A Joint Scale Analysis And Machine Learning Framework For Cell Detection And Segmentation In Time Lapse Microscopy

Cell segmentation is a crucial step for understanding cell mechanisms, and behaviors and for analyzing them with significant applications in disease modeling, personalized medicine, and drug development. In this work, we propose an automated system for cell segmentation in time-lapse microscopy. This work seeks space-time interest points in multiple scales and performs spatio-temporal scale selection in image sequences. Spatio-temporal features drive segmentation and identification of cells by a multilayered neural net. We validated our method on datasets of image sequences of live cells and reference masks from the Cell Tracking Challenge (CTC) consortium. Our methodology produced promising segmentation results over multiple test image sequences. The code is available at https://github.com/smakrogi/CSTQ_Pub.