SomaSeg: A robust neuron identification framework for two-photon imaging video.

ABSTRACT

Accurate neuron identification is fundamental to the analysis of neuronal population dynamics and signal extraction in fluorescence videos. However, several factors such as severe imaging noise, out-of-focus neuropil contamination, and adjacent neuron overlap would impair the performance of neuron identification algorithms and lead to errors in neuron shape and calcium activity extraction, or ultimately compromise the reliability of analysis conclusions. Herein, to address these challenges, we developed a novel cascade framework - SomaSeg that combines Duffing denoising, neuropil contamination defogging and stacked instance differentiating. Compared with the state-of-the-art neuron identification methods, both simulation and actual experimental results demonstrate that SomaSeg framework is robust to noise, insensitive to out-of-focus contamination and effective in dealing with overlapping neurons in actual complex imaging scenarios, providing a widely applicable framework for two-photon video processing.