WormPose: Image synthesis and convolutional networks for pose estimation in C. elegans
| العنوان: | WormPose: Image synthesis and convolutional networks for pose estimation in C. elegans |
|---|---|
| المؤلفون: | Antonio de Lisboa Lopes Costa, Liam O'Shaughnessy, Greg J. Stephens, Laetitia Hebert, Tosif Ahamed |
| المساهمون: | Physics of Living Systems, LaserLaB - Molecular Biophysics |
| المصدر: | PLoS Computational Biology PLoS Computational Biology, 17(4):e1008914, 1-20. Public Library of Science Hebert, L, Ahamed, T, Costa, A C, O’Shaughnessy, L & Stephens, G J 2021, ' WormPose : Image synthesis and convolutional networks for pose estimation in C. elegans ', PLoS Computational Biology, vol. 17, no. 4, e1008914, pp. 1-20 . https://doi.org/10.1371/journal.pcbi.1008914 PLoS Computational Biology, Vol 17, Iss 4, p e1008914 (2021) |
| بيانات النشر: | Public Library of Science, 2021. |
| سنة النشر: | 2021 |
| مصطلحات موضوعية: | 0301 basic medicine, Nematoda, Machine vision, Computer science, Image Processing, Velocity, Markov models, Social Sciences, Convolutional neural network, 0302 clinical medicine, Psychology, Hidden Markov models, Biology (General), Hidden Markov model, Ecology, Artificial neural network, Animal Behavior, Physics, Applied Mathematics, Simulation and Modeling, Eukaryota, Classical Mechanics, Animal Models, Generative model, Computational Theory and Mathematics, Experimental Organism Systems, Modeling and Simulation, Physical Sciences, Engineering and Technology, Algorithms, Research Article, Computer and Information Sciences, Neural Networks, QH301-705.5, Imaging Techniques, ComputingMethodologies_IMAGEPROCESSINGANDCOMPUTERVISION, Image processing, Research and Analysis Methods, Models, Biological, Synthetic data, 03 medical and health sciences, Cellular and Molecular Neuroscience, Motion, SDG 17 - Partnerships for the Goals, Model Organisms, Genetics, Animals, Computer Simulation, Caenorhabditis elegans, Molecular Biology, Pose, Ecology, Evolution, Behavior and Systematics, Behavior, business.industry, Organisms, Biology and Life Sciences, Pattern recognition, Probability theory, Invertebrates, 030104 developmental biology, Signal Processing, Animal Studies, Caenorhabditis, Artificial intelligence, Neural Networks, Computer, business, Zoology, 030217 neurology & neurosurgery, Mathematics, Neuroscience |
| الوصف: | An important model system for understanding genes, neurons and behavior, the nematode worm C. elegans naturally moves through a variety of complex postures, for which estimation from video data is challenging. We introduce an open-source Python package, WormPose, for 2D pose estimation in C. elegans, including self-occluded, coiled shapes. We leverage advances in machine vision afforded from convolutional neural networks and introduce a synthetic yet realistic generative model for images of worm posture, thus avoiding the need for human-labeled training. WormPose is effective and adaptable for imaging conditions across worm tracking efforts. We quantify pose estimation using synthetic data as well as N2 and mutant worms in on-food conditions. We further demonstrate WormPose by analyzing long (∼ 8 hour), fast-sampled (∼ 30 Hz) recordings of on-food N2 worms to provide a posture-scale analysis of roaming/dwelling behaviors. Author summary Recent advances in machine learning have enabled the high-resolution estimation of bodypoint positions of freely behaving animals, but manual labeling can render these methods imprecise and impractical, especially in highly deformable animals such as the nematode C. elegans. Such animals also frequently coil, resulting in complicated shapes whose ambiguity presents difficulties for standard pose estimation methods. Efficiently solving coiled shapes in C. elegans, exhibited in a variety of important natural contexts, is the primary limiting factor for fully automated high-throughput behavior analysis. WormPose provides pose estimation that works across imaging conditions, naturally complements existing worm trackers, and harnesses the power of deep convolutional networks but with an image generator to automatically provide precise image-centerline pairings for training. We apply WormPose to on-food recordings, finding a near absence of deep δ-turns. We also show that incoherent body motions in the dwell state, which do not translate the worm, have been misidentified as an increase in reversal rate by previous, centroid-based methods. We expect that the combination of a body model and image synthesis demonstrated in WormPose will be both of general interest and important for future progress in precise pose estimation in other slender-bodied and deformable organisms. |
| اللغة: | English |
| تدمد: | 1553-7358 1553-734X |
| DOI: | 10.1371/journal.pcbi.1008914 |
| URL الوصول: | https://explore.openaire.eu/search/publication?articleId=doi_dedup___::ce02b72fe6f7f628b3b8380cc2b6449c http://europepmc.org/articles/PMC8078761 |
| Rights: | OPEN |
| رقم الانضمام: | edsair.doi.dedup.....ce02b72fe6f7f628b3b8380cc2b6449c |
| قاعدة البيانات: | OpenAIRE |
| تدمد: | 15537358 1553734X |
|---|---|
| DOI: | 10.1371/journal.pcbi.1008914 |