Versatile Microfluidic Platform for Automated Live-Cell Hyperspectral Imaging Applied to Cold Climate Cyanobacterial Biofilms
Tianyang Deng, Damon DePaoli, Ludovick Bégin, Nan Jia, Leon Torres de Oliveira, Daniel Côté, Warwick F. Vincent, Jesse Greener
Abstract
live-cell imaging and automated species detection in mixed cyanobacterial biofilms from cold climate environments. Using a multimodal microscope with custom optics applied to a chip with six parallel growth channels, we monitored biofilm dynamics via continuous imaging at natural irradiance levels. Machine learning algorithms were applied to the collected hyperspectral images for automatic segmentation of mixed-species biofilms into individual species of cyanobacteria with similar filamentous morphology. The coupling of microfluidic technology with modern multimodal imaging and computer vision systems provides a versatile platform for the study of cause-and-effect scenarios of cyanobacterial biofilms, which are important elements of many ecosystems, including lakes and rivers of the polar regions.