Graphical-model framework for automated annotation of cell identities in dense cellular images
Open Access
- 24 February 2021
- journal article
- research article
- Published by eLife Sciences Publications, Ltd in eLife
Abstract
Although identifying cell names in dense image stacks is critical in analyzing functional whole-brain data enabling comparison across experiments, unbiased identification is very difficult, and relies heavily on researchers’ experiences. Here, we present a probabilistic-graphical-model framework, CRF_ID, based on Conditional Random Fields, for unbiased and automated cell identification. CRF_ID focuses on maximizing intrinsic similarity between shapes. Compared to existing methods, CRF_ID achieves higher accuracy on simulated and ground-truth experimental datasets, and better robustness against challenging noise conditions common in experimental data. CRF_ID can further boost accuracy by building atlases from annotated data in highly computationally efficient manner, and by easily adding new features (e.g. from new strains). We demonstrate cell annotation in Caenorhabditis elegans images across strains, animal orientations, and tasks including gene-expression localization, multi-cellular and whole-brain functional imaging experiments. Together, these successes demonstrate that unbiased cell annotation can facilitate biological discovery, and this approach may be valuable to annotation tasks for other systems.Funding Information
- National Institutes of Health (R21DC015652)
- National Institutes of Health (R01NS096581)
- National Institutes of Health (R01GM088333)
- National Science Foundation (1764406)
- National Science Foundation (1707401)
- National Institutes of Health (R01GM108962)
- National Institutes of Health (P40OD010440)
This publication has 77 references indexed in Scilit:
- Automated cellular annotation for high-resolution images of adult Caenorhabditis elegansBioinformatics, 2013
- ViBE-Z: a framework for 3D virtual colocalization analysis in zebrafish larval brainsNature Methods, 2012
- Simultaneous recognition and segmentation of cells: application in C.elegansBioinformatics, 2011
- Gromov–Wasserstein Distances and the Metric Approach to Object MatchingFoundations of Computational Mathematics, 2011
- V3D enables real-time 3D visualization and quantitative analysis of large-scale biological image data setsNature Biotechnology, 2010
- In vivo calcium imaging of OFF-responding ASK chemosensory neurons in C. elegansBiochimica et Biophysica Acta (BBA) - General Subjects, 2009
- A 3D digital atlas of C. elegans and its application to single-cell analysesNature Methods, 2009
- Automated analysis of embryonic gene expression with cellular resolution in C. elegansNature Methods, 2008
- Dimensionality and Dynamics in the Behavior of C. elegansPLoS Computational Biology, 2008
- Cognate putative nuclear localization signal effects strong nuclear localization of a GFP reporter and facilitates gene expression studies in Caenorhabditis elegansBioTechniques, 2007