BigNeuron: a resource to benchmark and predict performance of algorithms for automated tracing of neurons in light microscopy datasets
more »
- Southeast University, Nanjing (China)
- Microsoft Corporation, Redmond, WA (United States)
- Tencent AI Lab, Bellevue, WA (United States)
- Argonne National Laboratory (ANL), Argonne, IL (United States)
- Kaya Medical, Seattle, WA (United States)
- University of Cassino and Southern Lazio (Italy)
- George Mason University, Fairfax, VA (United States)
- Beijing University of Technology (China); Beijing International Collaboration Base on Brain Informatics and Wisdom Services (China)
- Nuctech Netherlands, Rotterdam (Netherlands)
- Howard Hughes Medical Institute, Ashburn, VA (United States)
- University of Alberta, Edmonton, AB (Canada)
- Southeast University, Nanjing (China); Anhui University, Hefei (China)
- Paige AI, New York, NY (United States)
- Lawrence Berkeley National Laboratory (LBNL), Berkeley, CA (United States); University of California, Berkeley, CA (United States)
- RIKEN, Tokyo (Japan). Center for Advanced Integrated Intelligence Platform Project (AIP); The University of Tokyo (Japan)
- University of Sydney, NSW (Australia)
- Texas A & M University, College Station, TX (United States)
- University of Houston, TX (United States)
- National Taiwan University of Science and Technology, Taipei (Taiwan)
- Bournemouth University, Poole (United Kingdom)
- PROPHESEE, Paris (France)
- Columbia University, New York, NY (United States)
- Northern Illinois University, DeKalb, IL (United States)
- AWS AI, Seattle, WA (United Sttaes)
- Universidade Do Porto (Portugal)
- Massachusetts General Hospital and Harvard Medical School, Boston, MA (United States)
- Allen Institute for Brain Science, Seattle, WA (United States); The University of Georgia, Athens, GA (United States)
- Florida State University College of Medicine, Tallahassee, FL (United States)
- University of Cambridge (United Kingdom)
- Ecole Polytechnique Federale Lausanne (EPFL) (Switzerland)
- University of Michigan, Ann Arbor, MI (United States)
- Georgetown University, Washington, DC (United States)
- Georg-August-University Göttingen (Germany)
- Harvard University, Cambridge, MA (United States)
- Georgia State University, Atlanta, GA (United States)
- 42 ENS Paris-Saclay, CNRS, CentraleSupélec, LuMIn, Université Paris-Saclay, Gif-sur-Yvette (France)
- Max Planck Institute for Neurobiology of Behavior – caesar, Bonn (Germany)
- Howard Hughes Medical Institute, Ashburn, VA (United States); MRC Laboratory of Molecular Biology, Cambridge (United Kingdom); University of Cambridge (United Kingdom)
- Howard Hughes Medical Institute, Ashburn, VA (United States); University of Tokyo (Japan); University of Cologne (Germany)
- University of Minnesota, St Paul, MN (United States)
- Korea Institute of Science and Technology (KIST), Seoul (Korea, Republic of)
- University of Washington, Seattle, WA (United States)
- The Scripps Research Institute, La Jolla, CA (United States)
- Allen Institute for Brain Science, Seattle, WA (United States)
- National Tsing Hua University, Hsinchu (Taiwan)
- Tencent AI Lab, Shenzhen (China)
- Allen Institute for Brain Science, Seattle, WA (United States); University of British Columbia, Vancouver, BC (Canada)
- UCL Great Ormond Street Institute of Child Health, London (United Kingdom)
- The University of Georgia, Athens, GA (United States)
- Imperial College London (United Kingdom)
- Beijing University of Technology (China); Beijing International Collaboration Base on Brain Informatics and Wisdom Services (China); Maebashi Institute of Technology (Japan)
- Oak Ridge National Laboratory (ORNL), Oak Ridge, TN (United States). BioEnergy Science Center (BESC)
- Centre for Addiction and Mental Health, Toronto, ON (Canada); University of Toronto, Toronto, ON (Canada)
- University of New South Wales, Sydney, NSW (Australia)
BigNeuron is an open community bench-testing platform with the goal of setting open standards for accurate and fast automatic neuron tracing. We gathered a diverse set of image volumes across several species that is representative of the data obtained in many neuroscience laboratories interested in neuron tracing. Here, we report generated gold standard manual annotations for a subset of the available imaging datasets and quantified tracing quality for 35 automatic tracing algorithms. The goal of generating such a hand-curated diverse dataset is to advance the development of tracing algorithms and enable generalizable benchmarking. Together with image quality features, we pooled the data in an interactive web application that enables users and developers to perform principal component analysis, t-distributed stochastic neighbor embedding, correlation and clustering, visualization of imaging and tracing data, and benchmarking of automatic tracing algorithms in user-defined data subsets. The image quality metrics explain most of the variance in the data, followed by neuromorphological features related to neuron size. Furthermore, we observed that diverse algorithms can provide complementary information to obtain accurate results and developed a method to iteratively combine methods and generate consensus reconstructions. The consensus trees obtained provide estimates of the neuron structure ground truth that typically outperform single algorithms in noisy datasets. However, specific algorithms may outperform the consensus tree strategy in specific imaging conditions. Finally, to aid users in predicting the most accurate automatic tracing results without manual annotations for comparison, we used support vector machine regression to predict reconstruction quality given an image volume and a set of automatic tracings.
- Research Organization:
- Lawrence Berkeley National Laboratory (LBNL), Berkeley, CA (United States)
- Sponsoring Organization:
- National Institutes of Health (NIH); USDOE Office of Science (SC)
- Grant/Contract Number:
- AC02-05CH11231
- OSTI ID:
- 2229298
- Journal Information:
- Nature Methods, Journal Name: Nature Methods Journal Issue: 6 Vol. 20; ISSN 1548-7091
- Publisher:
- Nature Publishing GroupCopyright Statement
- Country of Publication:
- United States
- Language:
- English
Similar Records
Resolving local ambiguity using semantics of shape.
An Open Combinatorial Diffraction Dataset Including Consensus Human and Machine Learning Labels with Quantified Uncertainty for Training New Machine Learning Models
Automated Tracing and Segmentation Tool for Migrating Neurons in 4D Confocal Imagery
Conference
·
Sat May 01 00:00:00 EDT 2010
·
OSTI ID:1012748
An Open Combinatorial Diffraction Dataset Including Consensus Human and Machine Learning Labels with Quantified Uncertainty for Training New Machine Learning Models
Journal Article
·
Tue Jun 08 20:00:00 EDT 2021
· Integrating Materials and Manufacturing Innovation
·
OSTI ID:1798722
Automated Tracing and Segmentation Tool for Migrating Neurons in 4D Confocal Imagery
Conference
·
Mon Dec 31 23:00:00 EST 2012
·
OSTI ID:1092287