Quantitative Digital Microscopy with Deep Learning

Abstract

Video microscopy has a long history of providing insights and breakthroughs for a broad range of disciplines, from physics to biology. Image analysis to extract quantitative information from video microscopy data has traditionally relied on algorithmic approaches, which are often difficult to implement, time consuming, and computationally expensive. Recently, alternative data-driven approaches using deep learning have greatly improved quantitative digital microscopy, potentially offering automatized, accurate, and fast image analysis. However, the combination of deep learning and video microscopy remains underutilized primarily due to the steep learning curve involved in developing custom deep-learning solutions. To overcome this issue, we introduce a software, DeepTrack 2.0, to design, train and validate deep-learning solutions for digital microscopy. We use it to exemplify how deep learning can be employed for a broad range of applications, from particle localization, tracking and characterization to cell counting and classification. Thanks to its user-friendly graphical interface, DeepTrack 2.0 can be easily customized for user-specific applications, and, thanks to its open-source object-oriented programming, it can be easily expanded to add features and functionalities, potentially introducing deep-learning-enhanced video microscopy to a far wider audience.

arXiv comment25 pages; 13 figures

References in corpus (14)

• Deep-STORM: super-resolution single-molecule microscopy by deep learning
• Advanced Steel Microstructural Classification by Deep Learning Methods
• PhaseStain: Digital staining of label-free quantitative phase microscopy images using deep learning
• DeepPap: Deep Convolutional Networks for Cervical Cell Classification
• Characterizing and tracking single colloidal particles with video holographic microscopy
• Extended depth-of-field in holographic image reconstruction using deep learning based auto-focusing and phase-recovery
• Convolutional neural networks automate detection for tracking of submicron scale particles in 2D and 3D
• Classification of diffusion modes in single-particle tracking data: Feature-based versus deep-learning approach
• Cross-modality deep learning brings bright-field microscopy contrast to holography
• Measurement of Anomalous Diffusion Using Recurrent Neural Networks
• Machine-learning techniques for fast and accurate feature localization in holograms of colloidal particles
• Convolutional Network for Attribute-driven and Identity-preserving Human Face Generation
• CATCH: Characterizing and Tracking Colloids Holographically using deep neural networks
• Stabilizing Adversarial Nets With Prediction Methods

Cited by in corpus (15)

• Geometric deep learning reveals the spatiotemporal fingerprint of microscopic motion
• Emerging Optical Microscopy Techniques for Electrochemistry
• Light, Matter, Action: Shining light on active matter
• Extracting quantitative biological information from brightfield cell images using deep learning
• Soft Metamaterials: Adaptation and Intelligence
• The 2024 Motile Active Matter Roadmap
• Quantitative evaluation of methods to analyze motion changes in single-particle experiments
• Active droploids
• Deep Learning for Optical Tweezers
• Roadmap for Animate Matter
• Microplankton life histories revealed by holographic microscopy and deep learning
• Tracking Janus microswimmers in 3D with Machine Learning
• Faster calculations of optical trapping using neural networks trained by T-matrix data: an application to micro and nanoplastics
• Precise localization of corneal reflections in eye images using deep learning trained on synthetic data
• LEyes: A Lightweight Framework for Deep Learning-Based Eye Tracking using Synthetic Eye Images