U-Net 3+ for Anomalous Diffusion Analysis enhanced with Mixture Estimates (U-AnD-ME) in particle-tracking data

TL;DR

This paper introduces U-AnD-ME, a machine learning framework combining U-Net 3+ and Gaussian mixture models, to improve the analysis of anomalous diffusion in particle-tracking data, especially in noisy or short trajectories.

Contribution

It presents a novel neural network-based method that outperforms existing approaches in characterizing anomalous diffusion from complex biological data.

Findings

U-AnD-ME outperformed all other methods in the 2024 Anomalous Diffusion Challenge.

The framework accurately segments trajectories and infers diffusion properties.

It demonstrates robustness in analyzing short, noisy trajectories.

Abstract

Biophysical processes within living systems rely on encounters and interactions between molecules in complex environments such as cells. They are often described by anomalous diffusion transport. Recent advances in single-molecule microscopy and particle-tracking techniques have yielded an abundance of data in the form of videos and trajectories that contain critical information about these biologically significant processes. However, standard approaches for characterizing anomalous diffusion from these measurements often struggle in cases of practical interest, e.g. due to short, noisy trajectories. Fully exploiting this data therefore requires the development of advanced analysis methods -- a core goal at the heart of the recent international Anomalous Diffusion Challenges. Here, we introduce a novel machine-learning framework, U-net 3+ for Anomalous Diffusion analysis enhanced with Mixture Estimates (U-AnD-ME), that applies a U-Net 3+ based neural network alongside Gaussian mixture models to enable highly accurate characterisation of single-particle tracking data. In the 2024 Anomalous Diffusion Challenge, U-AnD-ME outperformed all other participating methods for the analysis of two-dimensional anomalous diffusion trajectories at both single-trajectory and ensemble levels. Using a large dataset inspired by the Challenge, we further characterize the performance of U-AnD-ME in segmenting trajectories and inferring anomalous diffusion properties.