Single molecule localization microscopy challenge: a biologically inspired benchmark for long-sequence modeling

2026-03-11

AI Summary

Existing state space models (SSMs) exhibit poor performance on sparse, stochastic, and temporally discontinuous biological imaging data, and lack dedicated evaluation benchmarks. To address this gap, this work introduces SMLM-C, the first biologically inspired benchmark for long-sequence modeling tailored to single-molecule localization microscopy (SMLM), encompassing both dSTORM and DNA-PAINT modalities. SMLM-C comprises ten simulated spatiotemporal point processes with ground-truth labels, designed to emulate realistic blinking dynamics. Systematic evaluation under controlled parameters reveals that SSMs struggle to model temporal discontinuities and heavy-tailed blinking behaviors, with performance degrading significantly as temporal sparsity increases. These findings expose fundamental limitations of current SSMs in real-world scientific imaging scenarios.

Technology Category

• Machine Learning: Large Multimodal Models (LMMs)
• Cognitive Modeling & Cognitive Systems: Neural Spike Coding
• Computer Vision: Medical and Biological Imaging

Application Category

• Security and Privacy: Security and privacy of machine learning and AI applications
• Search and Retrieval-Augmented AI: Large language models for search
• Graph Algorithms and Modeling for the Web: Foundation models and LLMs for Web-related graphs

Abstract

State space models (SSMs) have recently achieved strong performance on long sequence modeling tasks while offering improved memory and computational efficiency compared to transformer based architectures. However, their evaluation has been largely limited to synthetic benchmarks and application domains such as language and audio, leaving their behavior on sparse and stochastic temporal processes in biological imaging unexplored. In this work, we introduce the Single Molecule Localization Microscopy Challenge (SMLM-C), a benchmark dataset consisting of ten SMLM simulations spanning dSTORM and DNA-PAINT modalities with varying hyperparameter designed to evaluate state space models on biologically realistic spatiotemporal point process data with known ground truth. Using a controlled subset of these simulations, we evaluate state space models and find that performance degrades substantially as temporal discontinuity increases, revealing fundamental challenges in modeling heavy-tailed blinking dynamics. These results highlight the need for sequence models better suited to sparse, irregular temporal processes encountered in real world scientific imaging data.

Problem

• single molecule localization microscopy
• state space models
• spatiotemporal point processes
• temporal discontinuity
• heavy-tailed blinking dynamics

Innovation

• state space models
• single molecule localization microscopy
• spatiotemporal point processes
• biological imaging
• long-sequence modeling