AnomalousNet: a hybrid approach with attention U-Nets and change point detection for accurate characterization of anomalous diffusion in video data

[EN] Anomalous diffusion is ubiquitous in systems ranging from intracellular transport and porous-medium flow to animal foraging, and its quantification requires robust methods that cope with short and noisy trajectories. We present AnomalousNet, a unified three-stage pipeline for analyzing anomalou...

ver descrição completa

Detalhes bibliográficos
Autores: Ahsini, Yusef, Escoto-Gomar, Marc, Conejero, J. Alberto|||0000-0003-3681-7533
Tipo de documento: artigo
Data de publicação:2025
País:España
Recursos:Universitat Politècnica de València (UPV)
Repositório:RiuNet. Repositorio Institucional de la Universitat Politécnica de Valéncia
Idioma:inglês
OAI Identifier:oai:riunet.upv.es:10251/227577
Acesso em linha:https://riunet.upv.es/handle/10251/227577
Access Level:Acceso aberto
Palavra-chave:U-Net
Anomalous diffusion
Fractional Brownian motion
Change point detection
AnDi Challenge
Descrição
Resumo:[EN] Anomalous diffusion is ubiquitous in systems ranging from intracellular transport and porous-medium flow to animal foraging, and its quantification requires robust methods that cope with short and noisy trajectories. We present AnomalousNet, a unified three-stage pipeline for analyzing anomalous particle dynamics. First, up to 64 particles per 128x128 field of view are tracked using the Crocker-Grier algorithm via Trackpy. Next, an Attention U-Net trained on over 8.6 x 104 simulated experiments infers frame-wise anomalous exponents alpha, generalized diffusion coefficients K, and discrete motion states. Finally, regime changes are identified using an L2-regularized, windowed pruned exact linear time change-point detection algorithm. On the 2nd Anomalous Diffusion Challenge benchmark the method achieved MAE(alpha)=0.32, MSLE(K)=0.10, state-classification F1=0.93, and change-point RMSE = 0.09, ranking second in the video single-trajectory task and ensemble task. These results demonstrate precise discrimination of subdiffusive, normal, and superdiffusive regimes, and frame-level identification of state transitions establishing AnomalousNet as a powerful tool for quantitative analysis of heterogeneous diffusion in video data.