Automated and semi‐automated cell tracking: addressing portability challenges

摘要: Cell tracking is a key task in the high-throughput quantitative study of important biological processes, such as immune system regulation and neurogenesis. Variability cell density dynamics different videos, hampers portability existing trackers across videos. We address these potability challenges order to develop portable algorithm. Our algorithm can handle noise segmentation well divisions deaths cells. also propose parameter-free variation our tracker. In tracker, we employ novel method for recovering distribution displacements. Further, present mathematically justified procedure determining gating distance relation performance. For range real videos tested, tracker correctly recovers on average 96% moves, outperforms an advanced probabilistic when detection quality high. The scalability was tested synthetic with up 200 cells per frame. more challenging conditions, semi-automated framework that increase ratio recovered tracks by 12%, through selective manual inspection only 10% all frames video.