• Home
  • Omniscient Neurotechnology

Omniscient Neurotechnology

Omniscient Neurotechnology has developed advanced solutions to support neurosurgeons, neurologists, psychiatrists, clinical researchers, and academic’s insights to modernise both research and clinical trial practices. Centered on the big data and machine learning approach of Connectomics, the solutions have transformed preprocessing practices for academic researchers by connecting neuroscientists together with cloud-based software. With the Infinitome, this software supports clinical researchers as a neuroresearch platform by simplifying data and image analysis for brain research with no coding required. Lastly, the Quicktome was developed with connectomics research, algorithms, and cloud computing to guarantee precision in neurosurgery.

Decoding the brain through connectomics.

o8t Labs

The o8t Labs is the groundbreaking, centralised solution to connect neuroscientists to breakthroughs in the human connectome. This free community platform for academic users was developed by Omniscient to streamline and standardise the quality of neurological research. With the integration of automating accurate preprocessing steps with cloud software, o8t labs effortlessly provide complex connectomic and functional network analysis for researchers across varying levels of computational skills. Moreover, the incorporation of federated learning provides users with consistently improved models of the human brain throughout the software’s usage.

For each subject, brain mapping is undertaken with a comprehensive and multimodal approach. This approach involves combining modern techniques adopted by top research institutions including; HCPMMP1.0,  CSD tractography, and many more. Moreover, design with Omniscient’s in-house technologies to develop accurate and personalised brain maps while seamlessly managing existing abnormalities and edemas.

This software provides access to the most advanced brain network viewer available to simplify the identification and visualisation of neurological connections with a network viewer, connectivity matrix, and parcellation encyclopedia. O8t Labs encourages users to prevent wasting time on coding and overcome IT constraints by focusing on developing breakthroughs by performing advanced analytics on scans accessible on MRI machines to be integrated seamlessly into existing data workflows. Designed for mass scalability and collaboration, this software manages all storage and server maintenance.

Implementing o8t labs to start streamlining neurological research by following these below steps:

Step 1: Upload Scans

Compatible with both NIFTIs and DICOMs. Multiple subjects can be uploaded and scanned in bulk. View Omniscient’s MRI acquisition protocol by clicking here

Step 2: Auto Processing

Scans are processed through our enterprise-grade servers which automatically perform all pre-processing steps within an hour. 

Step 3: View Results Online

Once processed, all of your data is then securely stored in the cloud that can be accessed from your browser, even on mobile. 

Step 4: Export Analyses

All data exports are designed for compatible workflow integration and support R, Python, MATLAB, and GO programs. View Omniscient’s downloadable export documentation to easily move data back into your existing workflows by clicking here

Highlights:

In House Technologies

Modern Tools

  • Structural Connectivity Atlas: Incorporated with novel machine learning-based approach by omniscient ‘reparcellates’ a brain to automatically and correctly map connections even in depressed or absent brain tissue.
  • Advanced Gradient Distortion Correction: Novel MRI gradient field correction techniques to increase the fidelity and definition of generally affected areas, specifically the frontopolar.
  • Subject Motion Correction: Modernised detection and deletion technique of time slice which subject motion occurs
  • Machine Learning: Implemented throughout omniscient software to tailor outputs to specific individual subjects and drive the 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 & Tractography Integration: This platform adopts both rsfMRI and tractography for multimodal connectivity analyses
  • HCP-MMP1.0 [1]: This technology provides immediate access to individualised connectomic information, including 360 HCP parcellations [2] and additional 19 subcortical subregions mapped in Baker et al. [3]
  • Constrained Spherical Deconvolution [4]: Constrained Spherical Deconvolution (CSD) is applied over conventional Diffusion Tensor Imaging (DTI) to eliminate legacy challenges of fiber crossing present in up to 90% of regions [5].
  • CompCor BOLD Signal Processing: a CompCor based methodology is used to reduce the 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.

Infinitome

This next-generation neuro research platform collates insights from groundbreaking data and images analysis of the brain without any coding required. This cloud-driven, HIPAA-compliant research platform transforms raw MRI data into detailed functional network maps of the human brain that are scalable for projects of all sizes. With the 1 in 5 people affected by neurological and mental illnesses around the world, it is through the implementation of computational neuroscience to interpret volumes of functional connectivity data. In addition, anatomical and biological data developed with machine learning is integral to advance clinical research.

The Infinitome is integral to accelerate researchers understanding and clinical trials of the most complex diseases today including; Alzheimer’s disease, depressive and anxiety disorders, Autism, brain cancer, brain injury rehabilitation, Epilepsy, Fibromyalgia, migraines, Multiple Sclerosis, OCD (Obsessive-compulsive disorder), Parkinson’s disease, schizophrenia, Tourette’s syndrome, and more.

Highlights:

  • Secure & Efficient Data Workflow: Built for HIPAA compliance and easily adaptable to your informational workflow. In addition, with natural language processing (NLP) and PACs integration, data is efficient and scalable. 
  • Subject Specific Brain Mapping: The Infinitome’s computation process integrates and automates techniques adopted by top research institutions with in-house technologies that are applied to develop accurate, personalised brain maps. 
  • Connectomic Matrix: With machine learning algorithms, it encourages users to seamlessly analyse countless interconnections of the brain.
  • Clinically Relevant Scan Time: This software applied DTI and resting-state fMRI scans that are acquirable on most MRI machines with minimally extended scan times. 
  • Intuitive User Experience: The Infinitome runs itself on your internet browser and is designed for users of all computational skill levels for seamless usage. 

Quicktome

This software was designed by neurosurgeons to empower surgery with detailed data of the brain’s network information that are built specifically for each patient. More than neuroimaging, it provides a rapid delivery of actionable surgical insight supported by combining decades of Connectomics research with algorithms and cloud computing.

For every scan, Quicktome utilises innovative algorithms to generate robust visualisations that are personalised to each patient’s anatomy. With noise affecting the visualisation, all raw MRI scans would undergo a series of steps that correct noise including gradient distortion and subjective motion correction. This software adopts state-of-the-art algorithms to automatically eliminate manual tuning in areas of freewater (e.g. edema). Dissimilar to the DTI, this software is equipped with CSD-based tractography to model multiple tracts crossing the same region, a phenomenon present in 70%-90% of white matter. This includes crucial regions such as the visual tracts, language tracts, and the lateral projections of hand-motor.

Learn more about the benefits of o8t’s product lines by contacting us today.

References

1. Neurolab, C., 2018. HCP-MMP1.0 volumetric (NIfTI) masks in native structural space.
2. 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.
3. 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.
4. 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.
5. 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.
6. 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.

  • The Connectome Revolution - Episode 1