Related Experiment Video
Updated: Aug 17, 2025
Quantitative Localization of a Golgi Protein by Imaging Its Center of Fluorescence Mass
Published on: August 10, 2017
A Primer on Deep Learning-Based Cellular Image Classification of Changes in the Spatial Distribution of the Golgi
Daisuke Takao1, Yuki M Kyunai2, Yasushi Okada3,4,5
1Department of Cell Biology and Anatomy and International Research Center for Neurointelligence (WPI-IRCN), Graduate School of Medicine, The University of Tokyo, Tokyo, Japan. dtakao@m.u-tokyo.ac.jp.
Abstract:
The visual classification of cell images according to differences in the spatial patterns of subcellular structure is an important methodology in cell and developmental biology. Experimental perturbation of cell function can induce changes in the spatial distribution of organelles and their associated markers or labels. Here, we demonstrate how to achieve accurate, unbiased, high-throughput image classification using an artificial intelligence (AI) algorithm. We show that a convolutional neural network (CNN) algorithm can classify distinct patterns of Golgi images after drug or siRNA treatments, and we review our methods from cell preparation to image acquisition and CNN analysis.
