Image annotation

This workflow is the integration of YOLO (You Only Look Once) machine learning models, image pre-processing scripts and labeling tools within the Galaxy platform. Galaxy is an open, web-based platform used primarily for data analysis in computational biology, but it also has applications in image processing and other fields. 

How the Galaxy YOLO image segmentation tool works

The combination of Galaxy and YOLO allows researchers to perform object detection and image analysis without requiring extensive programming knowledge. Here's how it generally works: 

• Web-based interface: Galaxy provides a graphical, user-friendly interface to access powerful analysis tools. Users can simply upload their image data, select the YOLO tool, and run the analysis.
• YOLO model execution: The Galaxy tool executes a pre-trained YOLO model, often from the Ultralytics framework, on the input images. These models can perform tasks like object detection (drawing bounding boxes) or instance segmentation (creating pixel-level masks).
• Training and prediction: Some tools allow for both model training and prediction. Users can train a custom YOLO model on their own labeled datasets to detect specific objects of interest. For example, bioimage analysis may involve detecting cells or other structures.
• Other integrations: Other machine-learning tools can be integrated with YOLO in Galaxy. For instance, the AnyLabeling tool supports YOLO for semi-automated and active learning-based data annotation. 

BIIGLE is a web-based software for image and video annotation that enables collaborative research on large datasets. It offers tools for manual and computer-assisted annotation, quality control and the collaboration on custom taxonomies to describe objects. BIIGLE is freely available and can be installed in cloud environments, a local network or on mobile platforms during research expeditions. The public instance on biigle.de is free for non-commercial use.

AnnotatorJ is a Fiji Plugin to ease annotation of images, particulrly useful for Deep Learning or to validate an alogorithm. Interestingly, it allows annotation for instance segmentation, semantic segmentation, or bounding box annotations. It includes toolssuch as active contours to ease these annotations.

webKnossos is an open-source data sharing and annotation platform for tera-scale 2D and 3D image datasets.

The core features of webKnossos are:

• fast 3D data streaming
• share links to specific locations in the data
• uniquely fast skeleton annotation (flight mode) and
• efficient volume annotation
• mesh rendering
• collaboration and sharing tools

webKnossos facilitates image analysis workflows on multi-terabyte datasets, including visualization of raw and multi-modal microscopy data, distributed training data generation and proof-reading of automatic segmentation.

As a scientific resource, webknossos.org serves as a database for published image datasets including their annotations.

Set of Fiji plugins facilitating the systematic manual annotation of images or image-regions. From a list of user-defined keywords, these plugins generate an easy-to-use graphical interface with buttons or checkboxes for the assignment of single or multiple pre-defined categories to full images or individual regions of interest. In addition to qualitative annotations, any quantitative measurement from the standard Fiji options can also be automatically reported. Besides the interactive user interface, keyboard shortcuts are available to speed-up the annotation process for larger datasets.

The plugins can be installed by activating the Qualitative annotations update site in Fiji.