Automated segmentations

Full service for reconstructing biological features from large-scale 3D microscopy datasets using AI technology. Neurons, Cell Organelles, Synapses, Lesions and more.
Custom trained for your use case and data. Scalable from gigabyte to petabyte-scale datasets.

Automated segmentation services

Illustration

Neuron Reconstruction


Our tooling has been developed for building powerful and custom AI models to reconstruct neurons, organelles and other features from biological microscopy data.
We offer a full service including training data generation and proof-reading in order to achieve high-quality results for your use cases.

● Neuron Segmentation● Axons & Dendrites Reconstruction● Synapse and Dendritic Spine Detection● Heuristical split and merge error handling● Annotation and proof-reading services available

Connectome Reconstruction

Using our Voxelytics Connect tooling, we offer a repeatable, automated approach to circuit reconstruction and generating Connectome matrices from raw electron microscopy data.
We collaborate closely with your group in order to make the most out of your data. As part of a full service, we optionally generate the required training data and proof-read the results.
● Neuron reconstruction and synapse detection● Heuristics for split and merge error fixes● Annotation and proof-reading services available● Ready for 3D volume electron microscopy● (SBEM, Multi-SEM. FIB-SEM, TEM)● Fully integrated, collaborative workflow in WEBKNOSSOS

Illustration
Illustration

Blood Vessel and Nuclei Segmentation

Segment large biological features, such as blood vessels, nuclei or somata, for analysis or masking purposes.

● Blood Vessel, Somata, and Nuclei Segmentation● No training data required● Excellent for operations requiring masks


Raw image data by Max Planck Institute for Brain Research

Custom AI Models

We are curious to learn about new use cases. Our tooling is flexible enough to be adapted to a wide range of image analysis tasks. Please get in touch to discuss your use cases and datasets with us.

● Segmentation, counting and measuring of objects● Support for many 2D and 3D image modalities (light and electron microscopy, ● Micro-CT, CT, MRI, Synchrotron X-Ray)● Custom trained for your use case● Scalable from gigabyte to petabyte-sized datasets


Raw image data from our collaboration partners

Illustration

HPC and Cloud Ready


For our services, we either use cloud services or your Scientific Computing cluster. Our tooling is optimised for throughput of very large datasets and heavily makes use of parallel computing.

● HPC and Cloud Ready● Highly parallelised across manycore and GPU systems● Distributed computing with SLURM, PBS or other schedulers

Neuron reconstruction of Human cortex from volume EM. Raw data by Loomba et al. (Science 2022). Segmentation, connectome, and animation by scalable minds.

Case study


Loomba et al. submitted a comparative study of neural structures in 8 Mouse, Macaque, and Human datasets (SBEM, each 0.5-2TB).
For that, a reliable, repeatable, highly-scalable solution for Connectome reconstruction across three different species with significant differences in cellular morphology was required.
The automated image alignment, neuron segmentation, and connectome reconstruction were carried out using Voxelytics.

We applied the default alignment workflows of Voxelytics on the respective dataset without manual tweaking. The out-of-the-box neuron segmentation and synapse detection workflows worked well for the mouse datasets. Any parameter tweaks could be made in a config file and consecutive Voxelyics runs would only execute the changed workflow tasks. To improve the reconstruction quality for the macaque and human tissue, we interactively re-trained the segmentation models with data labeled in WEBKNOSSOS. We decided on a best-performing configuration after using the integrated evaluation methods and rolled that out to the remaining datasets. All Voxelytics workflows were executed highly parallelized on an HPC and results were instantly available in WEBKNOSSOS for inspection.
Our declarative analysis approach, the repeatable workflows, and extensible task architecture allowed us to quickly iterate on the 8 datasets and derive insights in a manner of days. For scientists, Voxelytics moves the analysis burden from big data processing challenges to neurobiological analysis.

How does it work

1

Upload your data and define tasks

With your data on WEBKNOSSOS, we will schedule an intro call to discuss your research goals. Based on that, we will propose a project structure and estimate.

2

Collaborative analysis

Work on your analysis project and have regular progress meetings(bi-weekly or monthly).We can optionally organise annotation or proof-reading of the work. 

3

Receive the results

The intermediate results will be accessible on WEBKNOSSOS throughout the project. 
You can then visualise the end results and receive them in a format of your choosing

Some examples

Neuron segmentation

Neuron segmentation

View example dataset

Synapse detection

Synapse, vesicle and mitochondria detection

View example dataset

Neuron type detection

Neuron type detection

View example dataset