Feature-based image analysis of zebrafish embryonic images

A pipeline of image analysis algorithm is developed for automatic analysis and quantification of neurons in microscopic images of zebrafish embryos. Key steps of pipeline include segmentation of zebrafish embryos from background, detection of the ROI, and quantitative measurement of neurons in the ROI. First, morphological operations are used to segment the zebrafish embryo from the background. Then based on the prior information that the torso has two approximately parallel boundaries corresponding to the back and abdomen, the algorithm automatically creates a ROI enclosing the torso. Finally, the number of neurons is obtained by improved Hough transform. Our results show that the image analysis algorithm has a high accuracy and fast computational speed. Development of such an automated image analysis pipeline represents a step toward high-throughput screening of zebrafish images with an accurate and reproducible quantification of neurons.