Dr. Minjeong Kim (Computer Science) received new funding from UNC Chapel Hill for the project “A Scalable Platform for Exploring and Analyzing Whole Brain Tissue Cleared Images.”
Public Health Relevance
This proposal aims to develop a next-generation cell segmentation engine for whole-brain tissue cleared images. The researchers’ proposed work is built upon their previous 2D nuclear segmentation project using deep-learning techniques. However, they found that their current computational tool is limited in 2D segmentation scenarios and insufficient in annotated training samples.
To address these limitations, researchers will first develop a cloud-based semi-automatic annotation tool with the capacity of virtual reality. Their annotation tool is designed to be cross-platform, which allows them to partner with “SciStarter” (the largest citizen science projects in the world) and acquire large amount of cell annotations from science-enthusiastic volunteers. Meanwhile, researchers will develop a next-generation 3D cell segmentation engine using an end-to-end fully-connected convolution neural network. To facilitate 3D cell segmentation, researchers will also develop a super-resolution method to impute an isotropic high-resolution image from a low-resolution microscopy image.
After the development of a 3D cell segmentation engine, researchers will continue to improve its generality by developing a transfer-learning framework which enables them to rapidly deploy their 3D cell segmentation engine to the novel microscopy images without the time-consuming manual annotation step.
Finally, researchers will apply their segmentation tool to visualize and quantify brain structure differences within genetically-characterized mouse and human brain tissue at UNC Neuroscience Center.
At the end of this project, researchers will release the software (both binary program and source code) and the 3D cell annotations in order to facilitate similar neuroscience studies at other institutes. Considering the importance of high-throughput computational tools in quantifying three-dimensional brain structure, this cutting-edge technique will be very useful in the neuroscience research community.
