What’s under
the hood

Let us handle it.
As a team of neuroscientists and data scientists ourselves, we built an engine that combines breakthrough in-house technologies with some of the most advanced pre-processing techniques available to make it possible to build maps for all brains.

Combining in-house technologies...

OmniLabs_Feature_1-1-

Structural Connectivity
Atlas

Novel machine-learning based approach developed by Omniscient ‘reparcellates’ a brain to correctly map connections even in depressed or absent brain tissue.

o8tLabs_Feature_1-2-

Advanced Gradient
Distortion Correction

Novel MRI gradient field correction techniques to increase fidelity and definition of generally affected areas (frontopolar).

OmniLabs_Feature_1-3-

Subject Motion
Correction

Novel detection and deletion technique of time slice in which subject motion occurs.

OmniLabs_Feature_1-10-

Machine Learning

Machine learning is used throughout Omniscient software to tailor outputs to specific individual subjects and drive continuous improvement in disease model specificity.

OmniLabs_Feature_1-11-

Abnormality Identification

Potential areas of abnormal connectivity are inferred from comparisons to normative data and registered back to anatomy.

OmniLabs_Feature_1-12-

rsfMRI and Tractography Integration

Platform uses both rsfMRI and tractography for multimodal connectivity analyses.

...with the best tools available today

OmniLabs_Feature_1-7-

HCP-MMP1.0
[1]

Gain immediate access to individualized connectomic information, including 360 HCP parcellations [2] and additional 19 subcortical subregions mapped in Baker et al. [3]

OmniLabs_Feature_1-5-

Constrained Spherical
Deconvolution [4]

Constrained Spherical Deconvolution (CSD) is used over conventional Diffusion Tensor Imaging (DTI) to eliminate legacy challenges of fiber crossing present in up to 90% of regions. [5]

OmniLabs_Feature_1-6-

CompCor BOLD Signal Processing [6]

A CompCor based methodology is used to reduce noise in both BOLD and fMRI data.

OmniLabs_Feature_1-8-

Advanced Skull Stripping

A 3D convolutional neuronal network is used to segregate brain tissue from bone.

OmniLabs_Feature_1-9-

Edema Correction

Free water is modeled and removed from DWI data, and tracts within and around these regions are modeled seamlessly.

OmniLabs_Feature_1-4-

Browser Based De-identification

All subject identifiers are stripped within the browser before being uploaded to cloud servers.