Neuron and Connectome Reconstruction Service

Full service for reconstructing biological features from large-scale 3D microscopydatasets using AI technology. Neurons, Cell Organelles, Synapses, Lesions, and more.
We apply our battle-tested AI models and reconstruction techniques on your data.Scalable from gigabyte to petabyte-scale datasets.

Reconstruction Results 

After
Before

Raw image data from the Max Planck Institute for Brain Research

Neuron Reconstruction

Our tooling has pre-trained AI models and state-of-the-art techniques to reconstruct neurons, organelles, and other features from biological microscopy data. 
We offer a full reconstruction service including training custom models 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 Voxelytics, we offer a repeatable approach to 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 proofread the results.

    Neuron reconstruction and synapse detection
    Heuristical split and merge error fixes
    Annotation and proof-reading services available
    Ready for 3D Electron Microscopy(SBEM, Multi-SEM. FIB-SEM, TEM) 
    Fully integrated, collaborative workflow in WEBKNOSSOS
Illustration
Illustration

Raw image data from the Max Planck Institute for Brain Research

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
Illustration

HPC and Cloud Ready

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

    HPC and Cloud Ready
    Highly parallelized across many core 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.

Project Workflow

In order to make the most out of your data, we like to collaborate closely with you.

1

Onboarding

    Introductory call to discuss your research goals and datasets
    Definition of the analysis tasks, project milestones and any specifics
    Complete all of the paperwork and arrange data access

2

Collaborative Analysis

    Work on your analysis project
    Regular progress meetings(bi-weekly or monthly)
    Optional annotation or proof-reading work 

3

Delivery

    Intermediate results in WEBKNOSSOS throughout the project
    Visualization of the results
    Delivery of the results in a format of your choosing

FAQ

Billing

Most projects are unique, so we try to be flexible about billing structures. Most of our projects are billed in time & materials, but we also offer milestone-based prices. For smaller well-defined tasks, we also offer fixed prices. Please reach out for a quote on your analysis project.

Compute Infrastructure

For your project, we can either work using the compute infrastructure that you already have (e.g., Scientific Computing cluster) or provision infrastructure in the cloud. Which resources we use depend on the dataset, analysis task, and availability.

Annotation work

Many projects require custom training data or manual proof-reading in order to achieve good analysis results. We are happy to generate this data fully managed through our partner network.If you have access to trained people who can help with annotation work, we can also supply the relevant tasks.

  • Quantum CEO & our partners
  • Quantum CEO & our partners
  • Quantum CEO & our partners

Looking for 3D Image Alignment?

Successful 3D image segmentation relies on proper normalization and robust alignment of the raw image slices.
Voxelytics Align provides all the tools for image normalization, in-plane stitching of individual images, and robust global alignment & registration.

Learn more