Applying deep learning for cell detection in time-lapse microscopic images

The budding yeast Saccharomyces cerevisiae is an effective model for studying cellular aging. We can measure the lifespan of yeast cells in two ways: replicative and chronological lifespans. Chronological focuses on the time that a cell can survive. The replicative lifespan (RLS) is the number of cell divisions that a single mother cell can go through before ceases to be dividing. RLS is a measurement of individual cells and is more informative on the aging process than in chronological lifespan. Many genes that influence yeast RLS have been shown to be highly conserved and have a similar effect on aging in humans. Hence, studies on cellular aging typically focus on RLS. RLS is traditionally measured by micro-dissection – a tedious and time-consuming process. Recently, a high-throughput yeast aging analysis (HYAA) based on microfluidics measurement of replicative aging has been developed. Each mother cell is captured by a trap on the microfluidic device. This device generates an enormous amount of dataset, but the process to manually track these objects is tedious and time consuming and would take years with how large a single dataset can be. This thesis is to address the challenges on how to efficiently and reliably infer the RLS from thousands of time-lapse microscopic images. We implemented two deep learning methods, Faster R-CNN and MASK R-CNN to detect cell the objects. Our results show that Mask R-CNN is a promising method to automate the HYAA image analysis compared to Faster R-CNN approach