Graph based method for cell segmentation and detection in live-cell fluorescence microscope imaging

• DOI: 10.1016/j.bspc.2021.103071
• Publication Date: 2021-09-03T05:50:40Z
• Authors: Katarzyna Hajdowska; Sebastian Student; Damian Borys
• Keywords: Hough Transform; Rand index; Segmentation-based object categorization; Dice

Live-cell fluorescence image segmentation is an essential step in many studies, including drug research and other contexts where keeping cells alive crucial. Several algorithms programs have been previously proposed; however, they do not work sufficiently well on top-down pictures with overlapping cells. Our proposed algorithm, called GRABaCELL, utilizes Graph Cut, Watershed Hough Circular Transform to improve automatic counting living We also introduce a modified accuracy metric determine the quality of terms number detected image. The GRABaCELL method results are vastly better visual assessment, by both Dice index metric, than all compared methods maintaining only high value these indices but relatively small spread.