Semantic Segmentation of Anomalous Diffusion Using Deep Convolutional Networks

Abstract

Heterogeneous dynamics commonly emerges in anomalous diffusion with intermittent transitions of diffusion states but proves challenging to identify using conventional statistical methods. To effectively capture these transient changes of diffusion states, we propose a deep learning model (U-AnDi) for the semantic segmentation of anomalous diffusion trajectories. This model is developed with the dilated causal convolution (DCC), gated activation unit (GAU), and U-Net architecture. The study addresses two key subtasks related to trajectory segmentation and changepoint detection, concentrating on variations in diffusion exponents and dynamic models. Additionally, extended analyses are conducted on the segmentation of single-model trajectories, multi-state biological trajectories, and anomalous diffusion with added long-time correlations. By rationally designing comparative models and evaluating the performance of U-AnDi against these models, we discover that U-AnDi consistently outperforms other models across all segmentation tasks, thereby affirming its superiority in the field. This performance edge also sheds light on the interpretability of U-AnDi's core components: DCC, GAU, and U-Net. The clarity with which these components contribute to U-AnDi's success underscores their congruence with the intrinsic physics underlying anomalous diffusion. Furthermore, our model is examined using real-world anomalous diffusion data: the diffusion of transmembrane proteins on cell membrane surfaces, and the segmentation results are highly consistent with experimental observations. Our findings could offer a heuristic deep learning solution for the detection of heterogeneous dynamics in single-molecule/particle tracking experiments, and have the potential to be generalized as a universal scheme for time-series segmentation.

26 pages, 18 figures

References in corpus (18)

• Understanding individual human mobility patterns
• The Medical Segmentation Decathlon
• Anomalous transport in the crowded world of biological cells
• Measurement of Anomalous Diffusion Using Recurrent Neural Networks
• Bayesian deep learning for error estimation in the analysis of anomalous diffusion
• Geometric deep learning reveals the spatiotemporal fingerprint of microscopic motion
• Classification, inference and segmentation of anomalous diffusion with recurrent neural networks
• Machine-Learning Solutions for the Analysis of Single-Particle Diffusion Trajectories
• Characterization of anomalous diffusion classical statistics powered by deep learning (CONDOR)
• Learning physical properties of anomalous random walks using graph neural networks
• Thermodynamic Uncertainty Relation Bounds the Extent of Anomalous Diffusion
• Inferring pointwise diffusion properties of single trajectories with deep learning
• Characterization of anomalous diffusion through convolutional transformers
• Unsupervised learning of anomalous diffusion data
• WaveNet-Based Deep Neural Networks for the Characterization of Anomalous Diffusion (WADNet)
• Scaling relations in the diffusive infiltration in fractals
• Variational inference of fractional Brownian motion with linear computational complexity
• Preface: Characterisation of Physical Processes from Anomalous Diffusion Data

Cited by in corpus (5)

• Machine Learning Analysis of Anomalous Diffusion
• Change-point detection in anomalous-diffusion trajectories utilising machine-learning-based uncertainty estimates
• Reinforcement Learning for Active Matter
• Super-resolved anomalous diffusion: deciphering the joint distribution of anomalous exponent and diffusion coefficient
• Recurrent neural network analysis of single trajectories switching between anomalous diffusion states