Abstract
Zebrafish (Danio rerio) are heavily studied because they share a similar genetic structure to humans. The skin patterns of zebrafish are comprised of horizontal stripes of different colored pigment cells. Accurately quantifying the cell size of various pigment cells in relation to their location on the skin is a crucial step towards better understanding cell behavior. The first step to measuring pigment cells is extracting cells from in vivo images of fish. In my research, I use machine-learning techniques to extract the size of black pigment cells from images of real zebrafish. Currently, I am focused on identifying the optimal method of extraction to ensure that we accurately determine cell locations in images with varying light intensities and microscope settings. To make image processing more efficient, I am utilizing batch processing to extract the cell locations of multiple images at once. In this presentation, I will highlight how training on different images impacts our measurements of pigment cells and share results on how cell size varies across the skin of zebrafish.