Stereology Resource Center, Inc. awarded $736,172 NSF Phase II grant

September 20, 2019

The Stereology Resource Center (SRC), Inc. was awarded a $736,172 National Science Foundation (NSF) grant to continue their research and development for the project titled “STTR (Small Business Technology Transfer) Phase II: Deep Learning Technology for the Microscopic Analysis of Stained Cells Using Unbiased Methods.” Leadership for the project will be provided by Principal Investigator Peter R. Mouton, Ph.D., President and Chief Scientific Officer of SRC Biosciences in Tampa, Florida and co-Principal Investigators Computer Science and Engineering Distinguished University Professor and Vice Chair Dmitry Goldgof and Computer Science and Engineering Distinguished University Professor Lawrence Hall.

Prior to conducting this research, Mouton led his team through the I-Corps program at USF Research and Innovation. I-Corps is a six-week workshop for university entrepreneurs to learn more about commercialization of their inventions. After completing this program, Mouton, Goldgof and Hall applied for a STTR Phase I grant that was awarded $224,417 for the project titled “STTR Phase I: Microscope-based Technology for Automatic Brain Cell Counts Using Unbiased Methods.” The STTR Phase I grant started on January 1, 2018 and ended on December 31, 2019.

According to the abstract, “The results of the Phase I research showed that tissue sections were automatically counted over 10X times faster with equal accuracy as manual stereology. In addition, reproducibility was 99% and required little or no user training.”

According to Mouton, “The purpose of the STTR Phase II grant is to expand development and validation of this software to automate the collection of stereology data for biomedical and bioscience research. The Phase II objectives are to develop standardized, high-throughput, deep learning networks for quantifying other stereology parameters of stained cells and tissues, validate active deep learning as a technique for customizing deep learning for all user staining protocols, and update the software and documentation to support user-friendly workflow. The aim is to train the neural network to accurately segment a wider range of cell and tissue pathology with variable morphologies with a performance metric for accuracy of 95%. By automating the process of collecting stereology data, this project will bring significant benefits to society by accelerating biomedical research, toxicology studies, drug development, scientific breakthroughs and medical discoveries.”  The current STTR Phase II grant started September 1, 2019 and ends August 31, 2021.