Experience fast 3D microscopy data exploration with WEBKNOSSOS.
Annotate your data with AI, explore 3D meshes, collaborate in real-time, manage datasets, and more. Share your research with just one click.
Sign up for free at https://t.co/0wSoQOZ6QT!
“Students weren’t just annotating - they were thinking critically about what they observed.”
In this course project, students used WEBKNOSSOS to explore real EM data, segment organelles, analyze cellular asymmetry, and develop biological hypotheses from their own observations. Read more: https://t.co/7Ur8YdXClH
Segment cells in 3D with the Quick Select tool in WEBKNOSSOS! Just click inside a process and WEBKNOSSOS automatically segments it across multiple sections. Adjust the number of Z sections in the toolbar settings (top right).
“The dataset was already on WEBKNOSSOS, which made it easy to onboard students and start annotating immediately.”
Ahmed Elewa shares how browser-based access to published EM datasets enabled a semester-long collaborative annotation project with ~50 students.
Read more: https://t.co/7Ur8YdXClH
Automatically sample bounding boxes for ML training in WEBKNOSSOS. Choose the magnification, number, and size of boxes, and review the generated boxes to adjust any that landed in empty regions.
Learn how to choose suitable box sizes and counts for ML training: https://t.co/7gs7KjlSMF
"We can produce up to 12 tomograms per hour, and beam time can run for 24 hours straight. So a single user can easily generate multiple terabytes in one session."
Read more on how Angelika Svetlove used WEBKNOSSOS to efficiently handle such massive images: https://t.co/AVSaYux4s0
We spoke with Ahmed Elewa from Miami University about using WEBKNOSSOS in a cell biology course built around real C. elegans vEM data.
48 students annotated cells, generated AI training data, and even contributed to a biological discovery.
Read the interview: https://t.co/7Ur8YdXClH
Managing a connectomics or volume EM project?
Validate segmentation on small regions before scaling to the full dataset. Iterate until results are satisfactory.
Start with a small test bounding box.
Validate the segmentation, inspect errors, and only then run the model on the full dataset.
A controlled workflow for large-scale EM analysis.
Applying AI segmentation to a vEM dataset?
Through the WEBKNOSSOS AI Grants, selected projects receive compute credits to evaluate segmentation workflows on their data.
Reach out with a link to your WEBKNOSSOS dataset and project description at [email protected].
Create figures for your paper with WEBKNOSSOS 🖼️
Customize the view to match your needs: set display modes, adjust the layout, load meshes and edit colors and transparency. These are just a few of the available options for generating publication-ready images. Try it out yourself on https://t.co/SSjiLBLCcH!
“Users can leave Hamburg and continue inspecting their datasets the same day without transferring large volumes of data.”
At the P14 beamline, tomography datasets appear in WEBKNOSSOS minutes after reconstruction, allowing users to explore them remotely in the browser.
https://t.co/AtidzxOHi7
All AI analysis workflows in WEBKNOSSOS are now fully documented.
Our step-by-step tutorials cover:
Alignment
Automated segmentation
Custom model training
Explore the documentation: https://t.co/1htbHtbFcH
Running a volume EM core facility?
Deliver aligned and segmented datasets with reproducible AI workflows in WEBKNOSSOS - from alignment to custom model training.
Support your users with documented, scalable analysis pipelines.
“We can generate data much faster than people can analyze it.”
At EMBL P14, synchrotron X-ray tomography produces terabytes per experiment. The bottleneck is no longer acquisition: it’s analysis.
Read the full interview with Angelika Svetlove: https://t.co/mLUh2pRBwS
Segmentation errors often reflect gaps in the training data.
Review the ground truth, add missing examples, retrain, and iterate.
Custom model training gives you direct control over model behavior.
Guidelines for ground truth annotation: https://t.co/5mI4hNMzjR
🌟Enhancement🌟
Open datasets or jump straight to annotations - right from the command palette.
Press Ctrl/Cmd + P from anywhere in the UI, then scroll or start typing to find what you need.
“And from a facility perspective, everything is automated. No one has to manually convert, upload, organize, or assign permissions.”
At EMBL P14, reconstructed tomography datasets are automatically converted and transferred to WEBKNOSSOS through the API.
Read more: https://t.co/AtidzxOHi7
WEBKNOSSOS AI Grant 🔬
We are offering compute credits to support selected research projects applying AI segmentation to volume EM datasets.
Interested? Send us a link to your dataset in WEBKNOSSOS and a short description of your analysis goals at [email protected].
Run automated alignment in WEBKNOSSOS and improve the results with manual matches when needed.
Maintain control over challenging areas while keeping the workflow efficient.
https://t.co/5ZDebsiZdC