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

TL;DR

This paper introduces a new benchmark dataset for evaluating state space models on biologically realistic single molecule localization microscopy data, revealing their limitations with sparse, irregular temporal processes.

Contribution

It presents the SMLM-C benchmark dataset for assessing models on biological imaging data and analyzes the performance of state space models on this challenging data.

Findings

Performance degrades with increased temporal discontinuity.

State space models struggle with heavy-tailed blinking dynamics.

Highlights need for models better suited to sparse biological data.

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.