Help
Welcome All Technologies Browse by Category

Intellicount

Technology #2018-013

Questions about this technology? Ask a Technology Manager

Download Printable PDF

License this Technology
Intellicount Research - Source Code Download
$0.00
Collections
Image Gallery
Categories
Researchers
Joseph Fantuzzo
Joseph received his B.S. degree in Chemical Engineering from Pennsylvania State University and is currently a PhD student at Rutgers University - Biomedical Engineering department. Joseph's research involves microfluidic applications in neuroscience, conducted under the guidance of Dr. Jeffrey Zahn. These interests involve developing in vitro models of neurological disorders toward the goal of improving drug screening approaches.
Vincent Mirabella
Vincent received B.S. degrees in Biochemistry and Psychology from Virginia Polytechnic Institute and State University and is currently a MDPhD student in the Rutgers-Princeton joint MDPhD program and Cell and Developmental Biology graduate program at Rutgers. Vince is studying synaptic regulation and neuromodulation under the guidance of Zhiping Pang, MDPhD.
Managed By
Andrea Dick
Assistant Director, Licensing 848-932-4018

Summary:

Aberrant synapse formation is implicated in a wide range of neuropsychiatric disorders, including autism spectrum disorders, schizophrenia, and others. As a result, considerable effort has been invested in developing techniques and tools to understand the molecular mechanisms by which synapses form and function. Analysis of synaptic puncta by imaging synaptic proteins using immunofluorescent (IF) labeling is an established and commonly used technique.  Existing approaches and materials used with IF to perform this analysis are time-consuming, prone to human error, requiring either substantial user interaction with semi-automated image processing programs or blind manual tracing.

To address the limitations of existing approaches, researchers at Rutgers University have developed a novel image processing software, Intellicount, that implements a high-throughput, fully automated synapse quantification method applying machine learning (ML) algorithms to systematically improve region of interest identification.  Additionally, a graphical user interface with statistical analysis, automated and multifunctional figure representation, and the ability to run full data sets through nested folders further increase the speed of performing analyses and ways of presenting data.

Features:

  • The platform provides fast, accurate, and largely unbiased analysis of synaptic puncta for analyzing synapses under different conditions.
  • Uses machine learning to perform synaptic protein puncta analysis on a series of images of any size and provides data on the synapse number, area, and fluorescence intensity.
  • Highly automated and does not require interaction of a user with the program at multiple processing steps (often with each image.) 
  • Supports batch processing of multiple nested folders or directories to upload and process several conditions at a time.
  • Includes statistical capabilities eliminating a need for separate processing of the raw data with excel or other software.
Benefits:
  • Improves ROI tracking and quickly quantifies puncta number and properties

  • Identifies puncta over a wide range of densities and intrinsic characteristics

  • Supports use under varied culture conditions and antibodies

  • Improves non-optimized threshold selections without a tedious and time-consuming process

  • Automates post processing analysis and data representation

Uses:

The program is designed for neuroscientists performing synaptic analysis.  It may also support a wider population within neuroscience due to the fact that the software is also able to quantify properties of dendrites. 

Intellicount requires Matlab software to operate.


Development of Intellicount was conducted through a collaboration of the Zahn, Pang, and Hart laboratories at Rutgers.