Share data with biological domain experts

Receive datasets fresh from the microscope. Ask for help with links to interesting locations in the dataset. 

Share results of your work, such as segmentations, object detections or classifications, with your collaborators. 

Store permanent links to data and annotations in your lab notebook.

Example: EM data from Motta et al. 2019, segmentation by scalable minds

Generate training and evaluation data

Use the volume annotation features to generate training data for a segmentation model or pixel classifier.

Use the skeleton tools to generate neuron evaluation data. The comment function is a flexible way of marking locations in the data, e.g., for seeding, or classification of segments.

Get annotation help from your collaborators. Use the task/project system to distribute tasks to multiple annotators. If you don't have annotators, you can hire our annotation services directly through webKnossos.

Example: Ground truth volume annotations from Berning et al. 2015

Visualize predictions and segmentations

Add prediction maps and color-coded segmentation layers to your dataset for debugging your work. Create and apply mappings (combining multiple segments into one) to evaluate agglomeration strategies.

Visually inspect prediction errors with the context of the raw data and other channels. Use the histogram to manually select classification thresholds.

Generate mesh visualizations of your segmentations (see screenshot above) or skeleton approximations (see screenshot below).

Example: EM data from Motta et al. 2019, segmentation (left) and affinity predictions (right) by scalable minds

Proof-read automatic reconstructions

Use Merger Mode to fix over-segmentations. Use the skeleton tools to quickly connect segments.

Use the volume annotation features to correct any errors in your automated segmentation.

Example: EM data from Motta et al. 2019, over-segmentation by scalable minds

Automate your work with our Python library

Use our free WEBKNOSSOS Python library to up/download datasets and annotations, work with WEBKNOSSOS datasets locally, and convert image stacks. The Python library seamlessly integrates WEBKNOSSOS in your existing data science workflows for training data generation, machine learning model training and volumetric data visualization.
Read the documentation.

Example: Skeleton approximation of an automatically segmented neuronEM data from Motta et al. 2019, segmentation by scalable minds

Interoperate with your favorite tools

Download your data and annotations from webKnossos to work with them in other tools. webKnossos supports standard formats (e.g. TIFF, STL, N5/ZARR, CSV) for exports.

Work with the webKnossos file formats in Python or MATLAB, with our open-source libraries. Learn more in the user documentation.

Publish your data alongside your publication

Tell your story with data. Link directly from a figure in your publication to that location in webKnossos. Readers will be able to explore your annotations and understand the context of your findings. 

webKnossos is an excellent platform for publishing large datasets including segmentations and training data. Viewers can freely browse through your data and build upon it. 

Example: Figures with wklink.org short-links from Motta et al. 2019 (Science)