A Cell Segmentation/Tracking Tool Based on Machine Learning

Heather S Deter; Marta Dies; Courtney C Cameron; Nicholas C Butzin; Javier Buceta

doi:10.1007/978-1-4939-9686-5_19

A Cell Segmentation/Tracking Tool Based on Machine Learning

Methods Mol Biol. 2019:2040:399-422. doi: 10.1007/978-1-4939-9686-5_19.

Authors

Heather S Deter¹, Marta Dies², Courtney C Cameron¹, Nicholas C Butzin³, Javier Buceta^{4

5}

Affiliations

¹ Biology and Microbiology Department, South Dakota State University, Brookings, SD, USA.
² Chemical and Biomolecular Engineering Department, Lehigh University, Bethlehem, PA, USA.
³ Biology and Microbiology Department, South Dakota State University, Brookings, SD, USA. nicholas.butzin@sdstate.edu.
⁴ Chemical and Biomolecular Engineering Department, Lehigh University, Bethlehem, PA, USA. jbuceta@lehigh.edu.
⁵ Bioengineering Department, Lehigh University, Bethlehem, PA, USA. jbuceta@lehigh.edu.

PMID: 31432490
DOI: 10.1007/978-1-4939-9686-5_19

Abstract

The ability to gain quantifiable, single-cell data from time-lapse microscopy images is dependent upon cell segmentation and tracking. Here, we present a detailed protocol for obtaining quality time-lapse movies and introduce a method to identify (segment) and track cells based on machine learning techniques (Fiji's Trainable Weka Segmentation) and custom, open-source Python scripts. To provide a hands-on experience, we provide datasets obtained using the aforementioned protocol.

Keywords: Bacterial growth; Cell lineage analysis; Cell segmentation; Cell tracking; Computational image analysis; Fluorescence microscopy; Machine learning; Single-cell quantification.

MeSH terms

Cell Tracking / methods*
Datasets as Topic
Escherichia coli
Image Processing, Computer-Assisted / methods*
Machine Learning*
Microscopy, Fluorescence / instrumentation
Microscopy, Fluorescence / methods
Software