{"about":{"site":"https://codewithpapers.app","non_affiliation":"Code with Papers and Syntology are not affiliated with, endorsed by, or sponsored by Papers with Code, Meta, or the pwc-archive mirror.","licence":"CC BY-SA 4.0","licence_url":"https://creativecommons.org/licenses/by-sa/4.0/legalcode","attribution":"https://codewithpapers.app/attribution","modified":"archive material modified by Syntology; see the attribution page"},"url":"/paper/cell-tracking-via-proposal-generation-and","title":"Cell Tracking via Proposal Generation and Selection","arxiv_id":"1705.03386","date":"2017-05-09","proceeding":null,"authors":["Saad Ullah Akram","Juho Kannala","Lauri Eklund","Janne Heikkilä"],"abstract":"Microscopy imaging plays a vital role in understanding many biological\nprocesses in development and disease. The recent advances in automation of\nmicroscopes and development of methods and markers for live cell imaging has\nled to rapid growth in the amount of image data being captured. To efficiently\nand reliably extract useful insights from these captured sequences, automated\ncell tracking is essential. This is a challenging problem due to large\nvariation in the appearance and shapes of cells depending on many factors\nincluding imaging methodology, biological characteristics of cells, cell matrix\ncomposition, labeling methodology, etc. Often cell tracking methods require a\nsequence-specific segmentation method and manual tuning of many tracking\nparameters, which limits their applicability to sequences other than those they\nare designed for. In this paper, we propose 1) a deep learning based cell\nproposal method, which proposes candidates for cells along with their scores,\nand 2) a cell tracking method, which links proposals in adjacent frames in a\ngraphical model using edges representing different cellular events and poses\njoint cell detection and tracking as the selection of a subset of cell and edge\nproposals. Our method is completely automated and given enough training data\ncan be applied to a wide variety of microscopy sequences. We evaluate our\nmethod on multiple fluorescence and phase contrast microscopy sequences\ncontaining cells of various shapes and appearances from ISBI cell tracking\nchallenge, and show that our method outperforms existing cell tracking methods.\n  Code is available at: https://github.com/SaadUllahAkram/CellTracker","url_abs":"http://arxiv.org/abs/1705.03386v1","url_pdf":"http://arxiv.org/pdf/1705.03386v1.pdf","source":{"archive":"pwc-archive (Hugging Face), CC BY-SA 4.0","snapshot":"2025-07-28","licence_url":"https://creativecommons.org/licenses/by-sa/4.0/legalcode","row_kind":"abstracts"},"code_links":[{"paper_slug":"cell-tracking-via-proposal-generation-and","repo_url":"https://github.com/SaadUllahAkram/CellTracker","is_official":1,"mentioned_in_paper":1,"mentioned_in_github":1,"framework":"none","reach":null}],"tasks":[{"task_slug":"cell-detection","task_name":"Cell Detection"},{"task_slug":"cell-tracking","task_name":"Cell Tracking"}],"methods":[],"datasets_introduced":[],"methods_introduced":[],"results":[],"syntology":{"atlas_url":null,"mcp":null,"developers":"https://syntology.ai/developers"},"arxiv_metadata":null,"syntology_extracted_results":null}