The objective of this project is to develop """"""""Prototype and Scale"""""""" kinetic image recognition software to score tracking based phenotypes in a broad range of microscopy based central nervous system (CNS) applications. The target software tool can be flexibly taught to score or screen the precise dynamic phenotypes of interest, and scalable, together with the imaging assay platform (e.g. imaging system, reagents, etc.) to provide high throughput scoring. It will provide 1) motion signal decomposition to isolate heterogeneous spatial-temporal patterns;2) teachable subcellular object detection;3) teachable subcellular object tracking;4) comprehensive track characterization;and 5) kinetic data analysis interfaces to support dynamic phenotype discovery and scoring. We propose to expand and commercialize our tracking technologies including teachable tracking state based tracking, motion energy tracking enhancement and track classification. The work product will be incorporated into our flagship product SVCell, and sold through our commercial partners including Nikon Corporation. The hypothesis is that our tracking software can be used for the accurate and robust analysis of a broad range of CNS applications, and scalable for the high throughput scoring of dynamic tracking characteristics with high speed, accuracy and reliability. To test this hypothesis, we set forth the following specific aims:
Aim 1 : Optimize the teachable tracking module for a broad range of tracking based phenotypes;
Aim 2 : Optimize and validate the high throughput scoring of tracking based phenotypes;
Aim 3 : Evaluate the product readiness of the SVCell tracking beta through field tests and scientific collaborations. This project is significant because technologies are needed which can flexibly screen a variety of tracking based, dynamic phenotypes at high throughput to support practical and effective CNS related scientific programs in basic research (e.g. phenotyping) and applied research (e.g. drug discovery). Analysis of these dynamic phenotypes in time-lapse microscopy movies could provide insights into CNS disease formation and enable earlier and more effective interventions.

Public Health Relevance

Project Narrative Time-lapse microscopy image recognition can make a significant impact on the fight against neurological diseases and mental illness. By quantifying complex, dynamic phenotypes in the movies, it gives scientists a powerful tool with which to discover the basic mechanisms underlying important CNS functions, and then screen methods that act on them. This could enable earlier and more effective therapeutic interventions.

Agency
National Institute of Health (NIH)
Institute
National Institute of General Medical Sciences (NIGMS)
Type
Small Business Innovation Research Grants (SBIR) - Phase II (R44)
Project #
5R44GM077774-04
Application #
8119649
Study Section
Microscopic Imaging Study Section (MI)
Program Officer
Deatherage, James F
Project Start
2006-08-01
Project End
2013-07-31
Budget Start
2011-08-01
Budget End
2013-07-31
Support Year
4
Fiscal Year
2011
Total Cost
$456,805
Indirect Cost
Name
Drvision Technologies, LLC
Department
Type
DUNS #
827582656
City
Bellevue
State
WA
Country
United States
Zip Code
98008
Long, Jennifer B; Bagonis, Maria; Lowery, Laura Anne et al. (2013) Multiparametric analysis of CLASP-interacting protein functions during interphase microtubule dynamics. Mol Cell Biol 33:1528-45
Lowery, Laura Anne; Stout, Alina; Faris, Anna E et al. (2013) Growth cone-specific functions of XMAP215 in restricting microtubule dynamics and promoting axonal outgrowth. Neural Dev 8:22