI, DTI
• Tractography generation algorithms, e.g. EuDX
• Intelligent downsampling of tracks
• Ultra fast tractography clustering
• Resampling datasets with anisotropic voxels to isotropic
• Visualizing multiple brains simultaneously
• Finding track correspondence between different brains
• Warping tractographies into another space, e.g. MNI space
• Reading many different file formats, e.g. Trackvis or NIfTI
• Dealing with huge tractographies without memory restrictions
• Playing with datasets interactively without storing

Grassroots DiCoM is a C++ library for DICOM medical files. It is automatically wrapped to python/C#/Java (using swig). It supports RAW,JPEG (lossy/lossless),J2K,JPEG-LS, RLE and deflated.

Python bindings to the GDCM DICOM library.

PyMVPA eases pattern classification analyses of large datasets, with an accent on neuroimaging. It provides high-level abstraction of typical processing steps (e.g. data preparation, classification, feature selection, generalization testing), a number of implementations of some popular algorithms (e.g. kNN, GNB, Ridge Regressions, Sparse Multinomial Logistic Regression), and bindings to external machine learning libraries (libsvm, shogun).

While it is not limited to neuroimaging data (e.g. fMRI, or EEG) it is eminently suited for such datasets.

NiBabel provides read and write access to some common medical and neuroimaging file formats, including: ANALYZE (plain, SPM99, SPM2), GIFTI, NIfTI1, MINC, as well as PAR/REC. The various image format classes give full or selective access to header (meta) information and access to the image data is made available via NumPy arrays. NiBabel is the successor of PyNIfTI.

This package also provides a commandline tools:

• dicomfs - FUSE filesystem on top of a directory with DICOMs
• nib-ls - 'ls' for neuroimaging files
• parrec2nii - for conversion of PAR/REC to NIfTI images

NiPy is a Python-based framework for the analysis of structural and functional neuroimaging data. It provides functionality for

• General linear model (GLM) statistical analysis
• Combined slice time correction and motion correction
• General image registration routines with flexible cost functions, optimizers and re-sampling schemes
• Image segmentation
• Basic visualization of results in 2D and 3D
• Basic time series diagnostics
• Clustering and activation pattern analysis across subjects
• Reproducibility analysis for group studies

Nipype interfaces Python to other neuroimaging packages and creates an API for specifying a full analysis pipeline in Python. Currently, it has interfaces for SPM, FSL, AFNI, Freesurfer, but could be extended for other packages (such as lipsia).

Nitime is a Python module for time-series analysis of data from neuroscience experiments. It contains a core of numerical algorithms for time-series analysis both in the time and spectral domains, a set of container objects to represent time-series, and auxiliary objects that expose a high level interface to the numerical machinery and make common analysis tasks easy to express with compact and semantically clear code.

pyxnat is a simple Python library that relies on the REST API provided by the XNAT platform since its 1.4 version. XNAT is an extensible database for neuroimaging data. The main objective is to ease communications with an XNAT server to plug-in external tools or Python scripts to process the data. It features:

• resources browsing capabilities
• read and write access to resources
• complex searches
• disk-caching of requested files and resources

The Image-Guided Surgery Toolkit (IGstk: pronounced IGStick) is a high-level component-based framework providing common functionality for image-guided surgery applications.

This software framework consists of a set of high-level components integrated with other low-level open source software libraries and application programming interfaces (API) from hardware vendors.

The cornerstone of IGstk is robustness. IGstk provides the following high-level functionality: Ability to read and display medical images including CT and MRI in DICOM format. An interface to common tracking hardware (e.g. AURORA from Northern Digital Inc.). A graphical user interface and visualization capability including a four-quadrant view (axial, sagittal, coronal, and 3D) as well as a multi-slice axial view (from 1 by 1 to many by many such as 10 by 10).

Registration: point based registration and a means for selecting these points. Robust common internal software services for logging, exception-handling and problem resolution.

This package contains examples from the IGstk source.

ITK is an open-source software toolkit for performing registration and segmentation. Segmentation is the process of identifying and classifying data found in a digitally sampled representation. Typically the sampled representation is an image acquired from such medical instrumentation as CT or MRI scanners. Registration is the task of aligning or developing correspondences between data. For example, in the medical environment, a CT scan may be aligned with a MRI scan in order to combine the information contained in both.

This package contains the source for example programs.

eegdev is a library that provides a unified interface for accessing various EEG (and other biosignals) acquisition systems. This interface has been designed to be both flexible and efficient. The device specific part is implemented by the mean of plugins which makes adding new device backend fairly easy even if the library does not support them yet officially.

The core library not only provides to users a unified and consistent interfaces to the acquisition device but it also provides many functionalities to the device backends (plugins) ranging from configuration to data casting and scaling making writing new device backend an easy task.

This library is particularly useful to handle the acquisition part of a Brain Computer Interface (BCI) or any realtime multi-electrode acquisition in neurophysiological research.

This package contains the files needed to compile and link programs which use eegdev. Its provides also the headers neeeded to develop new device plugins. The manpages and examples are shipped in this package.

Niftilib is a set of i/o libraries for reading and writing files in the NIfTI-1 data format. NIfTI-1 is a binary file format for storing medical image data, e.g. magnetic resonance image (MRI) and functional MRI (fMRI) brain images.

This package provides the library API reference documentation.

The Visualization Toolkit (VTK) is an object oriented, high level library that allows one to easily write C++ programs, Tcl, Python and Java scripts that do 3D visualization.

VTK enables users to concentrate on their work by providing a large number of excellent and feature packed high level functions that do visualization. The library needs OpenGL to render the graphics and for Linux machines Mesa is necessary. The terms/copyright can be read in /usr/share/doc/vtk/README and README.html. VTK-Linux-HOWTO has information about using vtk, getting documentataion or help and instructions on building VTK.

This package provides the shared libraries needed to run C++ programs that use VTK.

To compile C++ code that uses VTK you have to install libvtk5-dev.

xdffileio is a library that provides a unified interface for writing and reading various biosignal file formats in realtime (i.e. streaming). It has been designed to provide a flexible, consistent and generic interface to all supported file formats while minimizing the overhead the function calls: the heaviest operations (type casting, scaling and formatting) are offloaded into a separated thread. This design makes its particularly suitable to be directly used in a data acquisition loop (like in electrophysiology recording or in Brain-Computer Interfaces (BCI)).

The genericity of the interface makes trivial various operations like transformation of a recorded file or its conversion to another file format. xdffileio currently supports EDF, BDF, GDF1 and GDF2 file formats and more will be added in future.

This package contains the files needed to compile and link programs which use xdffileio.

libavg is a high-level development platform for media-centric applications. It uses an xml-based layout language for screen design and Python as scripting language. libavg allows developers and media artists/designers to quickly develop media applications.

The goals of CTK are as follows:

• Provide a unified set of basic programming constructs that are useful for medical imaging applications development
• Facilitate the exchange and combination of code and data
• Document, integrate, and adapt successful solutions
• Avoid the duplication of code and data
• Continuously extend to new tasks within the scope of the toolkit (medical imaging) without burdening existing tasks

This package provides the CTK header files required to compile C++ programs that use CTK.

Emotive is an interface to a budget Emotiv EPOC EEG headset.

Bio-Formats is a standalone Java library for reading and writing life sciences image file formats. It is capable of parsing both pixels and metadata for a large number of formats, as well as writing to several formats.

Bio-Formats's primary purpose is to convert proprietary microscopy data into an open standard called the OME data model, particularly into the OME-TIFF file format.

OpenSlide is a C library that provides a simple interface to read whole-slide images also known as virtual slides.

Whole-slide images, also known as virtual slides, are large, high resolution images used in digital pathology. Reading these images using standard image tools or libraries is a challenge because these tools are typically designed for images that can comfortably be uncompressed into RAM or a swap file. Whole-slide images routinely exceed RAM sizes, often occupying tens of gigabytes when uncompressed. Additionally, whole-slide images are typically multi-resolution, and only a small amount of image data might be needed at a particular resolution.

This library currently supports:

• Trestle (.tif)
• Hamamatsu (.vms, .vmu)
• Aperio (.svs, .tif)
• MIRAX (.mrxs)
• Generic tiled TIFF (.tif)

This package contains the java module needed to run OpenSlide applications.

OpenSlide is a C library that provides a simple interface to read whole-slide images also known as virtual slides.

Whole-slide images, also known as virtual slides, are large, high resolution images used in digital pathology. Reading these images using standard image tools or libraries is a challenge because these tools are typically designed for images that can comfortably be uncompressed into RAM or a swap file. Whole-slide images routinely exceed RAM sizes, often occupying tens of gigabytes when uncompressed. Additionally, whole-slide images are typically multi-resolution, and only a small amount of image data might be needed at a particular resolution.

This library currently supports:

• Trestle (.tif)
• Hamamatsu (.vms, .vmu)
• Aperio (.svs, .tif)
• MIRAX (.mrxs)
• Generic tiled TIFF (.tif)

This package contains the python module needed to run OpenSlide applications.

Collection of various Perl module used by other MNI software packages.

Digital communications in medicine (DICOM) file io. Depends on Grassroots DICOM (GDCM)