Automatic Identification of CTCs in Fluorescence Microscope Images Using Morphological Filtering to Detect Cell Nuclei

Abstract

Currently, cancer is the leading cause of death in the world, and in 2020, about 10 million people died from cancer. Since cancer progresses by repeating metastasis, early detection and early treatment are required. There are various treatments for diagnosing cancer, but it is difficult to determine the presence or absence of metastasis. Therefore, as a new biomarker, analysis of CTCs (Circulating Tumor Cells) in blood including HL-60 and MCF-7 is drawing attention. However, since the proportion of CTCs in the blood is very small, there is concern that the burden on doctors will increase. Therefore, in order to detect CTC in blood, we propose a method that automatically detects CTCs from fluorescence microscope images and enables quantitative analysis by computer. First, rough extraction of cell candidate regions is performed by morphological filtering, and the watershed method using hue images is applied to the connected cells to set the ROI (region of interest). In this paper, the proposed method was applied to a total of 16 images, 8 for HL-60 and 8 for MCF-7, and CTCs detection experiment was performed. As a result, the number of detections was 882 (TPR $=98.4$%) for HL-60 and 275 (TPR $= 99.2$%) for MCF-7.