Machine Learning

 

Machine Learning Products for Neuroscience Research

Automated Stereology using Artificial Intelligence

Cellairus

Cellairus uses state of the art machine learning and 3D segmentation technology integrated with a sophisticated framework using unbiased stereological sampling and counting rules to automate the most widely used unbiased stereological probe, the optical fractionator. Cellairus includes a train-by-example 3D cell classification tool, so that you can train the software to recognize the cells of interest in your specimens, imaged with your microscope imaging system. Or, you can use one of our pre-trained cell classifiers.

Optimized specifically for single-channel and multi-channel fluorescent images, Cellairus provides sophisticated co-localization analyses for multiple fluorescent labels.

  • Faster than manual stereology—our testing indicates that a typical study is up to 35 times faster than manual stereology.
  • Unbiased and more accurate than other 3D automatic detection methods. Only Cellairus provides the innovating, verifiable, reproducible combination of artificial intelligence-based 3D detection combined with stereological analysis.
 

 

Automatic Cell Detection in 2D/3D

MBF Bioscience harnesses the power of deep machine learning to enhance automatic 2D and 3D cell detection. Using extensively trained neural networks, BrainMaker, NeuroInfo, and Neurolucida all have faster and more accurate automated cell detection for a variety of cell types and co-localization analyses.

BrainMaker

BrainMaker performs cell mapping using machine learning, combined with cytoarchitectonics and user specified areas of interest requiring the characterization of neuronal circuitry to create a comprehensive anatomical 3D reconstruction.

With just a glance, you can see the location of all neurons expressing a particular gene, visualize the axonal projections of specific neurons with full anatomical context, or automatically detect cells throughout the brain.

 

 

NeuroInfo

With NeuroInfo, researchers can automatically identify and delineatebrain regions within experimental mouse brain sections. Deep learning algorithms automatically detect and reports on cell number within selected anatomical regions of interest. Our sophisticated detection algorithm is robust against histologic and imaging artifacts such as edge effects, uneven illumination, and variable staining across specimens. Using NeuroInfo, you can combine results from multiple animals and multiple experiments and standardize them with the Allen Mouse Brain Atlas.

 

Neurolucida

Identify labeled neurons in whole slide images using an intuitive cell detection workflow. Automatically map cells using machine learning based detection, combined with user-specified areas to count and map cells in 3D sections and in 3D reconstructions. Combine these maps with 3D neuron reconstructions and perform state-of-the art analyses.

 

 

Still Have Questions? Just Ask!

Paragraphs Contact Form

CAPTCHA
This question is for testing whether or not you are a human visitor and to prevent automated spam submissions.
3 + 4 =
Solve this simple math problem and enter the result. E.g. for 1+3, enter 4.