A High Throughput Platform for Exploring and Analyzing Whole Brain Tissue Cleared Images

With ~100 million nuclei, no human can count all the cells in a mouse brain.

We need to train an image recognition algorithm to recognize what a nucleus looks like.

This requires many manually labeled nuclear samples, so we’re developing a tool to make this easier to do.

This tool will allow us to easily quantify differences in brain structure caused by mutations associated with neuropsychiatric disorders.

Video credit: Tala Farah