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...


Structural Connectivity
Atlas [1]

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


Advanced Gradient
Distortion Correction

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


Subject Motion

Novel detection and deletion techniques of slices in which subject motion occurs.


Machine Learning

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


Abnormality Identification

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


rsfMRI and Tractography Integration

Platform uses both rsfMRI and tractography for multimodal connectivity analyses.

...with the best tools available today



Gain immediate access to individualized connectomic information, including 360 HCP parcellations [3] and additional 19 subcortical subregions mapped in Baker et al. [4]


Constrained Spherical
Deconvolution [5]

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. [6]


CompCor BOLD Signal Processing [7]

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


Advanced Skull Stripping

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


Edema Correction

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


Browser Based De-identification

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

1. Doyen, S., Nicholas, P., Poologaindran, A., Crawford, L., Young, I. M., Romero-Garcia, R., & Sughrue, M. E. (2021). Connectivity-based parcellation of normal and anatomically distorted human cerebral cortex. Human Brain Mapping, 1– 12. https://doi.org/10.1002/hbm.25728
2. Neurolab, C., 2018. HCP-MMP1.0 volumetric (NIfTI) masks in native structural space.
3. Glasser, M.F., Coalson, T.S., Robinson, E.C., Hacker, C.D., Harwell, J., Yacoub, E., Ugurbil, K., Andersson, J., Beckmann, C.F., Jenkinson, M. and Smith, S.M., 2016. A multi-modal parcellation of human cerebral cortex. Nature536(7615), pp.171-178.
4. Baker, C.M., Burks, J.D., Briggs, R.G., Conner, A.K., Glenn, C.A., Sali, G., McCoy, T.M., Battiste, J.D., O’Donoghue, D.L. and Sughrue, M.E., 2018. A Connectomic Atlas of the Human Cerebrum—Chapter 1: Introduction, Methods, and Significance. Operative Neurosurgery15(suppl_1), pp.S1-S9.
5. Tournier, J.D., Calamante, F. and Connelly, A., 2007. Robust determination of the fibre orientation distribution in diffusion MRI: non-negativity constrained super-resolved spherical deconvolution. Neuroimage35(4), pp.1459-1472.
6. Jeurissen, B., Leemans, A., Tournier, J.D., Jones, D.K. and Sijbers, J., 2013. Investigating the prevalence of complex fiber configurations in white matter tissue with diffusion magnetic resonance imaging. Human brain mapping34(11), pp.2747-2766.
7. Behzadi, Y., Restom, K., Liau, J. and Liu, T.T., 2007. A component based noise correction method (CompCor) for BOLD and perfusion based fMRI. Neuroimage37(1), pp.90-101.