Compact model forecasts neurite growth and ranks difficulty accurately
MGRD: Compact morphology-gated residual diffusion for variance-aware cross-domain neurite forecasting
Machine Learning
Summary
Tracking the tiny branches of nerve cells over time is hard and slow because it requires lots of detailed imaging. The authors created a new computer model called MGRD that predicts how these branches might grow in the future while showing different possible outcomes, not just one guess. This model is smaller, faster, and more accurate than previous ones, and it can even estimate how hard it is to predict certain cases. This can help scientists reduce the amount of imaging needed and focus on the most uncertain predictions.
What this means in practice
- •For neuroscience lab technicians: Reduce extensive time-lapse imaging by forecasting neurite growth across different neuron types, speeding up experiments that study nerve development and disease.
- •For microscopy core facility managers: Prioritize imaging tasks by ranking which neurite forecasts have higher uncertainty, improving efficiency in resource allocation for long-term microscopy studies.
Authors
Tsung Yeh Hsieh, Cosmin Anitescu, Chunghwan Kim, Victoria A. Webster-Wood, Yongjie Jessica Zhang
Abstract
Tracking neurite morphology over time helps characterize structural changes during neuronal development and deterioration, but long-term time-lapse imaging is resource-intensive and difficult to scale. Forecasting future morphology could reduce this burden. Existing neurite digital-twin models such as gated spatiotemporal attention (gSTA) produce a single deterministic forecast without representing variability among plausible futures. We introduce Morphology-Gated Residual Diffusion (MGRD), a compact stochastic surrogate that jointly forecasts twenty future neurite-morphology frames from ten observed frames while conditioning on morphology features derived from the latest observation. On controlled phase-field trajectories, MGRD reduces trajectory-wise mean MAE by 9.7% relative to a matched control while updating 4.46 times fewer parameters. On human iPSC-derived neuron microscopy, MGRD improves all four reported metrics over gSTA, including a 39.6% reduction in trajectory-wise mean MAE and a 45.3% increase in skeleton F1. Without mouse-domain retraining or fine-tuning, MGRD also improves MAE and skeleton F1 on mouse cortical-neurosphere microscopy across 10-40-min sampling intervals and forecast horizons beyond 13 hours. Repeated sampling provides a case-level variance score for ranking forecast difficulty. Retaining approximately 60% of the lowest-variance cases reduces mean MAE by 17.6% on iPSC microscopy and 16.8% on simulation data. MGRD uses 1.01% of gSTA's parameters, requires less than one tenth of its training-update time, and generates a 50-step DDIM trajectory 7.9% faster when morphology features are cached. These results establish MGRD as a compact stochastic surrogate for neurite-morphology forecasting and case prioritization across simulation and microscopy datasets.