The first step in any ilastik workflow is to load the data into the project. ilastik supports importing data in various formats, from a single file or a stack of files which form a new dimension.
After creating a new project, you will be presented with the main ilastik window. The left panel of this window is populated with steps of the workflow and the overlay selection box. The right panel contains different data views based on the active workflow step selected on the left.
Data can be added to a project in the “Input Data” step visible on the left panel. When this step is active, the data selection box on the right panel can be used to import new data files or modify properties of selected files.
New data can be imported in a project with the “Add New…” button. Clicking this will present two options,
These can be used to load a 2D/3D/4D image from a single file or load a single 2D/3D/4D image from a stack of 2D images respectively.
Some workflows require matching datasets that correspond to an input. For example, the object classification from prediction maps workflow needs a separate file to specify the background pixels in the input data. In this case, tabs visible at the top of the data selection box can be used to import additional data corresponding to an input.
You can use the “Add separate image(s)…” option to add new data files to a project. This will present a standard file open dialog, where the desired input file can be selected. This dialog also allows selecting multiple files. Note that multiple files will be added as if the dialog was used once for each of these. See the following section for instructions on how to interpret multiple files as a new dimension in the data.
If one dimension of the data is separated into different files, such as a stack of 2D images to form a 3D image or a sequence of 2D images for each frame in a movie, this option can be used to form a new dimension based on a list of files.
Selecting this option will open a new dialog to select the files that will be included in the stack. The selection can be specified in three ways:
A special case are image stacks saved in multiple .h5 files (HDF5, see paragraph
Supported File Formats). HDF5 supports saving multiple datasets
encapsulated in a single file which can be accessed using internal paths,
similar to paths in a file system. For instance, you could have a folder with
file_001.h5, file_002.h5, ..., containing data that can be
composed into a single image volume. In order to assemble the images an
internal path to the image data in each file has to be specified.
Ilastik assumes that data with similar internal paths should be stacked and will
try to determine a common internal path in the selected .h5 files.
In case of multiple common internal paths the user is asked to select the
So, if the image data is found in
file_*.h5/data/imagedata in each of the
files, ilastik will automatically choose
In case of multiple datasets per file, e.g. the files might contain data
collected from multiple subjects at internal paths like
file_*.h5/images/subject1, file_*.h5/images/subject2, ..., ilastik will ask
which of those sub-images should be selected for stacking.
Once a selection has been made, the
File List box can be used to review
the names of the files that will be imported as an image stack.
The main file format used by ilastik is HDF5. Files with extensions
ilp (ilastik project files) will be recognized as HDF5.
Widely used image formats such as
libopenexrsupport in VIGRA) ,
libjpegsupport in VIGRA)
libtiffsupport in VIGRA)
libpngsupport in VIGRA)
can be imported directly into a project, as well as NumPy binary array
files with extension
You can review and/or change the way ilastik interprets your dataset using the Dataset Properties Editor. For example, to specify that a stack of images should be interpreted as having a t-axis (for time) instead of a z-axis, use this editor. To open the editor, double-click an item in the dataset list or right-click the item and select “Edit Properties”. Read on for a description of each field in this window.
ccorrespond to time and color dimensions respectively. ilastik differentiates 2D + time data from 3D data, computing temporal features for the former. Marking a dimension as time changes ilastik behavior.