Automated Curation of CNMF-E-Extracted ROI Spatial Footprints and Calcium Traces Using Open-Source AutoML Tools

Created by W.Langdon from gp-bibliography.bib Revision:1.8051

@Article{tran:2020:fncir,

• author = "Lina M. Tran and Andrew J. Mocle and Adam I. Ramsaran and Alexander D. Jacob and Paul W. Frankland and Sheena A. Josselyn",
• title = "Automated Curation of {CNMF-E-Extracted ROI} Spatial Footprints and Calcium Traces Using Open-Source {AutoML} Tools",
• journal = "Frontiers in Neural Circuits",
• year = "2020",
• volume = "14",
• number = "42",
• month = jul # " 15",
• keywords = "genetic algorithms, genetic programming, TPOT, AutoSklearn, Python, calcium imaging, open-source, machine learning, microendoscopy, image processing, ROI, region of interest",
• ISSN = "1662-5110",
• code_url = "https://github.com/jf-lab/cnmfe-reviewer",
• URL = "https://www.biorxiv.org/content/10.1101/2020.03.13.991216v1",
• DOI = "doi:10.3389/fncir.2020.00042",
• abstract = "In vivo 1-photon (1p) calcium imaging is an increasingly prevalent method in behavioral neuroscience. Numerous analysis pipelines have been developed to improve the reliability and scalability of pre-processing and ROI extraction for these large calcium imaging datasets. Despite these advancements in pre-processing methods, manual curation of the extracted spatial footprints and calcium traces of neurons remains important for quality control. Here, we propose an additional semi-automated curation step for sorting spatial footprints and calcium traces from putative neurons extracted using the popular constrained non-negative matrix factorization for microendoscopic data (CNMF-E) algorithm. We used the automated machine learning (AutoML) tools TPOT and AutoSklearn to generate classifiers to curate the extracted ROIs trained on a subset of human-labeled data. AutoSklearn produced the best performing classifier, achieving an F1 score greater than 92 percent on the ground truth test dataset. This automated approach is a useful strategy for filtering ROIs with relatively few labeled data points and can be easily added to pre-existing pipelines currently using CNMF-E for ROI extraction.",
• notes = "Hospital for Sick Children, Neurosciences and Mental Health, Toronto, ON, Canada

  The datasets and code generated for this study can be found in the cnmfe-reviewer GitHub repository (https://github.com/jf-lab/cnmfe-reviewer).

  PMID: 32792911; PMCID: PMC7384547",

}

Genetic Programming entries for Lina M Tran Andrew J Mocle Adam I Ramsaran Alexander D Jacob Paul W Frankland Sheena A Josselyn

Citations