Convolutional neural networks automate detection for tracking of submicron-scale particles in 2D and 3D

• Published in: Proceedings of the National Academy of Sciences - PNAS Vol. 115; no. 36; pp. 9026 - 9031
• Main Authors: Newby, Jay M., Schaefer, Alison M., Lee, Phoebe T., Forest, M. Gregory, Lai, Samuel K.
• Format: Journal Article
• Language: English
• Published: United States National Academy of Sciences 04.09.2018
• Subjects: Artificial intelligence; Artificial neural networks; Automation; Biological Sciences; Biology; Biophysics and Computational Biology; Computer simulation; Data analysis; Data processing; Heterogeneity; Identification methods; Learning algorithms; Localization; Machine Learning; Mechanical properties; Nanoparticles; Neural networks; Neural Networks (Computer); Parameter identification; Particle Size; Particle tracking; Pharmacology; Physical Sciences; Species; artificial neural network; particle tracking; machine learning; quantitative biology; bioimaging
• ISSN: 0027-8424; 1091-6490; 1091-6490
• DOI: 10.1073/pnas.1804420115

Particle tracking is a powerful biophysical tool that requires conversion of large video files into position time series, i.e., traces of the species of interest for data analysis. Current tracking methods, based on a limited set of input parameters to identify bright objects, are ill-equipped to handle the spectrum of spatiotemporal heterogeneity and poor signal-to-noise ratios typically presented by submicron species in complex biological environments. Extensive user involvement is frequently necessary to optimize and execute tracking methods, which is not only inefficient but introduces user bias. To develop a fully automated tracking method, we developed a convolutional neural network for particle localization from image data, comprising over 6,000 parameters, and used machine learning techniques to train the network on a diverse portfolio of video conditions. The neural network tracker provides unprecedented automation and accuracy, with exceptionally low false positive and false negative rates on both 2D and 3D simulated videos and 2D experimental videos of difficult-to-track species.