Database
The Database tab gives an overwiew of all datasets that have been imported in the project so far.
The main table shows each dataset with its name and a thumbnail of the image. By default, all datasets are shown but they can be sorted or filtered, using the comboboxes above. In particular, the database can be filtered according to:
whether they have already been labeled or not,
whether a comment has been written,
which tags have been assigned to them.
Additionally, a text field lets you search more specifically a subset of the database.
If the project was defined with layers, a drop-down menu can be used to define which layers are active. See the Layers page for more information.
When one of the items is selected, all stored information about the image are displayed on the right hand side. Most of the entries in the table are read-only, except for:
Name: the identifier shown in the database. It is only used for identification purpose and does not need to be unique.
Comments: this field allows you to enter any particular remark on the dataset. Comments can be searched for in the “Filter” text field.
Tags: if your projects has tags, you can toggle the selected datasets’ tags.
Right-clicking a dataset in the grid view opens a context menu with the following actions:
Annotate: This action loads the image and switches to the Annotation tab. This can also be achieved by double clicking on the thumbnail, or pressing <enter> with a selection.
Open in ImFusion Suite: If you have the ImFusion Suite software installed on your computer, this option will start it and automatically load the selected image (as well as its annotations). The first time you click on this action, the software will ask you to specify the path of the ImFusion Suite executable. In order to do that, open the Settings dialog by clicking on the icon in the top right corner of the software, select the Global category and then define it adequately.
Export Data: A copy of an individual dataset can be exported into one of the supported image formats.
Export Labels: A copy of an individual annotation can be exported either as a label map or as a mesh.
Delete: This option will remove the dataset from the project. The original data will not be lost, but if a copy has been created during import, this copy will be deleted. This action cannot be undone and any associated annotation will be lost. Datasets can also be removed from the project by pressing the Delete key after selecting them.
Options are available in the bottom right corner to change the size of the thumbnail and the visibility of the label maps for the already annotated images. An icon with a brush will appear on the thumbnail of all datasets that have already been annotated. An icon with three dots will appear on the thumbnail of all datasets with a comment. For each tag, a square (with the color of the tag and the corresponding text) will appear on the thumbnail of all datasets with this tag.
Grouping
Warning
This feature is still experimental.
The database supports optional grouping of datasets. By default, datasets which have been loaded from DICOM can be grouped by their patient, study and series. Custom grouping is possible through the Python API.
Note that grouping is only available in projects created with v0.22 or later. You can use this Python script to initialize grouping for an existing project.