Deep Learning Method for Extracting Areas of Cancer Cells Using Microscope Images

The targets of therapy in treatments for cancer are the cancer cells themselves. To verify the effectiveness of treatment, a system to measure the status of these cells is necessary. The objective of this study is to develop a system that automatically measures the area of a cell colony in a microscope image and the number of cells in the colony. To this end, we propose a method to predict the colony region using deep learning, and to count the number of cells quantitatively and without staining. © 2023 Institute of Electrical Engineers of Japan. Published by Wiley Periodicals LLC.